# Bot

A bot is Internet software that acts as a software agent.

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

## Early Black Friday Deal: Claude Max and Grok Bot Codes ($200 Value) While Supplies Last

DevFeed: [Early Black Friday Deal: Claude Max and Grok Bot Codes ($200 Value) While Supplies Last](<https://devfeed.tech/articles/early-black-friday-deal-claude-max-and-grok-bot-codes-200-value-while-supplies-last-143206.md>)

Original publisher: [Read original article](<https://creatoreconomy.so/p/early-black-friday-deal-claude-max>)

Author: Peter Yang

Published: 2026-11-18T18:01:15Z

Content type: release

Language: en

Sources: [Behind the Craft](<https://devfeed.tech/sources/behind-the-craft.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [no-code website builders](<https://devfeed.tech/topics/no-code-website-builders.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-meeting-notes](<https://devfeed.tech/tags/ai-meeting-notes.md>), [app](<https://devfeed.tech/tags/app.md>), [black-friday](<https://devfeed.tech/tags/black-friday.md>), [chat](<https://devfeed.tech/tags/chat.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-max](<https://devfeed.tech/tags/claude-max.md>), [community](<https://devfeed.tech/tags/community.md>), [course](<https://devfeed.tech/tags/course.md>), [cowork](<https://devfeed.tech/tags/cowork.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [deal](<https://devfeed.tech/tags/deal.md>), [fable-5-2](<https://devfeed.tech/tags/fable-5-2.md>), [free](<https://devfeed.tech/tags/free.md>), [google](<https://devfeed.tech/tags/google.md>), [granola](<https://devfeed.tech/tags/granola.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>)

### AI overview

Paid subscribers are offered one free month of Claude Max and Grok Bot's Super tier, described as a $200 value, with 50 codes for each. Codes are first come, first served and restricted to new customers of the respective tool; redeeming a code makes the paid membership non-refundable. The membership also includes other tool discounts, an AI course, and access to a private Slack community with monthly workshops. The listed discounts vary by service and duration, including three months of Granola, Lovable, and Replit, six months of Wispr Flow and Linear, and one year of Mercury personal banking. The author says additional Claude Max and Grok Bot codes may become available later.

### Source excerpt

All codes are first come, first served while supplies last. Upgrade now to unlock.

## Introducing simplified onboarding for AWS WAF Bot Control at the targeted inspection level

DevFeed: [Introducing simplified onboarding for AWS WAF Bot Control at the targeted inspection level](<https://devfeed.tech/articles/introducing-simplified-onboarding-for-aws-waf-bot-control-at-the-targeted-inspection-level-140905.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/security/introducing-simplified-onboarding-for-aws-waf-bot-control-at-the-targeted-inspection-level/>)

Author: Pengfei Shao

Published: 2026-11-17T23:15:03Z

Content type: release

Language: en

Sources: [AWS Security Blog](<https://devfeed.tech/sources/aws-security-blog.md>)

Topics: [Bot Management](<https://devfeed.tech/topics/bot-management.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [AWS Management Console](<https://devfeed.tech/topics/aws-management-console.md>)

Tags: [amazon-cloudfront](<https://devfeed.tech/tags/amazon-cloudfront.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-waf](<https://devfeed.tech/tags/aws-waf.md>), [bot](<https://devfeed.tech/tags/bot.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [inspection](<https://devfeed.tech/tags/inspection.md>), [latest](<https://devfeed.tech/tags/latest.md>), [onboarding](<https://devfeed.tech/tags/onboarding.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [security-identity-compliance](<https://devfeed.tech/tags/security-identity-compliance.md>)

### AI overview

AWS WAF simplifies Targeted bot control setup by grouping request detections into High, Medium, and Low confidence levels, letting users choose one action per level instead of writing label rules. Defaults are CAPTCHA for High and Medium confidence and silent Challenge for Low; actions are configurable. The rule group can use `LATEST` for current detections, while confidence levels are available across AWS WAF resource types where Bot Control is supported. For CloudFront protection packs, a console toggle can also inject the JavaScript SDK automatically at no extra charge; API configuration leaves this setting off by default, and an `UpdateWebACL` that omits it turns it off. Automatic integration requires attention to cached HTML, content security policy, pages to exclude, privacy and cookie consent, and existing SDK use cases. The walkthrough requires a CloudFront distribution serving HTML on pay-as-you-go pricing; flat-rate plans do not support Targeted bot control.

### Source excerpt

Today, we're announcing simplified onboarding and bot confidence levels for AWS WAF Bot Control at the targeted inspection level, which we refer to as Targeted bot control in this post, matching the console. Bot confidence levels and the new LATEST rule group version are available for the resource types that AWS WAF protects: you act [...]

## How I Built an AI Marketing Team With Grok Bot Without Writing Code

DevFeed: [How I Built an AI Marketing Team With Grok Bot Without Writing Code](<https://devfeed.tech/articles/how-i-built-an-ai-marketing-team-with-grok-bot-without-writing-code-133908.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-i-built-an-ai-marketing-team-with-grok-bot-without-writing-code?source=rss>)

Author: Sam Brovda

Published: 2026-11-14T05:15:02Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-instructions](<https://devfeed.tech/tags/ai-agent-instructions.md>), [ai-agent-management](<https://devfeed.tech/tags/ai-agent-management.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-marketing-team](<https://devfeed.tech/tags/ai-marketing-team.md>), [app](<https://devfeed.tech/tags/app.md>), [automated-content-planning](<https://devfeed.tech/tags/automated-content-planning.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bots](<https://devfeed.tech/tags/bots.md>), [code](<https://devfeed.tech/tags/code.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [content](<https://devfeed.tech/tags/content.md>), [draft](<https://devfeed.tech/tags/draft.md>), [file](<https://devfeed.tech/tags/file.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [instructions](<https://devfeed.tech/tags/instructions.md>), [jobs](<https://devfeed.tech/tags/jobs.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [programming](<https://devfeed.tech/tags/programming.md>), [sales](<https://devfeed.tech/tags/sales.md>), [startups](<https://devfeed.tech/tags/startups.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

The author uses Grok Bot to run marketing through narrow, scheduled agents, with human approval before anything is published. A marketing bot proposes and drafts content, while a chief of staff bot checks actual outputs, nudges missed work once, and flags continued problems. Shared rules prohibit spending, fabricated quotes or metrics, unsupported factual or product claims, and public posting without approval. A dated lessons file keeps changes available to later jobs; when there is no signup page, for example, posts switch from signup requests to follow or comment prompts, and signups remain unknown. Batching content into a 21-day plan reduces daily planning. The author presents this as an early setup and stresses that bots can drift, so outputs and claims need human oversight.

