# Simon Willison's Weblog

Published articles for Simon Willison's Weblog.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## llm-gemini 0.38.1

DevFeed: [llm-gemini 0.38.1](<https://devfeed.tech/articles/llm-gemini-0-38-1-147691.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/20/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-20T03:01:57Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [open-llm-leaderboard](<https://devfeed.tech/topics/open-llm-leaderboard.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-334](<https://devfeed.tech/tags/ai-2-334.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-205](<https://devfeed.tech/tags/gemini-205.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [gemini-llm](<https://devfeed.tech/tags/gemini-llm.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-072](<https://devfeed.tech/tags/generative-ai-2-072.md>), [google](<https://devfeed.tech/tags/google.md>), [google-422](<https://devfeed.tech/tags/google-422.md>), [grid](<https://devfeed.tech/tags/grid.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-656](<https://devfeed.tech/tags/llm-656.md>), [llm-reasoning](<https://devfeed.tech/tags/llm-reasoning.md>), [llm-reasoning-106](<https://devfeed.tech/tags/llm-reasoning-106.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-036](<https://devfeed.tech/tags/llms-2-036.md>), [neon](<https://devfeed.tech/tags/neon.md>), [pelican](<https://devfeed.tech/tags/pelican.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-162](<https://devfeed.tech/tags/pelican-riding-a-bicycle-162.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

llm-gemini 0.38.1 fixes reasoning-level support: Gemini 4 Carbon offers low, medium, and high, while Hydrogen and Neon also offer xhigh. In the author's comparison, Hydrogen at xhigh used 31,477 output tokens and cost 23.61 cents, versus 5,311 tokens and 3.99 cents at high; its pelican result was described as competitive with Gemini 4 Neon.

### Source excerpt

Release: llm-gemini 0.38.1 Gemini 4 Carbon only supports low, medium and high reasoning levels - but Gemini 4 Hydrogen and Gemini 4 Neon both have an extra xhigh level. I missed that when I added those models to the llm-gemini plugin, which is now fixed in this dot release. The xhigh setting for Hydrogen makes a significant difference. I updated my Gemini 4 comparison grid - note how Hydrogen at high used 5,311 output tokens and cost 3.99 cents, but the same model at xhigh used 31,477 output tokens, cost 23.61 cents, and produced a pelican that's competitive with Gemini 4 Neon: Tags: gemini, llm, llm-reasoning, pelican-riding-a-bicycle, ai, llms, google, generative-ai

## Token fraud is here and it's BAD (YouTube)

DevFeed: [Token fraud is here and it's BAD (YouTube)](<https://devfeed.tech/articles/token-fraud-is-here-and-it-s-bad-youtube-145292.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/20/token-fraud-is-here-and-its-bad/>)

Author: Simon Willison

Published: 2026-11-20T02:49:57Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [multi-accounting fraud](<https://devfeed.tech/topics/multi-accounting-fraud.md>), [online-fraud-prevention](<https://devfeed.tech/topics/online-fraud-prevention.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [Roblox](<https://devfeed.tech/topics/roblox.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-331](<https://devfeed.tech/tags/ai-2-331.md>), [ai-misuse](<https://devfeed.tech/tags/ai-misuse.md>), [ai-misuse-69](<https://devfeed.tech/tags/ai-misuse-69.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-069](<https://devfeed.tech/tags/generative-ai-2-069.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-033](<https://devfeed.tech/tags/llms-2-033.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-161](<https://devfeed.tech/tags/pelican-riding-a-bicycle-161.md>), [youtube](<https://devfeed.tech/tags/youtube.md>), [youtube-59](<https://devfeed.tech/tags/youtube-59.md>)

### AI overview

Claire Vo says groups are abusing ChatPRD's free trials and promo codes to obtain AI usage, resell tokens, and run commercial projects through its agent, including building Roblox and Fortnite maps. She reports seeing repeated prompts for SVGs of pelicans riding bicycles; the source speculates these may help identify underlying models, but does not establish that purpose. In response to the abuse, Vo is winding down free trials entirely.

### Source excerpt

Token fraud is here and it's BAD (YouTube) Claire Vo runs ChatPRD, an AI platform that helps product managers "turn an idea into a spec". The product has been live since the GPT-4 era, and Claire has been building it in public for much of that time. In this YouTube video (see also the accompanying Twitter post) Claire describes the flood of token fraud she has seen from groups abusing the product's free trial, sometimes just to get free AI usage but often to resell tokens or run other commercial enterprises on top of the ChatPRD agent. I am funding a international Roblox and Fortnite map studio. They run a loop of free trials and promo codes and then tunnel to my agent and use it to build Roblox and Fortnite maps. Apparently one of the common prompts Claire saw running through her agent involved SVGs of pelicans riding bicycles! Presumably the token scammers are using that to help sniff the underlying models - different model families have a definite signature, and I've used it like this in the past to try and guess the identity of stealth preview models on platforms like OpenRouter. Claire is winding down her free trials entirely, which sadly looks like the right decision in the face of this abuse. Tags: youtube, ai, generative-ai, llms, pelican-riding-a-bicycle, ai-misuse

## PostgreSQL 19 Released

DevFeed: [PostgreSQL 19 Released](<https://devfeed.tech/articles/postgresql-19-released-144325.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/19/postgresql-19/>)

Author: Simon Willison

Published: 2026-11-19T20:43:57Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [read-replica](<https://devfeed.tech/topics/read-replica.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-security-research](<https://devfeed.tech/tags/ai-security-research.md>), [ai-security-research-51](<https://devfeed.tech/tags/ai-security-research-51.md>), [applications](<https://devfeed.tech/tags/applications.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cookie](<https://devfeed.tech/tags/cookie.md>), [feature](<https://devfeed.tech/tags/feature.md>), [lag](<https://devfeed.tech/tags/lag.md>), [mediawiki](<https://devfeed.tech/tags/mediawiki.md>), [movie](<https://devfeed.tech/tags/movie.md>), [mysql](<https://devfeed.tech/tags/mysql.md>), [mysql-82](<https://devfeed.tech/tags/mysql-82.md>), [mysql-replication](<https://devfeed.tech/tags/mysql-replication.md>), [new-feature](<https://devfeed.tech/tags/new-feature.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [postgresql-161](<https://devfeed.tech/tags/postgresql-161.md>), [postgresql-19](<https://devfeed.tech/tags/postgresql-19.md>), [replica](<https://devfeed.tech/tags/replica.md>), [replication](<https://devfeed.tech/tags/replication.md>), [replication-32](<https://devfeed.tech/tags/replication-32.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [scaling-149](<https://devfeed.tech/tags/scaling-149.md>), [standby](<https://devfeed.tech/tags/standby.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [wal](<https://devfeed.tech/tags/wal.md>), [wikipedia](<https://devfeed.tech/tags/wikipedia.md>), [wikipedia-79](<https://devfeed.tech/tags/wikipedia-79.md>)

### AI overview

PostgreSQL 19 adds `WAIT FOR LSN` for applications that read from standbys: a session can wait for a replica to replay WAL through a specified log sequence number before querying, enabling read-your-writes consistency after a write on the primary. The excerpt's example captures the primary's WAL position after an update, saves it for a later request, then waits for that position before reading from the standby. An optional timeout causes an error if the replica has not caught up in time. The article relates this to MediaWiki's existing MySQL approach, which saves a primary binlog position and waits for the replica before reads, using `WAIT_FOR_EXECUTED_GTID_SET()` or, as a fallback, `MASTER_POS_WAIT()`.

