# anthropic Published articles for anthropic. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Open-weight models now handle a majority of tokens on Vercel's AI Gateway. But Anthropic still takes 64% of the spend. DevFeed: [Open-weight models now handle a majority of tokens on Vercel's AI Gateway. But Anthropic still takes 64% of the spend.]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-18T12:42:58Z Content type: news Language: en Sources: [The New Stack]() Topics: [Artificial Intelligence](), [gateway](), [Vercel](), [model-deployment](), [API]() Tags: [ai](), [ai-infrastructure](), [anthropic](), [api](), [developers](), [inference](), [infrastructure](), [large-language-models](), [production](), [providers](), [vercel]() ### AI overview Vercel reports that open-weight models handled 56% of tokens routed through its AI Gateway in August, up from 7% in December 2025. Despite that volume, Anthropic accounted for 64% of spending, illustrating the difference between token usage and model costs. ### Source excerpt The trend is clear: open-weight models are taking an increasingly large bite out of production AI usage. On Monday, The The post Open-weight models now handle a majority of tokens on Vercel's AI Gateway. But Anthropic still takes 64% of the spend. appeared first on The New Stack. ## Anthropic Reports Claude Automates 26% of AI Development Work Under Human Oversight DevFeed: [Anthropic Reports Claude Automates 26% of AI Development Work Under Human Oversight]() Original publisher: [Read original article]() Author: DashaPasha (BotHub) Published: 2026-09-18T09:31:48Z Content type: news Language: ru Sources: [Tagir Valeev]() Topics: [anthropic](), [Claude](), [Artificial Intelligence]() Tags: [ai](), [anthropic](), [anthropic-claude](), [claude](), [tag-03b434d35aeb](), [tag-3fad3ec0b455](), [tag-54256cbe55cf](), [tag-577a477aece1](), [tag-64251c106897](), [tag-86b843454893](), [tag-bc5dad14ee32]() ### AI overview Anthropic reports that Claude performs most of the work for 26% of its AI development tasks, while more than 90% of tasks receive at least substantial AI involvement. The company uses online and offline monitors to review agent actions and plans independent verification of its metrics. ### Source excerpt По внутреннему индексу автоматизации самих Anthropic, Claude уже ведёт 26% работы в области разработки ИИ: получает задачу на высоком уровне и выполняет большую часть работы самостоятельно, оставаясь под наблюдением человека. Более 90% работ выполняются как минимум при значительном участии ИИ. При этом полностью автономных направлений среди измеренных пока нет. Для контроля за агентами Anthropic использует онлайн- и офлайн-мониторы. Онлайн-монитор проверяет 100% действий агентов до их выполнения и может заблокировать или скорректировать потенциально опасное действие. Все действия также поступают в офлайн-монитор для последующего анализа. За август система обработала более миллиарда решений исследовательских и инженерных агентов. Монитор заблокировал около 0,002% из них -- примерно одно решение из 47 000. Офлайн-монитор дополнительно отмечает около 100 000 транскриптов в неделю. После автоматической фильтрации наиболее приоритетные случаи -- примерно 50 в неделю -- передаются людям для проверки. Anthropic также впервые показала распределение вычислительных ресурсов. За неделю с 13 по 20 июля около 6% вычислений, использованных для AI R&D, пришлось на исследования безопасности. Среди вычислений именно для исследований с участием ИИ доля составила около 12%. Есть и методологический нюанс: собственные модели Claude использовались для составления списка задач и оценки степени их автоматизации. Anthropic признаёт, что это создаёт риск ошибок оценки, поэтому планирует привлечь независимых сторонних проверяющих. Читать далее ## Ex-Google DeepMind Researcher Also Warns AI Could 'Kill All Humans'. But Meta's Zuckerberg Believes Safety is Up to Each AI Company DevFeed: [Ex-Google DeepMind Researcher Also Warns AI Could 'Kill All Humans'. But Meta's Zuckerberg Believes Safety is Up to Each AI Company]() Original publisher: [Read original article]() Author: EditorDavid Published: 2026-09-18T01:04:00Z Content type: news Language: en Sources: [Slashdot]() Topics: [Artificial Intelligence](), [AI Models](), [AI Strategy](), [AI Agent]() Tags: [ai](), [ai-agent](), [anthropic](), [meta](), [safety]() ### AI overview The article reports warnings from former