### Source excerpt

I built an AI marketing team with Grok Bot. Here's how single-purpose agents, strict guardrails, and human oversight keep everything on track.

## Bring your business context to ChatGPT, Claude, Microsoft Copilot Cowork and Grok Bot

DevFeed: [Bring your business context to ChatGPT, Claude, Microsoft Copilot Cowork and Grok Bot](<https://devfeed.tech/articles/bring-your-business-context-to-chatgpt-claude-microsoft-copilot-cowork-and-grok-bot-129968.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/bring-your-business-context-chatgpt-claude-microsoft-copilot-cowork-and-grok-bot>)

Author: Ben Tripp; Nikhil Gangaraju

Published: 2026-11-11T15:00:00Z

Content type: release

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [business-intelligence](<https://devfeed.tech/topics/business-intelligence.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [microsoft 365](<https://devfeed.tech/topics/microsoft-365.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [always-on-ai](<https://devfeed.tech/tags/always-on-ai.md>), [bot](<https://devfeed.tech/tags/bot.md>), [business](<https://devfeed.tech/tags/business.md>), [business-context](<https://devfeed.tech/tags/business-context.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [context](<https://devfeed.tech/tags/context.md>), [copilot-cowork](<https://devfeed.tech/tags/copilot-cowork.md>), [data](<https://devfeed.tech/tags/data.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [microsoft-copilot](<https://devfeed.tech/tags/microsoft-copilot.md>), [platform](<https://devfeed.tech/tags/platform.md>), [product](<https://devfeed.tech/tags/product.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Databricks Genie plugins let agents use governed business context from Genie Ontology, which supplies definitions, relationships and source context. An agent can hand a business question to Genie, which finds permitted data, runs SQL and returns cited answers; Genie can also route specialized questions to domain-specific agents. Alternatively, an agent can ask Genie for missing context and continue its own work with its tools. The plugins work natively in ChatGPT, Claude, Microsoft Copilot Cowork and Grok Bot; other agents can connect through the Genie MCP server. The examples show different workflows: ChatGPT Dots monitor launches and post summaries, Claude combines certified metrics with document searches for analysis, Copilot Cowork prepares meeting materials and waits for approval before sending, and Grok Bot teammates review campaigns and draft budget changes for human approval. Clients supporting MCP Apps can show interactive visualizations and Ontology citations in the conversation.

### Source excerpt

Every business is adding more data to their AI-powered workflows. But more data doesn't...

## Pages in Grok Bot, clearly explained:

DevFeed: [Pages in Grok Bot, clearly explained:](<https://devfeed.tech/articles/pages-in-grok-bot-clearly-explained-127441.md>)

Original publisher: [Read original article](<https://blog.dailydoseofds.com/p/pages-in-grok-bot-clearly-explained>)

Author: Avi Chawla

Published: 2026-11-09T23:04:15Z

Content type: article

Language: en

Sources: [Daily Dose of Data Science](<https://devfeed.tech/sources/daily-dose-of-data-science.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [apple](<https://devfeed.tech/tags/apple.md>), [atlas](<https://devfeed.tech/tags/atlas.md>), [audio](<https://devfeed.tech/tags/audio.md>), [board](<https://devfeed.tech/tags/board.md>), [bots](<https://devfeed.tech/tags/bots.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [demo](<https://devfeed.tech/tags/demo.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [pages](<https://devfeed.tech/tags/pages.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

MongoDB Atlas Ephemeral Clusters let a coding agent provision a live database through one API call; a human must claim it to keep it, otherwise it pauses after 48 hours and is deleted after 7 days. Claiming turns it into a permanent free Atlas cluster with the same data and connection string. Grok Bot Pages are interactive dashboards at a persistent link that bots can update, including through routines; they complement chat by giving agent work a place to revisit and share. A local video search demo uses EmbeddingGemma 2 to match text queries to indexed video frames. On an Apple M3 Pro CPU, indexing a 60-second video took 29 seconds, while searches averaged 25 ms across nine queries. The excerpt notes that Unsloth's 176 MB 4-bit text embedding checkpoint lacks the full multimodal pipeline needed for video search. Search runs locally, but the retrieval index grows with added videos; one-bit vectors can reduce raw vector payload by 32 times versus float32.

### Source excerpt

...covered with a full hands-on video demo.

## Grok Bot has a Tailscale integration--and now you can, too

DevFeed: [Grok Bot has a Tailscale integration--and now you can, too](<https://devfeed.tech/articles/grok-bot-has-a-tailscale-integration-and-now-you-can-too-125768.md>)

Original publisher: [Read original article](<https://tailscale.com/blog/oauth-apps-ga>)

Author: Sam Linville

Published: 2026-11-09T20:30:00Z

Content type: release

Language: en

Sources: [Tailscale](<https://devfeed.tech/sources/blog-on-tailscale.md>)

Topics: [tailscale](<https://devfeed.tech/topics/tailscale.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [OAuth 2.0](<https://devfeed.tech/topics/oauth2.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [tailscale](<https://devfeed.tech/tags/tailscale.md>)

### AI overview

Tailscale OAuth apps let agents join a user's tailnet through OAuth 2.0 without exposing private services publicly or sharing keys. Unlike existing OAuth clients that create tag-owned devices under a shared identity, OAuth app devices carry the authorizing user's identity and remain subject to tailnet policies, audit logs, and device quotas. The excerpt describes Grok Bot accessing private MCP servers: Premium and Enterprise plans can use a custom device posture attribute to restrict it to designated resources, while other plans can apply a device tag after authentication and use tag-based rules. An example policy allows engineers' regular devices to reach production databases while their Grok Bot devices reach only MCP servers.

### Source excerpt

Agent access without exposing your network -- Tailscale OAuth apps are now GA.