### Source excerpt

PostgreSQL 19 Released Most years PostgreSQL ships a new release in September, but this year's release came two months later thanks mainly to the flurry of issues that the PostgreSQL team needed to address as part of the ongoing AI-reported vulnerability apocalypse. This release was definitely worth the wait. My favorite new feature is this one: For applications that send reads to standbys, PostgreSQL 19 adds "read-your-writes" consistency with the new WAIT FOR LSN command. A session on a standby can use WAIT FOR LSN to wait until the standby has replayed the write-ahead log (WAL) up to a specific log sequence number (LSN) before running a query, so the application can read data it just wrote on the primary. In practice, that looks like this: UPDATE movie SET genre = 'Dramatic' WHERE genre = 'Drama'; SELECT pg_current_wal_insert_lsn(); That returns a value like 0/0306EE20. Store that somewhere (a signed cookie would work) such that on a subsequent request your application can do: WAIT FOR LSN '0/0306EE20' WITH (TIMEOUT '0.1s'); SELECT * FROM movie WHERE genre = 'Drama'; The timeout is optional - if you provide one you'll get an error if the replica you are talking to doesn't catch up within the specified time. I first encountered this pattern in Wikipedia, which has a hand-rolled version of this built against MySQL replication: In addition to this, MediaWiki attempts to ensure that the user sees events occurring on the wiki in chronological order. A few seconds of lag can be tolerated, as long as the user sees a consistent picture from subsequent requests. This is done by saving the primary binlog position in the session, and then at the start of each request, waiting for the replica to catch up to that position before doing any reads from it. Here's the relevant MediaWiki code, which these days uses MySQL's WAIT_FOR_EXECUTED_GTID_SET() function and falls back to MASTER_POS_WAIT(). Via Lobste.rs Tags: mysql, postgresql, replication, scaling, wikipedia, ai-security-r

## llm-gemini 0.38

DevFeed: [llm-gemini 0.38](<https://devfeed.tech/articles/llm-gemini-0-38-143027.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/18/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-18T23:59:20Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [1-4](<https://devfeed.tech/tags/1-4.md>), [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-330](<https://devfeed.tech/tags/ai-2-330.md>), [also](<https://devfeed.tech/tags/also.md>), [animation](<https://devfeed.tech/tags/animation.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [argon](<https://devfeed.tech/tags/argon.md>), [better](<https://devfeed.tech/tags/better.md>), [brooklyn](<https://devfeed.tech/tags/brooklyn.md>), [but](<https://devfeed.tech/tags/but.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cool](<https://devfeed.tech/tags/cool.md>), [data](<https://devfeed.tech/tags/data.md>), [discount](<https://devfeed.tech/tags/discount.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-204](<https://devfeed.tech/tags/gemini-204.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-068](<https://devfeed.tech/tags/generative-ai-2-068.md>), [google](<https://devfeed.tech/tags/google.md>), [google-421](<https://devfeed.tech/tags/google-421.md>), [has](<https://devfeed.tech/tags/has.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-655](<https://devfeed.tech/tags/llm-655.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-244](<https://devfeed.tech/tags/llm-release-244.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-032](<https://devfeed.tech/tags/llms-2-032.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-160](<https://devfeed.tech/tags/pelican-riding-a-bicycle-160.md>), [yonkers-rising](<https://devfeed.tech/tags/yonkers-rising.md>), [yonkers-rising-4](<https://devfeed.tech/tags/yonkers-rising-4.md>)

### AI overview

Google's Gemini 4 Neon adds another pricing wrinkle to the Gemini 4 lineup: its listed rates are $3/$15 per million input/output tokens, above Carbon's temporary $2/$10 and Hydrogen's $1.50/$7.50. The author says Carbon is due to rise to $4/$20 on December 1, after which the announced ordering of Carbon, Neon, and Hydrogen by price would make sense; the announcement also omits Argon, previously priced the same as Carbon. In the author's pelican comparison, Neon looked better than Hydrogen and worse than Carbon, across tests at three reasoning levels. A separate experiment ran a prompt for a mapped Yonkers-mech animation in Google Antigravity at "extra" effort.

### Source excerpt

Release: llm-gemini 0.38 Today Google introduced Gemini 4 Neon. I wrote recently about how confusing the pricing for the Gemini 4 series was - Neon has somehow made this even worse. Previously the Gemini 4 lineup was Hydrogen, Argon, and Carbon - where Argon and Carbon were the same price, and Hydrogen was 3/4 of that price now but will be 1/4 of that price when the other two double an 1st December once their initial discount pricing expires. The Neon announcement pretends that Argon doesn't exist. Here's their new image explaining the model line-up: So the lineup now, from most to least expensive, is Carbon, Neon, Hydrogen. Except Carbon is currently half price, so right now Neon ($3/million input, $15/million output) is the most expensive of the three - then Carbon ($2/$10), then Hydrogen ($1.50/$7.50). I guess this will make more sense when Carbon doubles to $4/$20 on December 1st. I ran some pelicans through the three reasoning levels for Neon - low, medium, high. I dropped Argon from my Gemini 4 comparison grid - here's the new Gemini 4 lineup, where the Neon pelicans do look better than Hydrogen and worse than Carbon: As I've done with several recent models, I also fired the following prompt against Gemini 4 Neon on "extra" effort level in Google Antigravity: Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's the result. Tags: yonkers-rising, gemini, llm, pelican-riding-a-bicycle, ai, llms, llm-release, google, generative-ai

## datasette-arrows 0.1a0

DevFeed: [datasette-arrows 0.1a0](<https://devfeed.tech/articles/datasette-arrows-0-1a0-142012.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/18/datasette-arrows/>)

Author: Simon Willison

Published: 2026-11-18T17:09:59Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [apache-arrow](<https://devfeed.tech/topics/apache-arrow.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [CSV](<https://devfeed.tech/topics/csv.md>)

Tags: [apache-arrow](<https://devfeed.tech/tags/apache-arrow.md>), [csv](<https://devfeed.tech/tags/csv.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-568](<https://devfeed.tech/tags/datasette-1-568.md>), [file-formats](<https://devfeed.tech/tags/file-formats.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [projects](<https://devfeed.tech/tags/projects.md>), [projects-567](<https://devfeed.tech/tags/projects-567.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [tsv](<https://devfeed.tech/tags/tsv.md>)

### AI overview

Datasette 1.0a43 lets plugins implement streaming export formats through the `register_output_renderer()` hook. The `datasette-arrows` plugin applies this to Apache Arrow, allowing exports to stream in chunks instead of loading all rows into memory, as Datasette already does for CSV and TSV. Install it with `datasette install datasette-arrows` to add an Arrow option to the export dialog. In the version described, Arrow is not yet grouped with CSV and TSV under "All rows in this table"; the excerpt says that grouping is planned for a later alpha release.

### Source excerpt

Release: datasette-arrows 0.1a0 Datasette 1.0a43 added the ability for plugins to implement streaming export formats. Datasette core supports streaming CSV and TSV - you can export millions of lines of data from a table without needing to load it all into memory, because those two file formats support streaming data in chunks. The register_output_renderer() plugin hook can now be used to implement the same pattern for other formats. I've learned never to release a new plugin feature without accompanying it with a plugin that uses it. Claude Fable 5.2 suggested the Apache Arrow streaming format as a good option, and built this plugin in almost a single shot. Add the plugin to Datasette (datasette install datasette-arrows) and the export dialog gains this new Arrow option: This screenshot is from Datasette's main branch - the most recent release doesn't yet group streaming formats such as Arrow with the TSV and CSV in the "All rows in this table" section, but that's coming in the next alpha release. Tags: datasette, projects

## Quoting Daniel Stenberg

DevFeed: [Quoting Daniel Stenberg](<https://devfeed.tech/articles/quoting-daniel-stenberg-140866.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/18/daniel-stenberg/>)

Author: Simon Willison

Published: 2026-11-18T15:58:27Z

Content type: opinion

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [cURL](<https://devfeed.tech/topics/curl.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-329](<https://devfeed.tech/tags/ai-2-329.md>), [bugfixes](<https://devfeed.tech/tags/bugfixes.md>), [c](<https://devfeed.tech/tags/c.md>), [c-56](<https://devfeed.tech/tags/c-56.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-agents-268](<https://devfeed.tech/tags/coding-agents-268.md>), [curl](<https://devfeed.tech/tags/curl.md>), [curl-14](<https://devfeed.tech/tags/curl-14.md>), [daniel-stenberg](<https://devfeed.tech/tags/daniel-stenberg.md>), [daniel-stenberg-8](<https://devfeed.tech/tags/daniel-stenberg-8.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-067](<https://devfeed.tech/tags/generative-ai-2-067.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-031](<https://devfeed.tech/tags/llms-2-031.md>), [rust](<https://devfeed.tech/tags/rust.md>), [rust-118](<https://devfeed.tech/tags/rust-118.md>), [security](<https://devfeed.tech/tags/security.md>), [security-647](<https://devfeed.tech/tags/security-647.md>), [vibe-porting](<https://devfeed.tech/tags/vibe-porting.md>), [vibe-porting-9](<https://devfeed.tech/tags/vibe-porting-9.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

While agents rewrote 185,000 lines of curl's C code into 340,000 lines of Rust over a little more than three weeks, the curl project merged more than 300 commits, including over 200 bug fixes and a few vulnerability fixes, according to Daniel Stenberg. He says the project made another 200 commits the following month and raises the question of whether the Rust clones will keep pace. The excerpt provides no further comparison of the clones.