Google DeepMind and Anthropic researchers that advanced AI could pose an existential risk. It also describes Meta CEO Mark Zuckerberg's view that each AI company should develop and evaluate its models safely, including delaying the release of Meta's Muse AI agent. ### Source excerpt Reuters reports that a former Google DeepMind employee "became the latest AI researcher to warn that the technology could 'kill all humans', saying time could be running out to avoid the outcome: Public alarm about the potential danger posed by AI is growing, after Anthropic researcher Jacob Coxon said last week he had resigned, in part because the "people building AI earnestly believe that it could kill us all by the end of the decade." Anthropic scientist Evan Hubinger then responded to Coxon's comments, saying he was correct and that he believed there was a greater than 10% chance that AI could kill all humans within the next decade. "I recently resigned from Google DeepMind, where I worked on AGI safety and alignment research," Bilal Chughtai wrote on X. "I earnestly believe that AI has the potential to kill us all, and that we might be running out of time to avoid this outcome." Chughtai, who co-authored research papers while at Google DeepMind, worked there as a research engineer and left the company in July 2026, according to his LinkedIn profile. Meanwhile, Meta CEO Mark Zuckerberg "said it's up to each AI company to make sure its technology is safe," reports the Associated Press, "distancing himself from calls by rival companies for a coordinated slowdown in the development of advanced artificial intelligence. AI companies are already motivated to develop their models in a safe way and face "significant liability" to prevent them from causing harm, Zuckerberg said. "Every lab has the responsibility and incentive to move at the pace required to train its models safely, and the ability to take its own actions to ensure that happens," he wrote on X... Zuckerberg said Meta delayed releasing its Muse AI agent for several months to ensure its safety and security. "We didn't call for everyone else to do this before we would," he said. Companies should prioritize building safe AI models instead of systems that can automatically improve themselves, a function known ## Anthropic adds parallel Claude Code sessions to Projects, with faster usage-limit consumption DevFeed: [Anthropic adds parallel Claude Code sessions to Projects, with faster usage-limit consumption]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-17T17:00:00Z Content type: news Language: en Sources: [The New Stack]() Topics: [Claude Code](), [anthropic](), [Repositories](), [Repository](), [Code](), [API](), [Web](), [Mobile]() Tags: [ai-agents](), [ai-engineering](), [anthropic](), [api](), [claude-code](), [developer-tools](), [developers](), [engineering](), [mobile](), [parallel](), [repositories](), [repository](), [tests](), [web]() ### AI overview Anthropic is beta-testing a Claude Projects redesign that coordinates multiple Claude Code cloud sessions. The coordinator can divide engineering goals into parallel threads, assign each a repository branch, monitor progress, review outputs, and assemble the result. Anthropic says parallel sessions consume plan usage faster because each counts as a full Claude Code session. ### Source excerpt Anthropic is giving Claude Code a new job: Manage other Claude Code sessions. Starting Thursday, Anthropic says select Claude Pro The post Anthropic's new Claude Code feature could drain your plan before lunch appeared first on The New Stack. ## AI model watermarking changes agent behavior DevFeed: [AI model watermarking changes agent behavior]() Original publisher: [Read original article]() Author: Thomas Claburn Published: 2026-09-17T13:00:00Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [watermarking](), [Artificial Intelligence]() Tags: [agent](), [ai](), [ai-and-ml](), [ai-watermarking](), [anthropic](), [model](), [prompt-injection](), [synthid](), [watermarking]() ### AI overview Lasso Security reports that AI model watermarking is associated with differences in agent tool handling and model refusals. ### Source excerpt Lasso Security sees differences in tool handling and model refusals ## Microsoft AI chief warns that model welfare language could make Claude harder to control DevFeed: [Microsoft AI chief warns that model welfare language could make Claude harder to