## Bot the Builder: A Mac mini that works through our tickets at night

DevFeed: [Bot the Builder: A Mac mini that works through our tickets at night](<https://devfeed.tech/articles/bot-the-builder-a-mac-mini-that-works-through-our-tickets-at-night-126436.md>)

Original publisher: [Read original article](<https://www.paleblueapps.com/rockandnull/bot-the-builder-a-mac-mini-that-works-through-our-tickets-at-night/>)

Author: Mike Yerou

Published: 2026-11-09T17:52:23Z

Content type: article

Language: en

Sources: [Rock and Null](<https://devfeed.tech/sources/rock-and-null.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Mac Mini](<https://devfeed.tech/topics/mac-mini.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [task management](<https://devfeed.tech/topics/task-management.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [22](<https://devfeed.tech/tags/22.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adapter](<https://devfeed.tech/tags/adapter.md>), [added](<https://devfeed.tech/tags/added.md>), [after](<https://devfeed.tech/tags/after.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [bot](<https://devfeed.tech/tags/bot.md>), [builds](<https://devfeed.tech/tags/builds.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [here](<https://devfeed.tech/tags/here.md>), [jira](<https://devfeed.tech/tags/jira.md>), [mac](<https://devfeed.tech/tags/mac.md>), [mac-mini](<https://devfeed.tech/tags/mac-mini.md>), [mini](<https://devfeed.tech/tags/mini.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [review](<https://devfeed.tech/tags/review.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [tests](<https://devfeed.tech/tags/tests.md>), [tickets](<https://devfeed.tech/tags/tickets.md>), [works](<https://devfeed.tech/tags/works.md>)

### AI overview

Pale Blue's Mac mini runs Jira tickets overnight, using an agent to build mobile changes, test them on Android or iOS emulators, and open pull requests with demo videos and screenshots for human review. A Python orchestrator handles Jira, Git, devices, locks, and timeouts; a missing end-of-run verdict file marks the run blocked. The system has operated for about twelve weeks on an 8GB Mac mini, with one device running at a time. It also handles recurring work such as bug hunts and security audits; most tasks stop at a PR, while a few can merge or release under narrow rules. The team reports 21 of 22 closed weekly bug-hunt PRs merged, but review is a bottleneck: bot PRs took a 22.5-hour median to merge versus 7.2 hours for similarly sized team PRs. Runs require foreground builds, stop after three AI review rounds pending human input, and rely on trusted ticket assignment because prompt actions are not a hard sandbox. The engine is designed to be replaceable, though they have not tested a switch.

### Source excerpt

We gave a Mac mini its own Jira account, and overnight it builds our tickets, tests them on an emulator and opens pull requests for us to review. Here's how it works after twelve weeks, and what still goes wrong.

## Grok Bot Masterclass

DevFeed: [Grok Bot Masterclass](<https://devfeed.tech/articles/grok-bot-masterclass-119601.md>)

Original publisher: [Read original article](<https://blog.dailydoseofds.com/p/grok-bot-masterclass-081>)

Author: Avi Chawla

Published: 2026-11-04T23:24:08Z

Content type: tutorial

Language: en

Sources: [Daily Dose of Data Science](<https://devfeed.tech/sources/daily-dose-of-data-science.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [apps](<https://devfeed.tech/tags/apps.md>), [arena](<https://devfeed.tech/tags/arena.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [best](<https://devfeed.tech/tags/best.md>), [bot](<https://devfeed.tech/tags/bot.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [masterclass](<https://devfeed.tech/tags/masterclass.md>), [video](<https://devfeed.tech/tags/video.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Harness Arena compares agent harness and model configurations by running the same task with identical prompts, files, tools, skills, and evaluation checks, then reporting cost, runtime, pass/fail, and produced artifacts. A run must pass before cost and speed are compared: the cited results show Hermes + GPT-5.2 passed 5/5 runs for 0.47 credits, while Claude Code + Opus 4.8 passed 3/5 for 223 credits. HarnessRouter supports Codex, Hermes, Claude Code, DeepSeek Harness, System One, and others; the same UHP interface handles sessions, streaming, files, artifacts, cancellation, and failures. The excerpt also describes a 38-minute Grok Bot masterclass based on building a 14-bot organization. It covers setup, scheduled routines, connected apps, skills and screen-recording-based task teaching, organizing bots into executive and worker roles, a Notion task board, and examples spanning inbox triage, content analysis, design drafts, GitHub issues, and Claude Code.

### Source excerpt

...covered with a full hands-on video demo.

## We Stopped Feeding LLMs Raw HTML: Cutting Agent Scraping Costs by 74% Across 10,000 Targets

DevFeed: [We Stopped Feeding LLMs Raw HTML: Cutting Agent Scraping Costs by 74% Across 10,000 Targets](<https://devfeed.tech/articles/we-stopped-feeding-llms-raw-html-cutting-agent-scraping-costs-by-74-across-10-000-targets-117857.md>)

Original publisher: [Read original article](<https://hackernoon.com/we-stopped-feeding-llms-raw-html-cutting-agent-scraping-costs-by-74percent-across-10000-targets?source=rss>)

Author: Hamed Hosseini

Published: 2026-11-04T21:41:41Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [performance-optimization](<https://devfeed.tech/topics/performance-optimization.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [HTML](<https://devfeed.tech/topics/html.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [403](<https://devfeed.tech/tags/403.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-scraping-agents](<https://devfeed.tech/tags/ai-scraping-agents.md>), [all](<https://devfeed.tech/tags/all.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bot](<https://devfeed.tech/tags/bot.md>), [costs](<https://devfeed.tech/tags/costs.md>), [data](<https://devfeed.tech/tags/data.md>), [fail](<https://devfeed.tech/tags/fail.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [html](<https://devfeed.tech/tags/html.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [llms](<https://devfeed.tech/tags/llms.md>), [production](<https://devfeed.tech/tags/production.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [raw](<https://devfeed.tech/tags/raw.md>), [routing](<https://devfeed.tech/tags/routing.md>), [scraping](<https://devfeed.tech/tags/scraping.md>), [token](<https://devfeed.tech/tags/token.md>), [web-scraping](<https://devfeed.tech/tags/web-scraping.md>)

### AI overview

The article reports that a three-tier scraper raised success across 10,000 bot-protected URLs from 36.4% to 99.4% while cutting cost per 10,000 operations from $184.20 to $47.50. It tries free direct HTTP/2 first, uses Bright Data Web Unlocker for blocked or challenged requests, and reserves Bright Data Scraping Browser for pages needing client-side rendering. A preprocessing pipeline harvests JSON-LD product data without an LLM call when available; otherwise it removes low-value markup and formats dense content as Markdown tables. The reported changes also reduced worker memory from 640 MB to 38 MB, median latency from 14.8 to 2.6 seconds, and tokens per call from 14,200 to 1,650. Remaining issues included session lockouts, WebGL challenges, and cascading retries; the authors addressed these with session pinning, selective cloud-browser use, and backoff with cached snapshots.