### Source excerpt

During the time these agents converted 185,000 lines of C code into 340,000 lines of Rust code (I counted), we merged over 300 commits in the actual curl project. We actually improved curl during these a little more than three weeks. A little over 200 bugfixes actually. 200 bugfixes that none of those rust rewrites have. We also fixed a few vulnerabilities. In another month we have done another 200 and maybe fixed a few more vulnerabilities. Will these clones keep up? -- Daniel Stenberg, Actual curl rewrites in Rust Tags: daniel-stenberg, curl, rust, security, coding-agents, c, ai, llms, generative-ai, vibe-porting

## The PSF end-of-year fundraiser

DevFeed: [The PSF end-of-year fundraiser](<https://devfeed.tech/articles/the-psf-end-of-year-fundraiser-140867.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/18/psf-end-of-year-fundraiser/>)

Author: Simon Willison

Published: 2026-11-18T14:44:48Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [PyPI](<https://devfeed.tech/topics/pypi.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Developer Events](<https://devfeed.tech/topics/developer-events.md>)

Tags: [community](<https://devfeed.tech/tags/community.md>), [community-events](<https://devfeed.tech/tags/community-events.md>), [developer](<https://devfeed.tech/tags/developer.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [ip](<https://devfeed.tech/tags/ip.md>), [program](<https://devfeed.tech/tags/program.md>), [psf](<https://devfeed.tech/tags/psf.md>), [psf-22](<https://devfeed.tech/tags/psf-22.md>), [pycon](<https://devfeed.tech/tags/pycon.md>), [pypi](<https://devfeed.tech/tags/pypi.md>), [python](<https://devfeed.tech/tags/python.md>), [python-1-295](<https://devfeed.tech/tags/python-1-295.md>), [python-software-foundation](<https://devfeed.tech/tags/python-software-foundation.md>), [security](<https://devfeed.tech/tags/security.md>), [sponsors](<https://devfeed.tech/tags/sponsors.md>), [sprints](<https://devfeed.tech/tags/sprints.md>), [staff](<https://devfeed.tech/tags/staff.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

The PSF has launched its end-of-year fundraiser to support Python development and its community. The supplied text says the foundation manages Python's intellectual property, operates PyPI, sponsors core developer sprints, supports community events including PyCon US, and employs staff to keep these efforts running. Its Developers in Residence program includes three security developers focused on Python, PyPI, and the wider ecosystem. The author encourages companies and people whose work benefits from Python to consider donating.

### Source excerpt

The PSF end-of-year fundraiser With my Python Software Foundation board director hat on: we've launched our end-of-year fundraiser for the non-profit that supports Python development and the Python community. If your company or your work benefits from Python, please consider donating this year! The PSF looks after the IP behind Python, operates PyPI, sponsors core developer sprints, supports community events (including running PyCon US every year), and employs a small and excellent staff team to keep everything running. We also operate the Developers in Residence program, which now includes three security developers (welcome, Brett Smith) focused on helping secure Python, PyPI, and the wider ecosystem. Tags: python, psf

## External sandboxes for coding agents

DevFeed: [External sandboxes for coding agents](<https://devfeed.tech/articles/external-sandboxes-for-coding-agents-138614.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/17/external-sandboxes-for-coding-agents/>)

Author: Simon Willison

Published: 2026-11-17T22:52:29Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-328](<https://devfeed.tech/tags/ai-2-328.md>), [alpine-linux](<https://devfeed.tech/tags/alpine-linux.md>), [api](<https://devfeed.tech/tags/api.md>), [apple](<https://devfeed.tech/tags/apple.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-136](<https://devfeed.tech/tags/claude-code-136.md>), [codex](<https://devfeed.tech/tags/codex.md>), [codex-62](<https://devfeed.tech/tags/codex-62.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-agents-267](<https://devfeed.tech/tags/coding-agents-267.md>), [containers](<https://devfeed.tech/tags/containers.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-066](<https://devfeed.tech/tags/generative-ai-2-066.md>), [http](<https://devfeed.tech/tags/http.md>), [https](<https://devfeed.tech/tags/https.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-030](<https://devfeed.tech/tags/llms-2-030.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [pattern](<https://devfeed.tech/tags/pattern.md>), [pi](<https://devfeed.tech/tags/pi.md>), [pi-7](<https://devfeed.tech/tags/pi-7.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [qemu](<https://devfeed.tech/tags/qemu.md>), [safely](<https://devfeed.tech/tags/safely.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [sandboxing](<https://devfeed.tech/tags/sandboxing.md>), [sandboxing-59](<https://devfeed.tech/tags/sandboxing-59.md>), [security](<https://devfeed.tech/tags/security.md>), [security-646](<https://devfeed.tech/tags/security-646.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>), [webassembly-137](<https://devfeed.tech/tags/webassembly-137.md>)

### AI overview

The external sandbox pattern keeps the coding agent outside a dedicated environment where its executed code runs, aiming to reduce the risk of harmful actions from mistakes or prompt injection. Three servers provide the same localhost API: external-sandbox-v86 uses Node.js, v86, and Alpine Linux in WebAssembly; external-sandbox-container uses a Python web server and Apple Containers; and external-sandbox-quicksand uses a Python web server with Microsoft's Quicksand library, QEMU, and Alpine Linux. Pi, Claude Code, and Codex can be configured to send execution requests to them. Optional HTTP/HTTPS allow-list proxying restricts which hosts sandboxed code can contact, while credential replacement supports authenticated API calls without exposing secrets to the agent. The excerpt presents these as implementations for experimenting with the pattern, not as a comparative security evaluation.

### Source excerpt

External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime Radiant, the AI research lab behind Superpowers and other projects. My post on the Prime Radiant blog introduces the external sandbox pattern, where code executed by the agent runs inside a dedicated sandbox while the agent itself lives outside of that sandbox. To demonstrate this pattern we've released three sandbox server implementations: external-sandbox-v86 runs a Node.js server which then uses v86 to run Alpine Linux inside WebAssembly. external-sandbox-container is a Python web server which runs the sandbox in Alpine Linux inside an Apple Containers instance. external-sandbox-quicksand is another Python web server, this time using Microsoft's Quicksand sandboxing library, which bundles QEMU and Alpine Linux in a Python package! Each of these implementations offers the same localhost API. You can then configure Pi, Claude Code, or Codex to send API calls to that sandbox any time they want to execute code. The sandboxes also include an optional HTTP/HTTPS allow-list proxy, so you can control exactly which hosts your agent's code is allowed to communicate with - plus a credential replacement mechanism to make authenticated API calls without sharing a secret with the agent. Here's the UI you can use to reconfigure that proxy while the sandbox is still running: I continue to be fascinated by the challenge of safely running untrusted code. This external sandbox pattern provides a neat way to experiment with different approaches. Tags: sandboxing, security, ai, webassembly, generative-ai, llms, coding-agents, claude-code, codex, pi

## GPT-6.2 Astra and GPT-6.2 Sol

DevFeed: [GPT-6.2 Astra and GPT-6.2 Sol](<https://devfeed.tech/articles/gpt-6-2-astra-and-gpt-6-2-sol-138615.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/17/gpt62-astra-and-sol/>)

Author: Simon Willison

Published: 2026-11-17T22:38:52Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [ChatGPT API](<https://devfeed.tech/topics/chatgpt-api.md>), [animations](<https://devfeed.tech/topics/animations.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-328](<https://devfeed.tech/tags/ai-2-328.md>), [animation](<https://devfeed.tech/tags/animation.md>), [animations](<https://devfeed.tech/tags/animations.md>), [api](<https://devfeed.tech/tags/api.md>), [astra](<https://devfeed.tech/tags/astra.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [brooklyn](<https://devfeed.tech/tags/brooklyn.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-fable](<https://devfeed.tech/tags/claude-fable.md>), [claude-fable-5-2](<https://devfeed.tech/tags/claude-fable-5-2.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [codex-cli](<https://devfeed.tech/tags/codex-cli.md>), [codex-desktop](<https://devfeed.tech/tags/codex-desktop.md>), [discount](<https://devfeed.tech/tags/discount.md>), [fable-5](<https://devfeed.tech/tags/fable-5.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-066](<https://devfeed.tech/tags/generative-ai-2-066.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-136](<https://devfeed.tech/tags/gpt-136.md>), [gpt-6-2](<https://devfeed.tech/tags/gpt-6-2.md>), [gpt-6-2-astra](<https://devfeed.tech/tags/gpt-6-2-astra.md>), [gpt-6-2-sol](<https://devfeed.tech/tags/gpt-6-2-sol.md>), [llm-pricing](<https://devfeed.tech/tags/llm-pricing.md>), [llm-pricing-99](<https://devfeed.tech/tags/llm-pricing-99.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-243](<https://devfeed.tech/tags/llm-release-243.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-030](<https://devfeed.tech/tags/llms-2-030.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-481](<https://devfeed.tech/tags/openai-481.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-159](<https://devfeed.tech/tags/pelican-riding-a-bicycle-159.md>), [sol](<https://devfeed.tech/tags/sol.md>), [theo-browne](<https://devfeed.tech/tags/theo-browne.md>), [theo-browne-5](<https://devfeed.tech/tags/theo-browne-5.md>), [yonkers-rising](<https://devfeed.tech/tags/yonkers-rising.md>), [yonkers-rising-3](<https://devfeed.tech/tags/yonkers-rising-3.md>)

### AI overview

GPT-6.2 Astra costs $8/$40 per million input/output tokens, 20% less than GPT-6 Astra, with cached input at $0.40 per million versus $1. GPT-6.2 Sol remains $2/$10, half the stated price of GPT-5.6 Sol. In an Ultra-effort Codex CLI test generating a 3D animation of Yonkers as a mech using OpenStreetMap, the author judged that neither new model handled the transformation as well as Claude Fable 5.2 or Gemini 4 Carbon. The excerpt also reports mixed reactions: Astra reportedly trails Fable 5.2 on some benchmarks, and a reviewer criticized its tendency during long tasks to ask users obscure implementation questions that could block progress.