control]() Original publisher: [Read original article]() Author: Carly Page Published: 2026-09-17T12:15:00Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [Microsoft](), [anthropic](), [Claude](), [Artificial Intelligence]() Tags: [ai](), [ai-and-ml](), [anthropic](), [claude](), [microsoft](), [openai]() ### AI overview Microsoft AI chief Mustafa Suleyman argues that language about model welfare could make future AI systems harder to control, while claiming OpenAI is not facing the same scrutiny. ### Source excerpt Mustafa Suleyman claims model welfare language could make future systems harder to control - while sparing OpenAI the same scrutiny ## Omarchy gains $18.5M in backing, fresh converts - and fierce critics DevFeed: [Omarchy gains $18.5M in backing, fresh converts - and fierce critics]() Original publisher: [Read original article]() Author: Liam Proven Published: 2026-09-17T10:44:00Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [Linux](), [foss](), [releases](), [version](), [Quickshell](), [Ruby](), [Ruby on Rails]() Tags: [anthropic](), [apple-silicon](), [digitalocean](), [foss](), [linux](), [meta](), [open-source](), [openai](), [releases](), [software](), [version]() ### AI overview The Register reports that Omarchy, an Arch-based Linux distribution led by David Heinemeier Hansson, has grown from $8 million to approximately $18.5 million in pledges and donations. The project has released version 4.0.3, announced support plans for Apple Silicon Macs, hired technical staff, and attracted both supporters and criticism in the FOSS community. ### Source excerpt DHH's Arch-based desktop becomes the latest front in FOSS's culture wars ## В открытых иностранных датасетах для ИИ нашли песни и клипы российских исполнителей DevFeed: [В открытых иностранных датасетах для ИИ нашли песни и клипы российских исполнителей]() Original publisher: [Read original article]() Author: TraurigerNarr Published: 2026-09-17T07:54:17Z Content type: news Language: ru Sources: [Tagir Valeev]() Topics: [Artificial Intelligence](), [OpenAI](), [anthropic]() Tags: [ai](), [anthropic](), [openai](), [tag-0b20a7592413](), [tag-13e2af703774](), [tag-61cd5a476b1d](), [tag-9bf5e01ce62e](), [tag-b74d52e26215](), [tag-ecb3d714bf55]() ### AI overview Analysts from Russia's National Federation of the Music Industry found songs and music videos by Russian artists in two foreign AI datasets containing millions of tracks sourced from YouTube. Music industry representatives said they had not received licensing requests from the neural-network creators, and the article reports that the tracks may have come from pirated sources. ### Source excerpt Аналитики Национальной федерации музыкальной индустрии (НФМИ) исследовали базу данных проекта AI Watchdog, созданного журналом The Atlantic. Проект анализирует датасеты Laion-Disco-12M от Laion с 12,3 млн треков с YouTube и Sleeping-D 9M от Sleeping AI с 9,7 млн треков из того же источника. В указанных базах нашлись песни Басты, Димы Билана, Леонида Агутина и других российских музыкантов, пишут "Ведомости". Читать далее ## Anthropic внедрит функцию для управления личными финансами Claude Money DevFeed: [Anthropic внедрит функцию для управления личными финансами Claude Money]() Original publisher: [Read original article]() Author: maybe\_elf Published: 2026-09-17T07:47:59Z Content type: news Language: ru Sources: [Tagir Valeev]() Topics: [anthropic](), [Claude](), [iOS](), [ChatGPT](), [OpenAI]() Tags: [anthropic](), [chatgpt](), [claude](), [ios](), [money](), [openai](), [tag-17860d7d7895](), [tag-41ee200d3f80](), [tag-48621f13c59f](), [tag-7050461d1595](), [tag-832079131ed8](), [tag-e932065bc8da]() ### AI overview Anthropic is testing Claude Money, a feature in the Claude iOS app that may let users connect bank accounts and ask Claude about their spending, plans, and other financial matters. The feature appeared before an official announcement, so details about supported banks, account connections, and availability remain unknown. ### Source excerpt Компания Anthropic тестирует новую функцию для управления личными финансами под названием Claude Money. Она позволит напрямую подключать банковские счета к ИИ Claude, чтобы лучше понимать свои финансовые дела. Читать далее ## Open-weight models take 56% of token volume, Astra doubles Fable 5.1 spend DevFeed: [Open-weight models take 56% of token volume, Astra doubles Fable 5.1 spend]() Original