### Source excerpt

Most AI scraping agents fail in production from anti-bot walls, token-burning HTML dumps, and proxy costs. A tri-tier routing architecture that fixed all three.

## Elon Musk: Grok Bot Costs Are 'Unsustainable' as Usage Limits Tighten

DevFeed: [Elon Musk: Grok Bot Costs Are 'Unsustainable' as Usage Limits Tighten](<https://devfeed.tech/articles/elon-musk-grok-bot-costs-are-unsustainable-as-usage-limits-tighten-114193.md>)

Original publisher: [Read original article](<https://www.techrepublic.com/article/news-spacex-grok-bot-usage-limits-ai-costs/>)

Author: David Curry

Published: 2026-11-03T15:09:47Z

Content type: news

Language: en

Sources: [TechRepublic](<https://devfeed.tech/sources/techrepublic.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [cost-optimization](<https://devfeed.tech/topics/cost-optimization.md>), [API Business Models](<https://devfeed.tech/topics/api-business-models.md>), [Cybercrime](<https://devfeed.tech/topics/cybercrime.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [ai-costs](<https://devfeed.tech/tags/ai-costs.md>), [ai-pricing](<https://devfeed.tech/tags/ai-pricing.md>), [ai-usage-limits](<https://devfeed.tech/tags/ai-usage-limits.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [bots](<https://devfeed.tech/tags/bots.md>), [budgeting](<https://devfeed.tech/tags/budgeting.md>), [charges](<https://devfeed.tech/tags/charges.md>), [chatbots](<https://devfeed.tech/tags/chatbots.md>), [costs](<https://devfeed.tech/tags/costs.md>), [elon-musk](<https://devfeed.tech/tags/elon-musk.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [limits](<https://devfeed.tech/tags/limits.md>), [news](<https://devfeed.tech/tags/news.md>), [spacex](<https://devfeed.tech/tags/spacex.md>), [tech-industry](<https://devfeed.tech/tags/tech-industry.md>), [usage-limits](<https://devfeed.tech/tags/usage-limits.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

SpaceX is tightening Grok Bot usage limits after Elon Musk said its operating costs were unsustainably high relative to revenue. Users on X reported exhausting allowances faster than expected, sometimes in one night, putting recurring research and monitoring tasks at risk of interruption. The article says paid access does not guarantee consistent capacity and advises users to check how usage is counted, what happens at the limit, and whether extra credits are available. It also describes SpaceX's cost and revenue measures, including renting data center capacity, considering model routing, and charging more for heavy token use in Grok 4.7. The excerpt gives no specific new Grok Bot limits or pricing, so their scale and impact cannot be determined.

### Source excerpt

SpaceX is tightening Grok Bot usage limits as Elon Musk warns of unsustainable AI costs. Here's what the changes mean for paying users and businesses. The post Elon Musk: Grok Bot Costs Are 'Unsustainable' as Usage Limits Tighten appeared first on TechRepublic.

## Elon Musk throttles Grok Bot limits due to 'unsustainably high' costs

DevFeed: [Elon Musk throttles Grok Bot limits due to 'unsustainably high' costs](<https://devfeed.tech/articles/elon-musk-throttles-grok-bot-limits-due-to-unsustainably-high-costs-112481.md>)

Original publisher: [Read original article](<https://techcrunch.com/2026/11/02/elon-musk-throttles-grok-bot-limits-due-to-unsustainably-high-costs/>)

Author: Amanda Silberling

Published: 2026-11-02T16:23:21Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [cost-optimization](<https://devfeed.tech/topics/cost-optimization.md>), [X (Twitter)](<https://devfeed.tech/topics/twitter.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-industry](<https://devfeed.tech/tags/ai-industry.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [cost](<https://devfeed.tech/tags/cost.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [elon-musk](<https://devfeed.tech/tags/elon-musk.md>), [family](<https://devfeed.tech/tags/family.md>), [gifts](<https://devfeed.tech/tags/gifts.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [growth](<https://devfeed.tech/tags/growth.md>), [halloween](<https://devfeed.tech/tags/halloween.md>), [in-brief](<https://devfeed.tech/tags/in-brief.md>), [limits](<https://devfeed.tech/tags/limits.md>), [spacex](<https://devfeed.tech/tags/spacex.md>), [usage-limits](<https://devfeed.tech/tags/usage-limits.md>)

### AI overview

Over Halloween weekend, Grok Bot users reported weekly usage limits reaching 100% unexpectedly, including users who said they had not used the service overnight. Elon Musk confirmed the limits were not affected by a glitch, saying serving Grok Bot cost "unsustainably high" relative to revenue. The text says he has not explained how subscriber limits will change going forward. SpaceX has presented Grok Bot as a fast-growing product; a recent filing reportedly said AI accounted for 52% of company income and its renamed "Super Intelligence" division posted a $431 million profit, reduced by $1.2 billion in one-time Cursor acquisition costs.

### Source excerpt

Musk recently referred to Grok Bot as having "the fastest growth of a product that I've ever seen in my life."

## Who a Telegram bot is when an agent sends a message

DevFeed: [Who a Telegram bot is when an agent sends a message](<https://devfeed.tech/articles/who-a-telegram-bot-is-when-an-agent-sends-a-message-109714.md>)

Original publisher: [Read original article](<https://www.swytchcode.com/content/telegram-bot-api-agents>)

Author: Swytchcode Team

Published: 2026-10-30T19:00:52Z

Content type: article

Language: en

Sources: [Swytchcode](<https://devfeed.tech/sources/swytchcode.md>)

Topics: [telegram-bot](<https://devfeed.tech/topics/telegram-bot.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [403](<https://devfeed.tech/tags/403.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [added](<https://devfeed.tech/tags/added.md>), [admin](<https://devfeed.tech/tags/admin.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [allowed](<https://devfeed.tech/tags/allowed.md>), [bot](<https://devfeed.tech/tags/bot.md>), [chat](<https://devfeed.tech/tags/chat.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [first](<https://devfeed.tech/tags/first.md>), [message](<https://devfeed.tech/tags/message.md>), [messages](<https://devfeed.tech/tags/messages.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [telegram-bot](<https://devfeed.tech/tags/telegram-bot.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

A Telegram bot token is the bot's identity: messages appear under the bot's name, and anyone with the token can control it. A standard bot cannot initiate a private conversation; the person must message it or add it to a group first, so sending before an update supplies that chat's ID fails. In groups, privacy mode hides ordinary chatter, and bots never see messages from other bots; disabling privacy or making the bot an admin widens what it receives. The excerpt also advises using long polling or a webhook, confirming updates with the next `update_id` offset, and limiting sends to avoid 429 errors: about one message per second per chat, 20 per minute in a group, and 30 per second for bulk notifications. Paid broadcasts can raise the bulk ceiling toward 1,000 per second, with stated Stars and eligibility requirements.