### Source excerpt

GPT-6.2 Astra and GPT-6.2 Sol OpenAI: We're introducing GPT-6.2 Astra, our new frontier model for your hardest projects, and GPT-6.2 Sol, our efficient, versatile model for everyday work. They're available in the API as gpt-6.2-astra and gpt-6.2-sol. I shipped LLM 0.38 with support for the new models. 6.2 Astra is 80% of the price of 6 Astra - $8/MTok input and $40/MTok output, the same price as Claude Fable 5.2 (which was also 80% of its predecessor). 6 Astra and Fable 5 were both $10/$50. The cached price is an even bigger discount - $0.40/million compared to $1/million for the older model. This is great news for longer running agentic sessions. GPT-6.2 Sol is the same $2/$10 price as 6.1 Sol and 6 Sol - which are half the price of GPT-5.6 Sol ($4/$20). Here are the pelicans for GPT-6.2 Sol and for GPT-6.2 Astra. The 6.2 Astra max pelican looks like this: I have a full comparison grid here, but here's how the high/xhigh/max pelicans compare with the previous Sol and Astra releases: I also ran my most recent benchmark prompt against the two models, using "Ultra' effort levels in the Codex CLI: Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's Sol and here's Astra. Neither of them did a good enough job of morphing Yonkers into a big mech, at least in comparison to Claude Fable 5.2 and Gemini 4 Carbon. This video showing the Astra and Sol animations playing out at the same time: I created that video using GPT-6.2 Astra (Ultra) in the Codex desktop app by prompting: https://static.simonwillison.net/static/2026/yonkers-gpt-6.2-astra-ultra/index.html and https://static.simonwillison.net/static/2026/yonkers-gpt-6.2-sol-ultra/index.html are two videos of the same thing by two different models I need a video of the first 10 seconds where the top half of the video plays the first and the bottom half plays the second I need an overlaid label of "GPT

## Running the full server-side Datasette Python app in the browser with service workers and Pyodide

DevFeed: [Running the full server-side Datasette Python app in the browser with service workers and Pyodide](<https://devfeed.tech/articles/running-the-full-server-side-datasette-python-app-in-the-browser-with-service-workers-and-pyodide-138121.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/17/datasette-lite/>)

Author: Simon Willison

Published: 2026-11-17T16:48:33Z

Content type: article

Language: en

Sources: [Simon Willison](<https://devfeed.tech/sources/simon-willison.md>), [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Web app](<https://devfeed.tech/topics/webapp.md>), [Back end](<https://devfeed.tech/topics/backend.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [bug](<https://devfeed.tech/tags/bug.md>), [csv](<https://devfeed.tech/tags/csv.md>), [database](<https://devfeed.tech/tags/database.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-567](<https://devfeed.tech/tags/datasette-1-567.md>), [datasette-lite](<https://devfeed.tech/tags/datasette-lite.md>), [datasette-lite-27](<https://devfeed.tech/tags/datasette-lite-27.md>), [github](<https://devfeed.tech/tags/github.md>), [github-repository](<https://devfeed.tech/tags/github-repository.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [javascript-774](<https://devfeed.tech/tags/javascript-774.md>), [json](<https://devfeed.tech/tags/json.md>), [map](<https://devfeed.tech/tags/map.md>), [maps](<https://devfeed.tech/tags/maps.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [projects](<https://devfeed.tech/tags/projects.md>), [projects-566](<https://devfeed.tech/tags/projects-566.md>), [pyodide](<https://devfeed.tech/tags/pyodide.md>), [pyodide-53](<https://devfeed.tech/tags/pyodide-53.md>), [pypi](<https://devfeed.tech/tags/pypi.md>), [python](<https://devfeed.tech/tags/python.md>), [python-1-294](<https://devfeed.tech/tags/python-1-294.md>), [service-workers](<https://devfeed.tech/tags/service-workers.md>), [service-workers-6](<https://devfeed.tech/tags/service-workers-6.md>), [sql](<https://devfeed.tech/tags/sql.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [urls](<https://devfeed.tech/tags/urls.md>), [urls-83](<https://devfeed.tech/tags/urls-83.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>), [webassembly-136](<https://devfeed.tech/tags/webassembly-136.md>)

### AI overview

Datasette Lite now runs a near server-side Datasette experience in the browser using Pyodide and service workers. URL parameters can select a Datasette release or GitHub reference, install plugins, load SQLite, JSON, CSV or SQL resources, and choose among 163 WebAssembly SQLite builds. Remote files need open CORS headers. A service worker intercepts page and asset requests; session IDs route each browser tab to its own Datasette instance, while a web worker preserves state that Pyodide in a service worker may lose after about 30 seconds. This makes shareable demos and bug reproductions possible without hosting a server. The author says the approach could suit other Python apps, though SQLite works more readily than PostgreSQL or MySQL in WebAssembly.

### Source excerpt

Datasette Lite is my port of the Datasette Python application to run directly in the browser using WebAssembly and Pyodide. I've released a complete rewrite of Datasette Lite using service workers, and it's now almost indistinguishable from the real server-side application. You can now do all of the following, using a carefully crafted URL to lite.datasette.io: Load client-side Datasette to browse any SQLite database, JSON file, CSV file or SQL script Select a released version of Datasette to load from PyPI Load a specific commit, tag, or branch name from the Datasette GitHub repository Pick from over 100 versions of SQLite to use with Datasette Install additional Datasette plugins from PyPI or URLs to wheel files, including JavaScript visualization tools The ability to load specific Datasette references, plugins, and SQLite versions makes this a fantastic tool for linking to demos of work-in-progress features or bug reproductions, without needing to spin up a full web server to serve that demo. As an example, consider the following URL: https://lite.datasette.io/?install=datasette-maplibre&url=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/demo.db&metadata=https://gist.githubusercontent.com/simonw/39fa5d399465766039549912e2b3d291/raw/f6dfba99a75cbb8b5d9386223220eb52272767ee/metadata.yml#/demo/capitals_and_countries%23map=0/4.2/180&color=continent Follow that link and, after a short loading screen, you'll find yourself on a page that looks like this: That's Datasette running the new datasette-maplibre plugin, loading up a database of GeoJSON shapes of countries and displaying both a combined map and individual boundary maps in a table. Let's break down that URL to see what it's doing: https://lite.datasette.io/ ?install=datasette-maplibre &url=https://.../demo.db &metadata=https://.../metadata.yml #/demo/capitals_and_countries%23map=0/4.2/180&color=continent The ?install=datasette-maplibre inst

## llm 0.37.3

DevFeed: [llm 0.37.3](<https://devfeed.tech/articles/llm-0-37-3-136597.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/16/llm/>)

Author: Simon Willison

Published: 2026-11-16T23:57:26Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Release notes](<https://devfeed.tech/topics/release-notes.md>), [SQLite](<https://devfeed.tech/topics/sqlite.md>), [Homebrew](<https://devfeed.tech/topics/homebrew.md>), [version](<https://devfeed.tech/topics/version.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-326](<https://devfeed.tech/tags/ai-2-326.md>), [bug-fix](<https://devfeed.tech/tags/bug-fix.md>), [d-richard-hipp](<https://devfeed.tech/tags/d-richard-hipp.md>), [d-richard-hipp-21](<https://devfeed.tech/tags/d-richard-hipp-21.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-064](<https://devfeed.tech/tags/generative-ai-2-064.md>), [homebrew](<https://devfeed.tech/tags/homebrew.md>), [json](<https://devfeed.tech/tags/json.md>), [json-array](<https://devfeed.tech/tags/json-array.md>), [json-object](<https://devfeed.tech/tags/json-object.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-654](<https://devfeed.tech/tags/llm-654.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-028](<https://devfeed.tech/tags/llms-2-028.md>), [logging](<https://devfeed.tech/tags/logging.md>), [release](<https://devfeed.tech/tags/release.md>), [software](<https://devfeed.tech/tags/software.md>), [sql](<https://devfeed.tech/tags/sql.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [sqlite-491](<https://devfeed.tech/tags/sqlite-491.md>), [webassembly](<https://devfeed.tech/tags/webassembly.md>), [webassembly-135](<https://devfeed.tech/tags/webassembly-135.md>), [workaround](<https://devfeed.tech/tags/workaround.md>)

### AI overview

LLM 0.37.3 fixes a logging problem exposed by Homebrew's SQLite 3.54.1. A nested `json_array` passed directly to `json_object` now becomes SQL text, so the result is `{"a":"[1]"}`; SQLite 3.54.0 had returned `{"a":[1]}` because of a bug. The documented workaround is to wrap the subquery in `json(...)`, which marks its text as JSON: `json_object('a', json((select json_array(1))))`. The excerpt describes this fix but does not specify other release changes.