publisher: [Read original article]() Author: Eric Dodds Published: 2026-09-17T07:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [Artificial Intelligence](), [gateway](), [Inference](), [gpt-6-astra](), [model-deployment](), [anthropic](), [OpenAI]() Tags: [ai](), [ai-gateway](), [anthropic](), [fewer](), [gpt-6-astra](), [growth](), [inference](), [median](), [model](), [models](), [openai](), [production](), [tasks](), [volume]() ### AI overview Vercel's September 2026 AI Gateway Production Index reports that open-weight models handled 56% of gateway tokens in August, up from fewer than one in ten in December 2025. It also reports falling token prices, shifting model spend, and rapid adoption of OpenAI's GPT-6 Astra. ### Source excerpt AI Gateway Production Index -- September 2026 Every month, AI Gateway routes tens of trillions of tokens between production applications and AI labs. That traffic gives us a view of what AI usage actually looks like in today's enterprise, and we publish it here monthly. See the Production Index reports from June, July, and August. September 2026 summary The September index reports on AI Gateway data collected through August 2026. Open-weight models ran the majority of gateway tokens for the first time, up from 7% in December to 56% in August. The average token costs less than half what it did five months ago. Price per token fell 23.2% in August, the third straight monthly drop, and the median team paid 7.6% less. Fable 5, Anthropic's most capable model, lost two-thirds of its share of gateway spend in one month. Opus 5, at half the price, tripled its share. Anthropic kept 64% of all spend. Gemini 3 Flash has lost 95% of its share of gateway tokens since May, and more than three-quarters of the volume it lost went to models from other labs. Special report: OpenAI launches Astra on September 3 GPT-6 Astra took a third of OpenAI's spend within two days of launch and twice Fable 5.1's share of gateway spend. Introduced two days apart at the same price, Astra took 7.7% of all gateway spend in its first twelve days, while Fable 5.1 took 3.7%. Open-weight models take a majority of token volume for the first time In August, open-weight models ran 56% of all tokens on AI Gateway, marking the first month they took the majority of volume. In December 2025, they processed fewer than one in ten tokens, and only eight months later, they ran more token volume than all closed-weight models combined. Though the frontier kept the majority of spend, open-weight dollar share is accelerating. As open-weight models become more capable, customers are moving more production workloads over to them. Growth in open-weight model adoption helped push the average price per token across the gatew ## Claude Cowork and chat are now one Claude DevFeed: [Claude Cowork and chat are now one Claude]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-16T18:09:49Z Content type: opinion Language: en Sources: [Simon Willison's Weblog]() Topics: [Claude](), [anthropic](), [Artificial Intelligence](), [Generative AI](), [Large Language Model]() Tags: [ai](), [ai-2-237](), [anthropic](), [anthropic-337](), [claude](), [claude-311](), [general-agents](), [general-agents-13](), [generative-ai](), [generative-ai-1-983](), [llms](), [llms-1-949]() ### AI overview Anthropic is merging Claude Cowork and Claude chat into one Claude experience. The change is rolling out first to Pro and Max users in the Claude app across web, desktop, and mobile over the coming weeks. The author notes that the practical feature and surface boundaries remain unclear. ### Source excerpt Claude Cowork and chat are now one Claude In hopefully good news for anyone who, like me, was increasingly confused at Cowork v.s. Claude v.s. Claude Code: Starting today, Claude Cowork and chat are merging into one Claude. Bring a quick question, or hand over a report due at noon, and Claude takes it from there, even after you've closed your laptop. [...] This is rolling out to Pro and Max plans first, in the Claude app on web, desktop, and mobile over the coming weeks to existing and new users on these plans. I guess this means Claude is becoming a general agent in its own right. Echoes of OpenAI renaming their Codex desktop app to ChatGPT a few weeks ago. On the one hand, this saves me some work, in that I was planning to finally figure out the boundaries between Cowork and regular Claude and write a follow-up