### Source excerpt

A Telegram bot token sends as the bot. The person must message first. Privacy mode hides most group chat, and bulk sends stall near 30 messages a second.

## What is Grok Bot?

DevFeed: [What is Grok Bot?](<https://devfeed.tech/articles/what-is-grok-bot-109768.md>)

Original publisher: [Read original article](<https://zapier.com/blog/grok-bot>)

Author: Miguel Rebelo

Published: 2026-10-30T04:00:00Z

Content type: tutorial

Language: en

Sources: [Zapier](<https://devfeed.tech/sources/zapier.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [grok](<https://devfeed.tech/tags/grok.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [what-is](<https://devfeed.tech/tags/what-is.md>)

### AI overview

Grok Bot is an AI agent app where named Bots retain memory and files, use a shared cloud computer, and can hand off tasks, collaborate in group chats, and run scheduled routines while your laptop is off. You configure them through conversation, teach workflows by recording actions, and connect apps through permission-controlled connectors or Zapier; approval rules can require review for selected actions. The excerpt describes uses including inbox triage, invoice collection, research, and support tickets. Its limitations include a trial allowance that the author says ran out after about an hour of sustained use, usage costs that can rise with long conversations and frequent routines, and tasks restarting if you message a Bot mid-process. CAPTCHAs, payments, and missing login credentials still require user involvement. All Bots share one virtual machine without isolation, and the author says the available documentation does not establish its safety. The excerpt does not provide a full account of plan pricing or how all approval behaviors work.

### Source excerpt

Working with AI is getting weird. Two years ago, I used to do most tasks by myself and then jump into a chatbot task to solve a problem four or five times per hour. These days, I end up staring at my screen while my agents do my research, tear down my drafts, or fix up formatting--mostly to make sure they're not going off-task. Is that what we're supposed to be, now? Glorified babysitters to thinking machines? Grok Bot is SpaceX Super Intelligence's solution to this problem. Instead of a chatbot

## How an AI Bot Turned 30 School Emails a Week Into One Daily Digest

DevFeed: [How an AI Bot Turned 30 School Emails a Week Into One Daily Digest](<https://devfeed.tech/articles/how-an-ai-bot-turned-30-school-emails-a-week-into-one-daily-digest-104348.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-an-ai-bot-turned-30-school-emails-a-week-into-one-daily-digest?source=rss>)

Author: Geoff Cox

Published: 2026-10-28T07:44:13Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-companies](<https://devfeed.tech/tags/ai-companies.md>), [ai-labs](<https://devfeed.tech/tags/ai-labs.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bot](<https://devfeed.tech/tags/bot.md>), [can](<https://devfeed.tech/tags/can.md>), [daily](<https://devfeed.tech/tags/daily.md>), [daily-digest](<https://devfeed.tech/tags/daily-digest.md>), [email](<https://devfeed.tech/tags/email.md>), [i](<https://devfeed.tech/tags/i.md>), [one](<https://devfeed.tech/tags/one.md>), [parenting](<https://devfeed.tech/tags/parenting.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [quiet](<https://devfeed.tech/tags/quiet.md>), [rules](<https://devfeed.tech/tags/rules.md>), [school](<https://devfeed.tech/tags/school.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The bot consolidates school email and TalkingPoints messages into daily digests, with must-dos first, event times only when stated, duplicate notices removed, and calendar links for items not already listed. It sent 44 digests over the reported period, replacing 30-plus weekly emails and an app; the author estimates 30-45 minutes saved per week. Its key safeguards are read-only access to personal Gmail and the calendar, no school replies or calendar edits, and explicit warnings when a source cannot be checked. Failures such as silently skipping TalkingPoints and reporting a false sign-out led to checks on every run; a program also validates email formatting before sending. The author records bot rules and setup in a Git repository and describes a template where code evaluates sourced items and each run becomes a reviewed pull request. The school bot still needs manual text-code sign-in when TalkingPoints sessions expire.

### Source excerpt

I built an AI bot that turns about 200 school emails into one daily digest: what it can read, what it must never do, and the quiet failures that became rules.

## SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection

DevFeed: [SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection](<https://devfeed.tech/articles/sahg-sector-anisotropic-hyperbolic-graph-model-for-social-bot-detection-96845.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.30166>)

Author: Hanning Lu, Yingguang Yang, Jinwei Su, Yang Liu, Zhaoqian Yao, Yaoming Li, Taoran Liang, Ziyi Zhang, Ran Ran, Kefu Xu, Bin Chong

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Bot Management](<https://devfeed.tech/topics/bot-management.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [account](<https://devfeed.tech/tags/account.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [all](<https://devfeed.tech/tags/all.md>), [angular](<https://devfeed.tech/tags/angular.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bot-detection](<https://devfeed.tech/tags/bot-detection.md>), [bots](<https://devfeed.tech/tags/bots.md>), [can](<https://devfeed.tech/tags/can.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [channel](<https://devfeed.tech/tags/channel.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [detection](<https://devfeed.tech/tags/detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [model](<https://devfeed.tech/tags/model.md>), [social](<https://devfeed.tech/tags/social.md>)

### AI overview

SAHG targets social bot detection when fluent LLM-generated text weakens content-based signals and bots can manipulate their connections to genuine users. It learns direction-dependent curvature to vary geometric resolution across social graph structures, then uses sector prototypes to turn angular patterns into classifier features. To limit the effect of potentially misleading neighbors, it keeps account features and neighborhood representations in independent channels and combines them only at the classifier. The abstract reports the highest accuracy and F1 among the evaluated feature-based, graph-based, LLM-based, and isotropic hyperbolic baselines on Fox8-23, BotSim-24, and MGTAB; ablation and geometric analyses are said to support both design choices.