### Source excerpt

Release: llm 0.37.3 A bug fix release for LLM, mainly to cover a problem with the most recent Homebrew package of the software. Homebrew now ships the latest SQLite, 3.54.1, which includes a fix that broke LLM's logging code. Short version: in SQLite 3.54.0 the following SQL: select json_object('a', (select json_array(1))) Returns this: {"a":[1]} But in 3.54.1 the same query returns this: {"a":"[1]"} According to D. Richard Hipp: That was a bug fix. Per the documentation, (SELECT json_array(...)) returns SQL text, not JSON. Hence the 3.54.1 behavior is correct and 3.54.0 was a bug. The workaround looks like this: select json_object('a', json((select json_array(1)))) Tags: llm, webassembly, sqlite, generative-ai, ai, llms, d-richard-hipp

## datasette-maplibre 0.1a0

DevFeed: [datasette-maplibre 0.1a0](<https://devfeed.tech/articles/datasette-maplibre-0-1a0-134641.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/15/datasette-maplibre/>)

Author: Simon Willison

Published: 2026-11-15T23:58:36Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [GeoJSON](<https://devfeed.tech/topics/geojson.md>), [SVG](<https://devfeed.tech/topics/svg.md>), [Image](<https://devfeed.tech/topics/image.md>), [Fable](<https://devfeed.tech/topics/fable.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-325](<https://devfeed.tech/tags/ai-2-325.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-mythos-fable](<https://devfeed.tech/tags/claude-mythos-fable.md>), [claude-mythos-fable-49](<https://devfeed.tech/tags/claude-mythos-fable-49.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-566](<https://devfeed.tech/tags/datasette-1-566.md>), [datasette-lite](<https://devfeed.tech/tags/datasette-lite.md>), [datasette-lite-26](<https://devfeed.tech/tags/datasette-lite-26.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-063](<https://devfeed.tech/tags/generative-ai-2-063.md>), [geospatial](<https://devfeed.tech/tags/geospatial.md>), [geospatial-87](<https://devfeed.tech/tags/geospatial-87.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-027](<https://devfeed.tech/tags/llms-2-027.md>), [maplibre](<https://devfeed.tech/tags/maplibre.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [openstreetmap-58](<https://devfeed.tech/tags/openstreetmap-58.md>), [pyodide](<https://devfeed.tech/tags/pyodide.md>), [svg](<https://devfeed.tech/tags/svg.md>), [visualization](<https://devfeed.tech/tags/visualization.md>), [visualization-46](<https://devfeed.tech/tags/visualization-46.md>), [webgl](<https://devfeed.tech/tags/webgl.md>)

### AI overview

datasette-maplibre 0.1a0 combines MapLibre GL and OpenFreeMap in a Datasette geospatial plugin, bringing together features from datasette-cluster-map and datasette-leaflet-geojson. It shows SVG previews of GeoJSON shapes and loads their WebGL previews only when they scroll into view. A demo with GeoJSON shapes and latitude/longitude points on one map runs in Datasette Lite through Pyodide and WebAssembly.

### Source excerpt

Release: datasette-maplibre 0.1a0 The first new Datasette geospatial plugin in quite a while! This one combines the excellent MapLibre GL library with OpenFreeMap, the free vector map server operated by Zsolt Ero (you should sponsor Zsolt on GitHub.) I built most of this with a single prompt to Claude Fable 5.2: Look at datasette-cluster-map and datasette-leaflet-geojson plugins, then look at ~/dev/tools/openfreemap-demo.html - then build a brand new Datasette plugin that uses maplibreGL and openfreemap and combines the features of those other two plugins - but be creative and think outside the box for other useful features the plugin might have "Be creative and think outside the box" resulted in a few neat ideas - my favorite is that it displays SVG previews of GeoJSON shapes, then loads a WebGL preview only when they scroll into view. I also had Claude build a comprehensive demo which works in the latest Datasette Lite, so you can visit this link to load the plugin and a demo database in your browser via Pyodide and WebAssembly. I like this demo page showing both GeoJSON shapes and lat/lon points on the same map: Tags: visualization, generative-ai, datasette-lite, claude-mythos-fable, ai, llms, geospatial, openstreetmap, datasette

## datasette 1.0a43

DevFeed: [datasette 1.0a43](<https://devfeed.tech/articles/datasette-1-0a43-134642.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/15/datasette/>)

Author: Simon Willison

Published: 2026-11-15T23:20:27Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [view transitions](<https://devfeed.tech/topics/view-transitions.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>), [web animation](<https://devfeed.tech/topics/web-animation.md>)

Tags: [annotated-release-notes](<https://devfeed.tech/tags/annotated-release-notes.md>), [annotated-release-notes-63](<https://devfeed.tech/tags/annotated-release-notes-63.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [browsers-110](<https://devfeed.tech/tags/browsers-110.md>), [button](<https://devfeed.tech/tags/button.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [chrome-45](<https://devfeed.tech/tags/chrome-45.md>), [claude-fable-5-2](<https://devfeed.tech/tags/claude-fable-5-2.md>), [component](<https://devfeed.tech/tags/component.md>), [copy](<https://devfeed.tech/tags/copy.md>), [css](<https://devfeed.tech/tags/css.md>), [css-242](<https://devfeed.tech/tags/css-242.md>), [csv](<https://devfeed.tech/tags/csv.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-566](<https://devfeed.tech/tags/datasette-1-566.md>), [export](<https://devfeed.tech/tags/export.md>), [firefox](<https://devfeed.tech/tags/firefox.md>), [firefox-104](<https://devfeed.tech/tags/firefox-104.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [javascript-773](<https://devfeed.tech/tags/javascript-773.md>), [json](<https://devfeed.tech/tags/json.md>), [milestone](<https://devfeed.tech/tags/milestone.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [pretty](<https://devfeed.tech/tags/pretty.md>), [private](<https://devfeed.tech/tags/private.md>), [queries](<https://devfeed.tech/tags/queries.md>), [safari](<https://devfeed.tech/tags/safari.md>), [safari-70](<https://devfeed.tech/tags/safari-70.md>), [schema](<https://devfeed.tech/tags/schema.md>), [security](<https://devfeed.tech/tags/security.md>), [security-645](<https://devfeed.tech/tags/security-645.md>), [security-fixes](<https://devfeed.tech/tags/security-fixes.md>), [stream](<https://devfeed.tech/tags/stream.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [tsv](<https://devfeed.tech/tags/tsv.md>)

### AI overview

Datasette 1.0a43 adds streaming output renderers: built-in TSV and CSV exports use the feature, and plugins can stream every row in a table through `Response.stream()`. A security fix addressed private stored queries being exposed by title and SQL, though the exposed queries could not be executed. Other changes include a redesigned row-page JSON representation, a `<datasette-copy-button>` component, pretty-printed JSON column values, `DatasetteModal.confirm()`, and bug fixes. CSS multi-page view transitions make navigation feel more like an SPA while Datasette remains a multi-page app; the excerpt reports support in Safari and Chrome and anticipated support in Firefox 162.