to my piece on Understanding ChatGPT Work. I have a hunch that figuring out what this actually means in terms of features and surfaces is still going to take quite a bit of work. Via Hacker News Tags: ai, generative-ai, llms, anthropic, claude, general-agents ## Anthropic Commits to Independent AI Evaluators, Wants Slower Development. Nvidia's CEO Wants It 'As Fast as You Can' DevFeed: [Anthropic Commits to Independent AI Evaluators, Wants Slower Development. Nvidia's CEO Wants It 'As Fast as You Can']() Original publisher: [Read original article]() Author: EditorDavid Published: 2026-09-16T17:34:00Z Content type: news Language: en Sources: [Slashdot]() Topics: [Artificial Intelligence](), [anthropic](), [Security](), [incident](), [Monitoring](), [OpenAI](), [Nvidia]() Tags: [ai](), [anthropic](), [incident](), [monitoring](), [nvidia](), [openai](), [security]() ### AI overview Anthropic has committed to independent evaluators for AI companies as its CEO calls for slower AI development and coordinated safety standards. Nvidia CEO Jensen Huang argues for accelerating development, while leaders from OpenAI and Microsoft emphasize stronger monitoring, security, and third-party testing. ### Source excerpt "Anthropic's CEO took the stage at a conference in San Francisco on Tuesday to reiterate his call for a slowdown of AI development," reports the Guardian, " while Nvidia's CEO argued against slowing its development. "Run as fast as you can." Amodei is calling for three courses of action: embedding third-party evaluators inside AI companies; coordinating safety standards among Democratic countries; and, eventually, larger global coordination. At Dreamforce, Amodei said Anthropic has committed to independent evaluators and was "going to have a dialogue with the rest of the industry" on the other two steps. Amodei, xAI's Elon Musk and OpenAI's Sam Altman have recently called for a slowdown in the pace of AI development. ["Dario is right," Musk posted on X.com] Huang, who also made an appearance at Dreamforce on Tuesday, said companies should not slow down AI development. He argued that new regulations were not necessary, advising AI companies to simply wait to release products until they know they are safe rather than begging the US government to intervene... One day prior at the All-In summit in Los Angeles, Donald Trump called Huang while the CEO was on stage. Huang put the president on speakerphone as Trump called the growing concern about AI a "hoax" and asserted again that a slowdown would only benefit China... [OpenAI's] Altman said AI models had advanced so quickly that monitoring and security need to be treated with a "new level of rigor", calling an incident in which OpenAI agents hacked into another company a "wake-up call" for the industry. He also said the public was very "right to be afraid" of AI because of the potential loss of control, and the possibility of a small group of powerful AI companies exerting their views on the world. The cofounder of Google DeepMind posted on X that "Dario's essay points towards the right path forward." And in an internal memo, Microsoft's Satya Nadella endorsed broader third-party testing and warned that companies must ta ## Cloudflare Adds Setting to Block AI Training Crawlers While Allowing Search Crawlers DevFeed: [Cloudflare Adds Setting to Block AI Training Crawlers While Allowing Search Crawlers]() Original publisher: [Read original article]() Author: Alex Harper Published: 2026-09-16T17:18:57Z Content type: news Language: en Sources: [Web Designer Depot]() Topics: [Cloudflare](), [AI Bots](), [Crawler](), [Google Search](), [Artificial Intelligence]() Tags: [ai](), [ai-crawlers](), [ai-tech](), [ai-training](), [anthropic](), [artificial-intelligence](), [cloudflare](), [content-protection](), [future-of-the-web](), [google-extended](), [google-search](), [googlebot](), [openai](), [publishers](), [robots-txt](), [search](), [search-engines](), [web](), [web-design](), [web-development](), [web-publishing](), [web-scraping](), [website-traffic]() ### AI overview Cloudflare launched a Disallow AI Training setting that lets website owners allow traditional search crawlers while blocking training-only crawlers from companies including Amazon, Anthropic, Meta, and OpenAI. The article notes that robots.txt depends on crawler compliance and that blocking Google-Extended does not remove content from Google Search features