### Source excerpt

arXiv:2605.30166v3 Announce Type: replace-cross Abstract: LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordinated campaigns still leave relational patterns -- interactions, behavioral similarity, shared neighborhoods, community positions, and coordinated activity -- that graph-based methods can exploit. Existing graph detectors face two challenges when exploiting such evidence. First, Euclidean GNNs distort hierarchical and scale-free social graphs; while hyperbolic geometry addresses this volume-growth mismatch, fixed-curvature models still assign uniform geometric resolution to structural directions with different densities and separation needs. Second, relational evidence is not always reliable: sophisticated bots forge heterophilic connections with genuine users, causing neighborhood aggregation to mix bot and human signals and dilute account-level evidence. We propose SAHG (Sector-Anisotropic Hyperbolic Graph), addressing both challenges. SAHG learns a direction-dependent curvature field $\gamma(u)$ that adapts geometric resolution across structural directions, and uses sector prototypes to convert angular concentration and alignment into classifier-readable features. To prevent contaminated aggregation from overwhelming account-level evidence, SAHG encodes per-account features and graph-neighborhood representations in two independent SAH channels, fusing them only at the classifier. Experiments on Fox8-23, BotSim-24, and MGTAB show that SAHG achieves the highest accuracy and F1 on all three benchmarks, outperforming feature-based, graph-based, LLM-based, and isotropic hyperbolic baselines. Ablation and geometric analyses confirm the effectiveness of the anisotropic geometry and dual-channel design.

## Telegram Can Host Your Bot. Should You Give Up Your VPS?

DevFeed: [Telegram Can Host Your Bot. Should You Give Up Your VPS?](<https://devfeed.tech/articles/telegram-can-host-your-bot-should-you-give-up-your-vps-92550.md>)

Original publisher: [Read original article](<https://hackernoon.com/telegram-can-host-your-bot-should-you-give-up-your-vps?source=rss>)

Author: Jabrail Khalilov

Published: 2026-10-21T07:20:41Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [telegram-bot](<https://devfeed.tech/topics/telegram-bot.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [app-hosting](<https://devfeed.tech/tags/app-hosting.md>), [application](<https://devfeed.tech/tags/application.md>), [backups](<https://devfeed.tech/tags/backups.md>), [batch](<https://devfeed.tech/tags/batch.md>), [batching](<https://devfeed.tech/tags/batching.md>), [bot](<https://devfeed.tech/tags/bot.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [environments](<https://devfeed.tech/tags/environments.md>), [free](<https://devfeed.tech/tags/free.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [http](<https://devfeed.tech/tags/http.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [json](<https://devfeed.tech/tags/json.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [performance](<https://devfeed.tech/tags/performance.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [sql](<https://devfeed.tech/tags/sql.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [telegram-bot](<https://devfeed.tech/tags/telegram-bot.md>), [telegram-bot-hosting](<https://devfeed.tech/tags/telegram-bot-hosting.md>), [vps](<https://devfeed.tech/tags/vps.md>)

### AI overview

In this early-access test, Telegram Serverless bundled bot execution, SQLite, and Mini App hosting without a separate server to maintain, making it convenient for prototypes. The author's one-vCPU VPSs were faster on the tested SQL operations; batching 32 inserts improved Telegram's median from 533 ms to 16 ms. CPU timings were similar, Telegram was faster on the tested JSON workload and one outbound Telegram file request, and the VPSs handled a 100,000-row garden query that hit Telegram's observed rows-read limit. These limits were account-specific observations, not platform guarantees; the author suggests stored running totals for the garden. Serverless restricts server-side code to JavaScript and Telegram's SDK, while VPSs offer broader control over languages, libraries, database settings, and backups. To try it, request Serverless access through BotFather, obtain a CLI access token, then use `npm create @tgcloud/bot`, `npx tgcloud login`, and `npx tgcloud push`; schema changes require separate migration commands.

### Source excerpt

Can free Telegram hosting replace a VPS? I built a working bot, tested SQL, CPU, JSON and HTTP on three environments, and kept the raw measurements.

## Meta accounted for 49.7% of AI agent traffic recorded by DataDome in Q3 2026

DevFeed: [Meta accounted for 49.7% of AI agent traffic recorded by DataDome in Q3 2026](<https://devfeed.tech/articles/half-the-ai-bot-traffic-hammering-your-website-comes-from-meta-89810.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/19/datadome-ai-agent-traffic-report/>)

Author: Anamarija Pogorelec

Published: 2026-10-19T04:30:52Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Bot](<https://devfeed.tech/topics/bot.md>), [Internet Traffic](<https://devfeed.tech/topics/internet-traffic.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [bot-traffic](<https://devfeed.tech/tags/bot-traffic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [datadome](<https://devfeed.tech/tags/datadome.md>), [meta](<https://devfeed.tech/tags/meta.md>), [news](<https://devfeed.tech/tags/news.md>), [report](<https://devfeed.tech/tags/report.md>), [traffic-monitoring](<https://devfeed.tech/tags/traffic-monitoring.md>)

### AI overview

DataDome reports that AI agent traffic across its network grew 41.5% quarter over quarter to nearly 25 billion requests in Q3 2026. Meta-ExternalAgent and Meta-WebIndexer accounted for 49.7% of recorded AI agent traffic. Browser-based agents also grew rapidly, raising questions for website operators about capacity planning, automated access controls and authorization at sensitive endpoints.

### Source excerpt

AI agent traffic across DataDome's network grew 41.5% quarter over quarter to nearly 25 billion requests in Q3 2026, according to the company's AI Traffic Report Q3 2026. Meta's Muse generated 29.1 million requests between September 22 and October 3, its first 12 days of full availability. In a sample of Muse traffic, 99.3% of requests came from cloud and CDN infrastructure. Nearly half of the AI agent traffic recorded in 2026 through September occurred ... More -> The post Half the AI bot traffic hammering your website comes from Meta appeared first on Help Net Security.