### Source excerpt

Release: datasette 1.0a43 I've been leaning hard into Claude Fable 5.2 to help knock things off the 1.0 milestone, which is now 53% complete. The biggest 1.0 item in this release is streaming support for output renderers - the built-in TSV and CSV export mechanisms now use this as well, and plugins can register themselves as capable of streaming every row in a table in one go via the new Response.stream() method. There are a couple of security fixes, one of which I deemed deserving of a GitHub advisory: private stored queries could be exposed, granting access to the title and SQL of the query (but not allowing that query to be executed). There are dozens of smaller improvements. The row page JSON representation finally has a design suitable for 1.0. A new <datasette-copy-button> Web Component provides copy-schema in various places. JSON in columns on the row page can be pretty-printed. There's a new DatasetteModal.confirm() JavaScript utility method. Plus dozens of bug fixes, including contributions by Zihan Dai, Peter Olkhovets, Ilya Khalafi, and Ankita Advitot. The feature I'm most excited about is a pretty tiny one: I've added CSS multi-page view transitions to Datasette! Here's the commit - key CSS is as follows: /* Enable cross-document view transitions, for anyone without prefers-reduced-motion */ @media (prefers-reduced-motion: no-preference) { @view-transition { navigation: auto; } } /* .facet-results should morph from old position to new */ html:active-view-transition .content > .facet-results { view-transition-name: facet-results; } /* So should a .table-wrapper, provided it contains .rows-and-columns */ html:active-view-transition .table-wrapper:has(> table.rows-and-columns) { view-transition-name: rows-table; } With that in place, navigations within Datasette - still staunchly a multi-page application - feel more like an SPA. This works on Safari and Chrome at the moment and I believe supports for Firefox is due to land in Firefox 162 on December 8th 202

## datasette 0.65.6

DevFeed: [datasette 0.65.6](<https://devfeed.tech/articles/datasette-0-65-6-134638.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/15/datasette-2/>)

Author: Simon Willison

Published: 2026-11-15T23:18:17Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>)

Tags: [database](<https://devfeed.tech/tags/database.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-566](<https://devfeed.tech/tags/datasette-1-566.md>), [security](<https://devfeed.tech/tags/security.md>), [security-645](<https://devfeed.tech/tags/security-645.md>)

### AI overview

Datasette 0.65.6 backports a security fix from 1.0a43. Previously, a database registered with `add_database(db, name=..., route=...)` could be downloaded at `/<route>.db` by users denied access when its route differed from its name. The fix addresses that access-control issue.

### Source excerpt

Release: datasette 0.65.6 I backported a minor security fix from 1.0a43: Fixed a security issue where a database registered using add_database(db, name=..., route=...) with a route that differs from its name could be downloaded from /<route>.db by actors who were denied access to it. [...] Tags: security, datasette

## datasette-apps 0.4a0

DevFeed: [datasette-apps 0.4a0](<https://devfeed.tech/articles/datasette-apps-0-4a0-134640.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/15/datasette-apps/>)

Author: Simon Willison

Published: 2026-11-15T04:02:45Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Tool](<https://devfeed.tech/topics/tool.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [artifacts](<https://devfeed.tech/tags/artifacts.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-566](<https://devfeed.tech/tags/datasette-1-566.md>), [datasette-agent](<https://devfeed.tech/tags/datasette-agent.md>), [datasette-agent-26](<https://devfeed.tech/tags/datasette-agent-26.md>), [datasette-apps](<https://devfeed.tech/tags/datasette-apps.md>), [datasette-apps-11](<https://devfeed.tech/tags/datasette-apps-11.md>), [html](<https://devfeed.tech/tags/html.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [linking](<https://devfeed.tech/tags/linking.md>), [links](<https://devfeed.tech/tags/links.md>), [records](<https://devfeed.tech/tags/records.md>), [release](<https://devfeed.tech/tags/release.md>), [sql](<https://devfeed.tech/tags/sql.md>), [url](<https://devfeed.tech/tags/url.md>), [urls](<https://devfeed.tech/tags/urls.md>), [urls-82](<https://devfeed.tech/tags/urls-82.md>)

### AI overview

Datasette Apps 0.4a0 adds URL-fragment support: an app can receive and use `#fragments`, allowing one app to link to a specific view or record in another. Supported URL schemes are also reported to Datasette Agent to help it create apps that link to each other. The release describes combining a record-detail app with a separate search app that links to those records. Datasette Apps are sandboxed HTML and JavaScript apps that can run SQL queries against Datasette data.

### Source excerpt

Release: datasette-apps 0.4a0 Datasette Apps are sandboxed HTML and JavaScript applications that live inside Datasette - think Claude Artifacts, but these ones can run SQL queries against your data. 0.4a0 adds support for linking: you can link to an app with #fragments in the URL and the app can see and use those, plus supported URL schemes are reported back to Datasette Agent so it can help write apps that link to each other. This means you can have e.g. an app that shows details about a specific record, and a completely separate app that searches those records and links to their representations in the first app. Tags: datasette-agent, datasette-apps, datasette, urls

## datasette-agent 0.6a0

DevFeed: [datasette-agent 0.6a0](<https://devfeed.tech/articles/datasette-agent-0-6a0-134639.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/15/datasette-agent/>)

Author: Simon Willison

Published: 2026-11-15T03:49:47Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-325](<https://devfeed.tech/tags/ai-2-325.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-566](<https://devfeed.tech/tags/datasette-1-566.md>), [datasette-agent](<https://devfeed.tech/tags/datasette-agent.md>), [datasette-agent-26](<https://devfeed.tech/tags/datasette-agent-26.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-063](<https://devfeed.tech/tags/generative-ai-2-063.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-653](<https://devfeed.tech/tags/llm-653.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-027](<https://devfeed.tech/tags/llms-2-027.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [queries](<https://devfeed.tech/tags/queries.md>), [release](<https://devfeed.tech/tags/release.md>), [tables](<https://devfeed.tech/tags/tables.md>)

### AI overview

Datasette Agent 0.6a0 adds an agent prompt to the Datasette homepage, with support for hash-mentions of tables and queries. The release also includes accumulated small fixes, though the excerpt does not specify them.

### Source excerpt

Release: datasette-agent 0.6a0 Accumulated small fixes for Datasette Agent, my agent plugin for Datasette that lets you ask questions about your data. Most notably, it now adds an agent prompt directly to the Datasette homepage, with support for hash-mentions of tables and queries: Tags: datasette-agent, llm, datasette, llms, ai, generative-ai

## datasette-llm 0.1a11

DevFeed: [datasette-llm 0.1a11](<https://devfeed.tech/articles/datasette-llm-0-1a11-134390.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/14/datasette-llm/>)

Author: Simon Willison

Published: 2026-11-14T23:59:28Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-323](<https://devfeed.tech/tags/ai-2-323.md>), [api](<https://devfeed.tech/tags/api.md>), [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-561](<https://devfeed.tech/tags/datasette-1-561.md>), [datasette-agent](<https://devfeed.tech/tags/datasette-agent.md>), [datasette-agent-24](<https://devfeed.tech/tags/datasette-agent-24.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-061](<https://devfeed.tech/tags/generative-ai-2-061.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-652](<https://devfeed.tech/tags/llm-652.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-025](<https://devfeed.tech/tags/llms-2-025.md>), [lm-studio](<https://devfeed.tech/tags/lm-studio.md>), [local](<https://devfeed.tech/tags/local.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [localhost](<https://devfeed.tech/tags/localhost.md>), [model](<https://devfeed.tech/tags/model.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [openai](<https://devfeed.tech/tags/openai.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [qwen3-8-27b](<https://devfeed.tech/tags/qwen3-8-27b.md>), [uv](<https://devfeed.tech/tags/uv.md>), [uv-104](<https://devfeed.tech/tags/uv-104.md>)

### AI overview

datasette-llm 0.1a11 adds support for OpenAI-compatible endpoints, letting Datasette use LLMs hosted by services such as LM Studio, Ollama, or llama.cpp. The excerpt provides a `uvx` command that configures a model name and API base URL, then starts a Datasette Agent instance powered by the local model.

### Source excerpt

Release: datasette-llm 0.1a11 datasette-llm is the intermediate plugin for Datasette that supports configuring LLMs for use with other Datasette plugins. This release adds support for OpenAI-compatible endpoints, so you can configure Datasette to use an LLM hosted anywhere that talks the OpenAI pseudo-standard web protocol. This means that if you're running local models with LM Studio or Ollama or llama.cpp (which just hit v1.0.0) you can run Datasette via uvx like this: wget https://datasette.io/content.db uvx --with datasette-agent datasette \ --root --secret 1 \ -s plugins.datasette-llm.default_model '{ "model": "lmstudio-qwen", "model_name": "qwen/qwen3.8-27b", "api_base": "http://localhost:1234/v1" }' content.db And you'll get a local server running a Datasette Agent instance powered by your local model! Tags: uv, datasette-agent, llm, datasette, llms, ai, generative-ai

## datasette-leaflet 0.3

DevFeed: [datasette-leaflet 0.3](<https://devfeed.tech/articles/datasette-leaflet-0-3-133563.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/13/datasette-leaflet/>)

Author: Simon Willison

Published: 2026-11-13T22:30:54Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [cache-control](<https://devfeed.tech/topics/cache-control.md>), [project release](<https://devfeed.tech/topics/project-release.md>)

Tags: [datasette](<https://devfeed.tech/tags/datasette.md>), [datasette-1-559](<https://devfeed.tech/tags/datasette-1-559.md>), [leaflet](<https://devfeed.tech/tags/leaflet.md>), [leaflet-47](<https://devfeed.tech/tags/leaflet-47.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [openstreetmap-57](<https://devfeed.tech/tags/openstreetmap-57.md>), [plugin](<https://devfeed.tech/tags/plugin.md>)

### AI overview

The datasette-leaflet 0.3 release fixes OpenStreetMap tile requests that previously conflicted with the service's referrer policy. Datasette table pages sent `Referrer-Policy: no-referrer`, so plugins loading OpenStreetMap tiles did not send the required referrer. The plugin now sets `strict-origin-when-cross-origin` on tile requests, which sends the page's host without its full path. datasette-leaflet bundles Leaflet for use by other Datasette plugins.