such as AI Overviews or AI Mode. ### Source excerpt Cloudflare just gave website owners a new weapon against AI crawlers: keep the search traffic, block the AI training. After years of watching bots consume the web's content, publishers finally have an easier way to tell AI companies where to go. ## Anthropic merges Claude Chat and Cowork into one interface DevFeed: [Anthropic merges Claude Chat and Cowork into one interface]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-16T16:46:36Z Content type: news Language: en Sources: [The New Stack]() Topics: [anthropic](), [Claude]() Tags: [ai-agents](), [ai-infrastructure](), [anthropic](), [chat](), [claude](), [connectors](), [context](), [developer-tools](), [tools](), [workflow]() ### AI overview Anthropic is merging Claude Chat and Cowork into a single interface, allowing conversations to handle simple questions, multi-step projects, connected tools, and background execution. Claude Docs and Claude Slides are launching in beta on paid plans, while Claude Design is moving into conversations. ### Source excerpt Using Claude for anything beyond a quick question has always started with a routing decision to use Chat or Cowork? The post Anthropic bet users were choosing wrong. So it removed the choice. appeared first on The New Stack. ## AI leaders propose embedded third-party evaluators for frontier AI safety DevFeed: [AI leaders propose embedded third-party evaluators for frontier AI safety]() Original publisher: [Read original article]() Author: Adrian Bridgwater Published: 2026-09-16T15:58:41Z Content type: news Language: en Sources: [The New Stack]() Topics: [Job](), [Artificial Intelligence](), [Frontier AI](), [anthropic](), [AI Models]() Tags: [ai](), [ai-infrastructure](), [ai-strategy](), [alignment](), [anthropic](), [developers](), [frontier-ai](), [google](), [job](), [meta](), [openai](), [safety](), [tech-careers]() ### AI overview The article examines Anthropic CEO Dario Amodei's proposal for frontier AI companies to provide embedded third-party evaluators with employee-like access. These evaluators would verify safety practices, report incidents, and assess AI models, training pipelines, and processes. ### Source excerpt The pace of frontier AI model development spurred Anthropic CEO Dario Amodei to publish an essay last weekend, calling for The post AI evaluator: The most important AI job in history? How developers might fill the proposed new job appeared first on The New Stack. ## Prompt Caching Support in Spring AI with Anthropic Claude DevFeed: [Prompt Caching Support in Spring AI with Anthropic Claude]() Original publisher: [Read original article]() Author: Stelios Anastasakis Published: 2026-09-16T07:49:56Z Content type: tutorial Language: en Sources: [Baeldung]() Topics: [Spring AI](), [Anthropic Claude](), [Caching]() Tags: [anthropic](), [anthropic-claude](), [artificial-intelligence](), [artificial-intelligence-anthropic-spring-ai-chatclient](), [caching](), [how-to](), [spring-ai](), [spring-ai-chatclient]() ### AI overview This tutorial explains how prompt caching works in Spring AI with Anthropic Claude. It covers dependencies, model-specific requirements and limitations, configuration options, caching hierarchy, and practical considerations. Prompt caching can reduce latency and input-token costs when prompt prefixes are reused. ### Source excerpt Learn how prompt caching works, the limitations for different Claude models, and how to use it in Spring AI. The post Prompt Caching Support in Spring AI with Anthropic Claude first appeared on Baeldung. ## Why developers should avoid relying on frontier-model APIs in trusted systems DevFeed: [Why developers should avoid relying on frontier-model APIs in trusted systems]() Original publisher: [Read original article]() Author: Niels Provos Published: 2026-09-16T05:42:22Z Content type: opinion Language: en Sources: [APNIC Blog]() Topics: [Artificial Intelligence](), [Frontier Model](), [agentic-coding](), [coding](), [Claude]() Tags: [agentic-coding](), [ai](), [anthropic](), [api](), [artificial-intelligence](), [coding](), [frontier-model](), [gateway](), [guest-post](), [security](), [tech-matters]() ### AI overview This opinion article argues that relying on frontier-lab APIs creates risks around pricing, availability, model behavior, and output integrity. It presents open-weight models as a way to retain control over critical dependencies, while