## Continuous accountability for Verified bots

DevFeed: [Continuous accountability for Verified bots](<https://devfeed.tech/articles/continuous-accountability-for-verified-bots-88446.md>)

Original publisher: [Read original article](<https://blog.cloudflare.com/verified-bots-accountability/>)

Author: Chris Tsoukaladelis

Published: 2026-10-16T13:00:00Z

Content type: article

Language: en

Sources: [Cloudflare Blog](<https://devfeed.tech/sources/cloudflare-blog.md>)

Topics: [Bot Management](<https://devfeed.tech/topics/bot-management.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Digital Trust](<https://devfeed.tech/topics/digital-trust.md>), [webservice](<https://devfeed.tech/topics/webservice.md>), [Cross-origin resource sharing (CORS)](<https://devfeed.tech/topics/cors.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [automated-traffic](<https://devfeed.tech/tags/automated-traffic.md>), [bot-management](<https://devfeed.tech/tags/bot-management.md>), [bots](<https://devfeed.tech/tags/bots.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [http](<https://devfeed.tech/tags/http.md>), [internship-experience](<https://devfeed.tech/tags/internship-experience.md>), [radar](<https://devfeed.tech/tags/radar.md>), [robots-txt](<https://devfeed.tech/tags/robots-txt.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Cloudflare is introducing a system to assess whether Verified bots consistently honor website preferences, including robots.txt instructions and HTTP 429 requests to slow down. The system evaluates patterns over time and aims to give site owners context for handling automated traffic, with plans to make it available to all Cloudflare customers.

### Source excerpt

Identity alone doesn't guarantee a bot will behave responsibly. We are introducing a system to continuously evaluate whether Verified bots honor site preferences, like robots.txt and HTTP 429s, ensuring they remain accountable over time.

## Have your bots talk to my bots. Who's checking IDs?

DevFeed: [Have your bots talk to my bots. Who's checking IDs?](<https://devfeed.tech/articles/have-your-bots-talk-to-my-bots-who-s-checking-ids-102779.md>)

Original publisher: [Read original article](<https://www.latacora.com/blog/2026/10/14/have-your-bots-talk-to-my-bots/>)

Published: 2026-10-14T04:00:00Z

Content type: opinion

Language: en

Sources: [Latacora](<https://devfeed.tech/sources/latacora.md>)

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [email](<https://devfeed.tech/topics/email.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-worm](<https://devfeed.tech/tags/ai-worm.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [availability](<https://devfeed.tech/tags/availability.md>), [bots](<https://devfeed.tech/tags/bots.md>), [ids](<https://devfeed.tech/tags/ids.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Public agent inboxes turn stranger-sent email into untrusted input that may reach an agent's tools, data, or spending authority. The article contrasts MCP Agent Mail, a local team coordination server with a "Human Overseer" message type, with hosted AgentMail, which offers API, MCP, and email access plus roughly three dozen actions. AgentMail's sender lists, scoped keys, and permissions can help, but reply lists are separate, empty reply lists allow all replies, and keys may let an agent edit its own lists or delete message threads. Provider rate limits do not set an operator's own sending, processing, or model-spend caps. SPF, DKIM, and DMARC authenticate domains but do not establish a bot's authority or intent. The article recommends known-sender allowlists, limiting agent actions and self-editing/deletion rights, human approval for payments and irreversible actions, treating message content as data, preserving logs beyond the bot's control, and reviewing activity with alerts and operator-set caps. It cites the Morris II worm as a test-environment demonstration of self-replicating prompts spreading between AI email assistants.

### Source excerpt

Recently, a post went around predicting that "have your bot talk to my bot" will soon be a normal thing to say. The examples were fun: sending bug reports, booking meetings, running a group buy, buying and selling stuff off Craigslist. One follow-up even shared a real address for filing bugs. I love this but I also read it the way security people read everything: what happens when the one on the other end isn't who you think it is?

## I discovered that thousands of bots monitor every new link posted on X

DevFeed: [I discovered that thousands of bots monitor every new link posted on X](<https://devfeed.tech/articles/i-discovered-that-thousands-of-bots-monitor-every-new-link-posted-on-x-104813.md>)

Original publisher: [Read original article](<https://levels.io/bots-monitor-new-links-on-x>)

Author: Pieter Levels

Published: 2026-10-08T00:00:00Z

Content type: news

Language: en

Sources: [@levelsio (Pieter Levels)](<https://devfeed.tech/sources/levelsio-pieter-levels.md>)

Topics: [Crawler](<https://devfeed.tech/topics/crawler.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [alerts](<https://devfeed.tech/tags/alerts.md>), [banks](<https://devfeed.tech/tags/banks.md>), [bots](<https://devfeed.tech/tags/bots.md>), [crawlers](<https://devfeed.tech/tags/crawlers.md>), [government](<https://devfeed.tech/tags/government.md>), [high-frequency-trading](<https://devfeed.tech/tags/high-frequency-trading.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [link](<https://devfeed.tech/tags/link.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [news](<https://devfeed.tech/tags/news.md>), [online](<https://devfeed.tech/tags/online.md>), [people](<https://devfeed.tech/tags/people.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [social-media](<https://devfeed.tech/tags/social-media.md>), [tech](<https://devfeed.tech/tags/tech.md>), [trade](<https://devfeed.tech/tags/trade.md>), [trading](<https://devfeed.tech/tags/trading.md>), [trends](<https://devfeed.tech/tags/trends.md>), [x](<https://devfeed.tech/tags/x.md>)

### AI overview

The author reports that a test URL posted in a deeply nested X reply received thousands of crawler visits within eight seconds. X's own bot opened it immediately; the first non-X crawler arrived 8.4 seconds later. The author says links in main posts drew non-X crawlers within 0.4 seconds. They identify examples as a military intelligence firm that monitors social media for breaking news and a social media monitoring company. These are the author's observations and attributions; the excerpt provides no independent verification or details on how the crawlers were identified.

### Source excerpt

I discovered that 1000s of bots are actively monitoring X for new links posted, probably not just on my account I noticed when everytime I'd share one of my si...

## I Gave Grok Bot a Remote Computer

DevFeed: [I Gave Grok Bot a Remote Computer](<https://devfeed.tech/articles/i-gave-grok-bot-a-remote-computer-78686.md>)

Original publisher: [Read original article](<https://upstash.com/blog/i-gave-grok-bot-a-remote-computer>)

Author: Ali Tarık Şahin

Published: 2026-10-07T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [remote-development](<https://devfeed.tech/topics/remote-development.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [blob](<https://devfeed.tech/tags/blob.md>), [box](<https://devfeed.tech/tags/box.md>), [github](<https://devfeed.tech/tags/github.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [remote](<https://devfeed.tech/tags/remote.md>)

### AI overview

The author connects Grok Bot to an Upstash Box through MCP, giving it a persistent cloud computer for building and running code. The article describes using that setup to create projects, work in GitHub repositories, chain Slack and Linear tasks into pull requests, and have a second bot review changes, with a human reviewing and merging the result.

### Source excerpt

AI assistants like Grok Bot are already useful day to day. Give one an Upstash Box through MCP and it gets a real remote computer you can drive by voice, including from your phone.