### Source excerpt

Release: datasette-leaflet 0.3 OpenStreetMap have a very reasonable policy that hits to their hosted tile server should send a referrer header. Datasette table pages used the Referrer-Policy: no-referrer HTTP header, causing plugins that loaded tiles from OpenStreetMap to violate that policy. datasette-leaflet is the plugin that loads a bundled Leaflet so other Datasette plugins can depend on it. It now sets the referrer policy on the tile requests themselves to strict-origin-when-cross-origin, passing the host but not the full path to the page. Tags: leaflet, datasette, openstreetmap

## llm-gemini 0.37

DevFeed: [llm-gemini 0.37](<https://devfeed.tech/articles/llm-gemini-0-37-131236.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/12/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-12T22:55:19Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-322](<https://devfeed.tech/tags/ai-2-322.md>), [argon](<https://devfeed.tech/tags/argon.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-haiku](<https://devfeed.tech/tags/claude-haiku.md>), [claude-haiku-5-5](<https://devfeed.tech/tags/claude-haiku-5-5.md>), [code](<https://devfeed.tech/tags/code.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cost](<https://devfeed.tech/tags/cost.md>), [discount](<https://devfeed.tech/tags/discount.md>), [effort](<https://devfeed.tech/tags/effort.md>), [frontier-models](<https://devfeed.tech/tags/frontier-models.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-203](<https://devfeed.tech/tags/gemini-203.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [google-420](<https://devfeed.tech/tags/google-420.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-luna](<https://devfeed.tech/tags/gpt-6-luna.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-651](<https://devfeed.tech/tags/llm-651.md>), [llm-pricing](<https://devfeed.tech/tags/llm-pricing.md>), [llm-pricing-98](<https://devfeed.tech/tags/llm-pricing-98.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-024](<https://devfeed.tech/tags/llms-2-024.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-158](<https://devfeed.tech/tags/pelican-riding-a-bicycle-158.md>)

### AI overview

Gemini 4 Hydrogen is positioned as a lower-cost model for everyday work, coding, and Google Search's AI features, and as an execution model that can pair with Carbon and Argon. The author says Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens, only 25% less than Carbon and Argon at their current prices; those two are scheduled to double in price on December 1, 2026, making Hydrogen a 75% discount afterward. Google describes Argon as faster and using fewer tokens per turn than Carbon despite equal listed prices. The author reports a marked gap in pelican-generation quality for Hydrogen, but the comparison grid is omitted from the supplied text. The author also says Hydrogen remains far more expensive than Claude Haiku 5.5 and GPT-6 Luna.

### Source excerpt

Release: llm-gemini 0.37 Google launched Gemini 4 Hydrogen today - the lowest cost member of the Gemini 4 family. It's actually not too far off the price of its much bigger siblings, Carbon and Argon. I'm finding Gemini 4's pricing really confusing. Here's the pricing scheme: Model Dates Input ($/M) Cached input Output Gemini 4 Carbon Through Nov 30, 2026 $2.00 $0.10 $10.00 From Dec 1, 2026 $4.00 $0.20 $20.00 Gemini 4 Argon Through Nov 30, 2026 $2.00 $0.10 $10.00 From Dec 1, 2026 $4.00 $0.20 $20.00 Gemini 4 Hydrogen $1.50 $0.075 $7.50 Carbon and Argon are the same price, and both are scheduled to double in price on December 1st. If they're the same price, why have two different models? Google says that Argon "delivers Gemini 4 intelligence with faster responses and lower token spend per turn compared to Gemini 4 Carbon" - so it may be priced the same, but it will use less tokens per task. Hydrogen, supposedly the cheap model, is currently only a 25% discount on its more capable peers. The Hydrogen price will make more sense after December 1st, when it will represent a 75% discount. It's still considerably more expensive than Claude Haiku 5.5 and GPT-6 Luna - they're both $0.10/$0.50, so Hydrogen is 15x that. I had Hydrogen generate some pelicans. Here's a full comparison grid showing the pelicans for all three members of the Gemini 4 family at their three supported effort levels: Considering how close they are in price, the difference in pelican quality for Hydrogen is quite stark. Here's how Google describe Hydrogen's intended position in their mix of models: In real-world software development, while teams rely on frontier models like Carbon and Argon for deep architectural judgment when designing systems or untangling subtle bugs, they still need a fast, disciplined execution model for writing code, running tests, and verifying changes. Hydrogen is built to stand on its own as a model for everyday work -- or to pair with Carbon and Argon as the high-efficiency exec

## Gemini Decisions API

DevFeed: [Gemini Decisions API](<https://devfeed.tech/articles/gemini-decisions-api-129842.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/11/gemini-decisions-api/>)

Author: Simon Willison

Published: 2026-11-11T22:03:25Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [API](<https://devfeed.tech/topics/api.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-321](<https://devfeed.tech/tags/ai-2-321.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [decision-models-4](<https://devfeed.tech/tags/decision-models-4.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-202](<https://devfeed.tech/tags/gemini-202.md>), [gemini-decision-1](<https://devfeed.tech/tags/gemini-decision-1.md>), [gemini-decisions-api](<https://devfeed.tech/tags/gemini-decisions-api.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-060](<https://devfeed.tech/tags/generative-ai-2-060.md>), [jev](<https://devfeed.tech/tags/jev.md>), [jev-4](<https://devfeed.tech/tags/jev-4.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-242](<https://devfeed.tech/tags/llm-release-242.md>)

### AI overview

Gemini Decision 1 supports yes/no, choice, and rubric-scoring questions, and accepts text, images, audio, video, and PDFs. The excerpt compares it with Jev, which is limited to text and JSON, and OpenAI, which handles text and images. Gemini costs 10 cents per million input tokens with free output, matching GPT-6 Luna's listed price; Jev is listed at 4.2 cents per million. In a video test, Gemini returned probabilities for yes/no answers (for example, 0.92 for a robot and 0.05 for a dragon), while Jev and OpenAI are described as returning only 1.0 or 0.0. These are the author's reported test results.

### Source excerpt

Gemini Decisions API Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question. It's priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, and output is free. Jev remains the cheapest of the three, at 4.2 cents per million. Jev is text (and JSON) only. OpenAI can handle text and images. Gemini Decision 1 is fully multi-model: it covers text, images, audio, video, and PDFs. I tested it against video by passing these questions to it along with my Yonkers stomping robot video file: dragon: Does this video have a dragon in it? robot: Does this video have a robot in it? france: Is this video set in France? usa: Is this video set in the USA? Jev and OpenAI both return 1.0 or 0.0 for yes/no questions, but Gemini insists on being a little less confident than that: { "dragon": { "type": "yes_no", "probability": 0.04976021841520312 }, "robot": { "type": "yes_no", "probability": 0.9234055387792485 }, "france": { "type": "yes_no", "probability": 0.08329171353166241 }, "usa": { "type": "yes_no", "probability": 0.9230459995157706 } } Via Hacker News Tags: ai, generative-ai, gemini, llm-release, jev, decision-models

## aws-emulator

DevFeed: [aws-emulator](<https://devfeed.tech/articles/aws-emulator-129841.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/11/aws-emulator/>)

Author: Simon Willison

Published: 2026-11-11T21:18:30Z

Content type: article

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Emulator](<https://devfeed.tech/topics/emulator.md>)

Tags: [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agentic-engineering-71](<https://devfeed.tech/tags/agentic-engineering-71.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-321](<https://devfeed.tech/tags/ai-2-321.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-72](<https://devfeed.tech/tags/amazon-72.md>), [amazon-web-services](<https://devfeed.tech/tags/amazon-web-services.md>), [amazon-web-services-85](<https://devfeed.tech/tags/amazon-web-services-85.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-emulator](<https://devfeed.tech/tags/aws-emulator.md>), [commits](<https://devfeed.tech/tags/commits.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-61](<https://devfeed.tech/tags/docker-61.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-060](<https://devfeed.tech/tags/generative-ai-2-060.md>), [guest-post](<https://devfeed.tech/tags/guest-post.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-023](<https://devfeed.tech/tags/llms-2-023.md>), [macos](<https://devfeed.tech/tags/macos.md>), [rust](<https://devfeed.tech/tags/rust.md>), [rust-117](<https://devfeed.tech/tags/rust-117.md>), [swarm](<https://devfeed.tech/tags/swarm.md>), [test](<https://devfeed.tech/tags/test.md>), [testing](<https://devfeed.tech/tags/testing.md>), [testing-96](<https://devfeed.tech/tags/testing-96.md>), [tests](<https://devfeed.tech/tags/tests.md>), [werner-vogels](<https://devfeed.tech/tags/werner-vogels.md>), [werner-vogels-3](<https://devfeed.tech/tags/werner-vogels-3.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

AWS's aws-emulator lets developers test against local clones of AWS services without provisioning a paid API key. The excerpt says it is written in Rust and currently requires Docker on macOS or Windows. Its author hopes it will eventually be available as a single binary for use in test suites across other languages and platforms; that is a hoped-for improvement, not a stated current capability. The excerpt attributes 29,684 commits in the project's first three weeks to a large swarm of agents.