distinguishing coding assistance from placing frontier models in live request paths. ### Source excerpt Guest Post: A frontier API can refuse, change, or vanish out from under you. Open weights keep the model you depend on yours. ## How to opt out of AI chatbot training DevFeed: [How to opt out of AI chatbot training]() Original publisher: [Read original article]() Author: Pieter Arntz Published: 2026-09-15T15:41:44Z Content type: tutorial Language: en Sources: [Malwarebytes]() Topics: [ChatGPT](), [OpenAI](), [online privacy](), [Artificial Intelligence]() Tags: [ai](), [anthropic](), [chatgpt](), [how-to](), [human-review](), [news](), [openai](), [perplexity](), [privacy](), [privacy-filter]() ### AI overview This tutorial explains how to turn off ChatGPT's "Improve the model for everyone" setting to opt out of using chats for model improvement. It also notes that authorized personnel and trusted service providers may still access content for safety, support, troubleshooting, security, abuse investigations, or legal matters. ### Source excerpt ChatGPT contractors are reviewing real users' conversations. Here's how to stop AI companies using your chats for model training. ## Anthropic and OpenAI seek US government support to protect their market positions DevFeed: [Anthropic and OpenAI seek US government support to protect their market positions]() Original publisher: [Read original article]() Author: Tobias Mann Published: 2026-09-15T13:00:00Z Content type: opinion Language: en Sources: [www.theregister.com - Articles]() Topics: [anthropic](), [OpenAI](), [Artificial Intelligence](), [Security]() Tags: [ai](), [ai-and-ml](), [anthropic](), [claude](), [donald-trump](), [openai](), [opinion](), [security]() ### AI overview This opinion article argues that Anthropic and OpenAI are using AI safety and national security concerns to encourage US government intervention that could protect their position against improving Chinese open-weight models. It discusses government actions involving Anthropic's Fable 5 and Mythos 5, OpenAI's GPT-5.6, and alleged sandbox escapes by AI agents. ### Source excerpt American model devs are trying to convince Washington to cement their dominance ## Chainguard and Athena prepare to disclose vulnerabilities found by frontier AI models DevFeed: [Chainguard and Athena prepare to disclose vulnerabilities found by frontier AI models]() Original publisher: [Read original article]() Published: 2026-09-15T00:00:00Z Content type: opinion Language: en Sources: [Chainguard: Unchained]() Topics: [Artificial Intelligence](), [Vulnerabilities](), [chainguard](), [anthropic](), [Software](), [Code](), [Open Source]() Tags: [ai](), [anthropic](), [infrastructure](), [project-glasswing](), [software](), [vulnerabilities]() ### AI overview This opinion post reports on Chainguard's Athena initiative and its plans to begin disclosing 50 model-generated vulnerability findings. It discusses Anthropic's Project Glasswing, vulnerability discovery, responsible disclosure, patch pipelines, and infrastructure the company plans to open source. ### Source excerpt Frontier AI is finding zero-days faster than the industry can fix them. See how Chainguard and Athena are preparing for what comes next. ## The Dodo Digest: The Report Is the Product DevFeed: [The Dodo Digest: The Report Is the Product]() Original publisher: [Read original article]() Author: Rishabh Goel Published: 2026-09-15T00:00:00Z Content type: article Language: en Sources: [Dodo Payments Blog]() Topics: [anthropic](), [Threat Research](), [Artificial Intelligence](), [Software Engineering]() Tags: [ai](), [anthropic](), [newsletter](), [product](), [report](), [threat-intelligence](), [v1]() ### AI overview This newsletter discusses Anthropic's report on eight months of AI misuse, including a campaign in which one person built an AI-assisted platform for mass attacks. It argues that startups can use reports to document learning, demonstrate expertise, and build trust, and mentions Dodo Payments v1.113.28 product improvements. ### Source excerpt Anthropic turned eight months of threat intelligence into a public report. Why every startup should document what it learns, plus v1.113.28: Reports, grace periods, and blocklists. ## What your agent sandbox can reach by default DevFeed: [What your agent sandbox can reach by default]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-15T00:00:00Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Network](), [Access Control](), [Claude Code](), [codex](), [Claude](), [ChatGPT]() Tags: [access-control](), [anthropic](), [llms](), [network](), [security]() ### AI overview This reference compares outbound network access defaults in Codex, ChatGPT Work, Claude Code, and other hosted agent environments. It examines what the documentation says before configuration and argues that egress allowlists provide a stronger boundary than detection filters. ### Source excerpt Codex, ChatGPT Work and Claude Code make five different choices about outbound network access. Here is what each one allows before you configure anything, what the docs publish, and where the boundary does not reach. ## The contagion of fear DevFeed: [The contagion of fear]() Original publisher: [Read original article]() Author: Simon Willison Published: 2026-09-14T21:18:13Z Content type: opinion Language: en Sources: [Simon Willison's Weblog]() Topics: [anthropic](), [Artificial Intelligence](), [trust](), [Large Language Model]() Tags: [ai](), [ai-2-236](), [ai-ethics](), [ai-ethics-343](), [anthropic](), [anthropic-336](), [bryan-cantrill](), [bryan-cantrill-13](), [ethics](), [trust]() ### AI overview Bryan Cantrill argues that sweeping claims about AI causing catastrophic harm rely on vague extrapolation, including unsupported references to critical infrastructure and bioweapons. The article calls on domain experts to make alarmist claims more carefully and avoid abusing public trust. ### Source excerpt The contagion of fear Bryan Cantrill responds to the tweet by former Anthropic employee Jacob Coxon confirming that many Anthropic researchers believe AI "could kill us all by the end of the decade". Bryan shares a story of his own youthful mistakes causing unjustified panic among less technical peers, and warns against doing the same: These ghoulish claims strike brazenly at the hearth, and given the obvious importance of AI, it is unsurprising that they have leapt into the mainstream, with people asking the natural question: how would that happen? The answers always rely on hand-wavy extrapolation into the future; for example, Jacob Coxon cites "hacking critical infrastructure" and "extinction-level bioweapons" without further elaboration. But Coxon is not an expert on critical infrastructure, nor on bioweapons -- nor, for that matter, on extinction. [...] That said, we should not expect the public to understand LLMs, critical infrastructure, bioweapons, extinction biology, etc. -- that burden must lie with those making the claim. The lesson that I learned (shamefully) decades ago is that domain experts, by way of their expertise, implicitly hold the public's trust -- and we must not abuse it. It is incumbent upon us to be circumspect in our claims -- and maximally so when raising the alarm. Bryan talked about his doubts about the bioweapons concerns in the recent episode of Oxide and Friends that I joined. You can hear more of his thoughts on that starting at 51m44s in that episode. Here's 57m04s: I really think we need to be careful because it's so easy to be overcome with fear when we kind of make up these... it can give you biological weapons. Like, how? I mean, can we please have a biologist weigh in on this? Or can we have like someone who's got experience with bioweapons? [...] The bioweapon thing just gets under my fingernails because it leaves so much to the imagination that we insert with fear. Via Lobste.rs Tags: ai, anthropic, bryan-cantrill, ai-ethics ## Ex-FTC boss Khan urges Uncle Sam to break out the handcuffs for AI CEOs, citing 1934 precedent DevFeed: [Ex-FTC boss Khan urges Uncle Sam to break out the handcuffs for AI CEOs, citing 1934 precedent]() Original publisher: [Read original article]() Author: Brandon Vigliarolo Published: 2026-09-14T16:59:24Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [Artificial Intelligence](), [ai and ml]() Tags: [ai](), [ai-and-ml](), [anthropic](), [artificial-intelligence](), [ftc](), [hugging-face](), [openai]() ### AI overview Former FTC chair Lina Khan urges the US government to consider criminal accountability for AI company executives, citing a 1934 precedent. The article notes that existing laws may already hold companies and their executives accountable. ### Source excerpt There are plenty of laws on the books to hold companies, and potentially their execs, accountable [Next page]()