### Source excerpt

aws-emulator Finally, an official emulator from AWS to run tests against a local clone of their many different services without having to provision a paid API key to do so. It's written in Rust by a huge swarm of agents - 29,684 commits in the first three weeks of the project. Swaminathan (Swami) Sivasubramanian wrote about how it came to be in a guest post on Werner Vogels' blog. It currently requires Docker to run on macOS or Windows. I'm hoping they fix that in the future - it would be great if you could download a single binary and use that as part of a standard test suite in other languages and on other platforms. Tags: amazon, amazon-web-services, testing, werner-vogels, ai, rust, docker, generative-ai, llms, agentic-engineering

## Browse tools.simonwillison.net by tag

DevFeed: [Browse tools.simonwillison.net by tag](<https://devfeed.tech/articles/browse-tools-simonwillison-net-by-tag-129844.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/11/tools-tags/>)

Author: Simon Willison

Published: 2026-11-11T18:42:50Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Tree-sitter](<https://devfeed.tech/topics/tree-sitter.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-321](<https://devfeed.tech/tags/ai-2-321.md>), [apis](<https://devfeed.tech/tags/apis.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-328](<https://devfeed.tech/tags/claude-328.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-060](<https://devfeed.tech/tags/generative-ai-2-060.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [javascript-772](<https://devfeed.tech/tags/javascript-772.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-023](<https://devfeed.tech/tags/llms-2-023.md>), [tools](<https://devfeed.tech/tags/tools.md>), [tools-83](<https://devfeed.tech/tags/tools-83.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>), [vibe-coding-104](<https://devfeed.tech/tags/vibe-coding-104.md>)

### AI overview

The tools.simonwillison.net homepage now offers tag clouds to browse a collection of 244 vibe-coded tools by JavaScript APIs, libraries, and web API hosts. The tags were generated by using Fable 5.2 and tree-sitter to analyze each tool's code.

### Source excerpt

Browse tools.simonwillison.net by tag I've been wanting a better way to browse my collection of vibe-coded tools (244 and counting) for a while. I had a few Fable 5.2 credits left over before my weekly reset so I set it to work using tree-sitter to analyze the code for JavaScript APIs, libraries, and web API hosts used by each tool. The homepage now features tag clouds for browsing by each of those categories of tag: Tags: javascript, tools, ai, generative-ai, llms, claude, vibe-coding

## llm 0.37.2

DevFeed: [llm 0.37.2](<https://devfeed.tech/articles/llm-0-37-2-129843.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/11/llm/>)

Author: Simon Willison

Published: 2026-11-11T17:19:52Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [llm](<https://devfeed.tech/tags/llm.md>), [llm-650](<https://devfeed.tech/tags/llm-650.md>), [projects](<https://devfeed.tech/tags/projects.md>), [projects-565](<https://devfeed.tech/tags/projects-565.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [releases-32](<https://devfeed.tech/tags/releases-32.md>), [security](<https://devfeed.tech/tags/security.md>), [security-643](<https://devfeed.tech/tags/security-643.md>)

### AI overview

LLM 0.37.2 fixes a security issue involving OpenAI-compatible endpoints from other providers. The configured OpenAI API key could be sent to another provider if the key named by `api_key_name` had never been stored, or if a model configured with `responses: true` was run with `-o chat_completions 1`. The excerpt says these endpoints are managed by the new `llm openai endpoint add` command; it does not describe further remediation details.

### Source excerpt

Release: llm 0.37.2 Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w. LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API endpoints from other providers. Daniel reported two ways this could accidentally send your configured OpenAI API key to one of those providers: if the key named by api_key_name had never been stored, or if a responses: true model was run with -o chat_completions 1. Tags: projects, security, llm, releases

## Anthropic's IPO roadshow video

DevFeed: [Anthropic's IPO roadshow video](<https://devfeed.tech/articles/anthropic-s-ipo-roadshow-video-129840.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/11/anthropic-ipo-roadshow/>)

Author: Simon Willison

Published: 2026-11-11T15:11:59Z

Content type: article

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [AWS Trainium](<https://devfeed.tech/topics/aws-trainium.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-321](<https://devfeed.tech/tags/ai-2-321.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [amd](<https://devfeed.tech/tags/amd.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-355](<https://devfeed.tech/tags/anthropic-355.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-trainium](<https://devfeed.tech/tags/aws-trainium.md>), [business](<https://devfeed.tech/tags/business.md>), [chip](<https://devfeed.tech/tags/chip.md>), [chips](<https://devfeed.tech/tags/chips.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-mythos-fable](<https://devfeed.tech/tags/claude-mythos-fable.md>), [claude-mythos-fable-48](<https://devfeed.tech/tags/claude-mythos-fable-48.md>), [co-founder](<https://devfeed.tech/tags/co-founder.md>), [compute](<https://devfeed.tech/tags/compute.md>), [days](<https://devfeed.tech/tags/days.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [driver](<https://devfeed.tech/tags/driver.md>), [effective](<https://devfeed.tech/tags/effective.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-060](<https://devfeed.tech/tags/generative-ai-2-060.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [gpus-16](<https://devfeed.tech/tags/gpus-16.md>), [ipo](<https://devfeed.tech/tags/ipo.md>), [ipo-roadshow](<https://devfeed.tech/tags/ipo-roadshow.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-023](<https://devfeed.tech/tags/llms-2-023.md>), [recursive-self-improvement](<https://devfeed.tech/tags/recursive-self-improvement.md>), [recursive-self-improvement-4](<https://devfeed.tech/tags/recursive-self-improvement-4.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Anthropic says Claude is trained and served across AWS Trainium, Google TPUs, NVIDIA GPUs and AMD GPUs, enabled by a long-running multi-chip strategy that requires separate, costly software and inference stacks. The roadshow excerpt says Mythos got Claude running on AMD in three days with almost no human intervention, compared with prior platform integrations that took dozens of engineers months; Claude ported or wrote nearly all the kernels. Anthropic describes effective compute as physical capacity multiplied by discovered compute multipliers, which can reduce the hardware needed for a given training run or enable a more capable model with the same capacity. It argues these multipliers build on one another and speculates Claude may discover them autonomously as self-improvement advances. These are claims from an excerpt of the roadshow transcript, not independently verified results.

### Source excerpt

Anthropic's IPO roadshow video Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom Brown is particularly interesting, describing how Anthropic train and serve Claude across AWS Trainium, Google TPUs, NVIDIA GPUs, and AMD GPUs. I'm not sure why there's no official video transcript, but here's one that I extracted using MacWhisper. Highlights below: We train and serve Claude now across all four major chip families. That's only possible because early on we made an unconventional bet on a multi-chip strategy. At the time, many people thought that running AI models on different chips wasn't worth the effort. Each chip needs its own tailored software stack and inference stack, which is expensive and difficult to build. We've now been doing it for years, and we've gotten incredibly good at it. [...] As an example, this year, we started working with AMD GPUs for the first time. In the past, bringing on a new chip platform took dozens of engineers months of work This time, we had Mythos try it out. It got Claude running on AMD in just three days, with basically no human intervention. Claude ported or wrote almost 100% of the kernels. [...] The second driver of our compute advantage is our rate of discovery of compute multipliers. We focus on total effective compute, which is the multiplicative product of physical capacity times the compute multipliers that we discover. Each one we discover makes our pool of total effective compute bigger. For example, say you need 100 units of compute to train a model of a certain intelligence. A 4x compute multiplier means you can use 25 units of compute to train the exact same model. Or you can use those hundred physical units to train an even more intelligent model that would have previously required 400 units. Compute multipliers create a competitive advantage for us that's hard to re

[Next page](<https://devfeed.tech/sources/simon-willison-s-weblog.md?cursor=WyIyMDI2LTExLTExVDE1OjExOjU5KzAwOjAwIiwgIjEyYTBkOGZlLTU1ZWQtNDNhOC1hYzI1LWI0NTVmNTBhOGExMiJd>)