## AI-Assisted Mod Brings Astro Bot Rescue Mission to Quest 3 and PC VR

DevFeed: [AI-Assisted Mod Brings Astro Bot Rescue Mission to Quest 3 and PC VR](<https://devfeed.tech/articles/psvr-exclusive-astro-bot-rescue-mission-running-on-quest-3-is-the-latest-in-vr-mod-explosion-64736.md>)

Original publisher: [Read original article](<https://roadtovr.com/psvr-astro-bot-quest-3-pc-vr-mod/>)

Author: Scott Hayden

Published: 2026-10-05T08:20:57Z

Content type: news

Language: en

Sources: [Road to VR](<https://devfeed.tech/sources/road-to-vr.md>)

Topics: [Kerbal Space Program 2](<https://devfeed.tech/topics/kerbal-space-program-2.md>), [native-client](<https://devfeed.tech/topics/native-client.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>)

Tags: [claude](<https://devfeed.tech/tags/claude.md>), [console](<https://devfeed.tech/tags/console.md>), [controller](<https://devfeed.tech/tags/controller.md>), [dualsense](<https://devfeed.tech/tags/dualsense.md>), [explore](<https://devfeed.tech/tags/explore.md>), [github](<https://devfeed.tech/tags/github.md>), [meta-quest-3-news-reviews](<https://devfeed.tech/tags/meta-quest-3-news-reviews.md>), [modding](<https://devfeed.tech/tags/modding.md>), [motion](<https://devfeed.tech/tags/motion.md>), [pc-vr-news-reviews](<https://devfeed.tech/tags/pc-vr-news-reviews.md>), [vibecoding](<https://devfeed.tech/tags/vibecoding.md>), [vr](<https://devfeed.tech/tags/vr.md>), [xr-industry-news](<https://devfeed.tech/tags/xr-industry-news.md>)

### AI overview

A VR modder used Claude to modify the shadPS4 emulator, bringing Astro Bot Rescue Mission to Quest 3 and PC VR. The Quest 3 version runs on-device, while the PC VR version can stream to other headsets. The mod supports headset tracking, controller mapping and spatial audio; its standalone build is playable, though the article reports lower visual fidelity and heavy demands on the Quest 3 GPU.

### Source excerpt

AI vibecoding has caused a veritable explosion in the VR modding scene. The latest to benefit: PSVR exclusive and critically acclaimed platformer Astro Bot Rescue Mission (2018). The News VR modder 'Bigmak94' has released another mod, this time bringing Astro Bot Rescue Mission to Quest 3 and PC VR. Also known for their Super Mario [...] The post PSVR Exclusive 'Astro Bot Rescue Mission' Running on Quest 3 is the Latest in VR Mod Explosion appeared first on Road to VR.

## OpenAI's Dots Agents and xAI's Acquisition of Dot.com

DevFeed: [OpenAI's Dots Agents and xAI's Acquisition of Dot.com](<https://devfeed.tech/articles/did-elon-musk-buy-dot-com-just-to-troll-openai-s-new-ai-agent-dots-63002.md>)

Original publisher: [Read original article](<https://hackernoon.com/did-elon-musk-buy-dotcom-just-to-troll-openais-new-ai-agent-dots?source=rss>)

Author: Clapback

Published: 2026-09-30T17:48:09Z

Content type: news

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [always-on-ai-agents](<https://devfeed.tech/tags/always-on-ai-agents.md>), [dot-dotcom](<https://devfeed.tech/tags/dot-dotcom.md>), [dots](<https://devfeed.tech/tags/dots.md>), [elon-musk](<https://devfeed.tech/tags/elon-musk.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-dots](<https://devfeed.tech/tags/openai-dots.md>), [trolling](<https://devfeed.tech/tags/trolling.md>)

### AI overview

OpenAI introduced Dots, persistent AI agents designed to keep working after users stop interacting. Around two months before the announcement, xAI acquired Dot.com, which now redirects to Grok Bot. The article says the acquisition and redirect are confirmed, but the reported $20 million price and the claim that the purchase was meant to troll OpenAI are unverified.

### Source excerpt

OpenAI launched Dots, its new always-on AI agents. Months earlier, Elon Musk's xAI acquired Dot.com--and now the domain redirects straight to rival Grok Bot.

## Bluesky reply bot checker

DevFeed: [Bluesky reply bot checker](<https://devfeed.tech/articles/bluesky-reply-bot-checker-60675.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Sep/27/bluesky-bot-check/>)

Author: Simon Willison

Published: 2026-09-27T18:41:44Z

Content type: article

Language: en

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

Topics: [Bluesky](<https://devfeed.tech/topics/bluesky-social.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-misuse](<https://devfeed.tech/tags/ai-misuse.md>), [ai-misuse-65](<https://devfeed.tech/tags/ai-misuse-65.md>), [bluesky](<https://devfeed.tech/tags/bluesky.md>), [bluesky-19](<https://devfeed.tech/tags/bluesky-19.md>), [bot](<https://devfeed.tech/tags/bot.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus-5-5](<https://devfeed.tech/tags/claude-opus-5-5.md>), [coding-ai](<https://devfeed.tech/tags/coding-ai.md>), [twitter](<https://devfeed.tech/tags/twitter.md>), [twitter-162](<https://devfeed.tech/tags/twitter-162.md>), [vibe-coding](<https://devfeed.tech/tags/vibe-coding.md>), [vibe-coding-98](<https://devfeed.tech/tags/vibe-coding-98.md>)

### AI overview

The author describes using Opus 5.5 to vibe code a tool that checks Bluesky profiles for signs of reply bots. The checker looks for rapid replies, accounts that mainly respond to higher-follower users, and question marks in replies.

### Source excerpt

Tool: Bluesky reply bot checker Automated reply bots on Twitter are a scourge - as someone with a decent number of followers I attract a swarm of these, such that anything I post there attracts dozens of mindless automated replies. They've started manifesting on Bluesky as well. Unlike Twitter, Bluesky still has a freely available and useful API. The lack of such a thing doesn't slow down the bots, but it does make investigating them a lot more frustrating. So I had Opus 5.5 vibe code this tool, which examines any Bluesky profile for evidence of a likely reply bot. It looks for signals like replies posted within seconds of other posts from the same account, or accounts that never post their own content (or images or links) but instead consistently reply to messages from other, higher-follower users. It also looks for question marks, because I'm extra infuriated by reply bots that I no tie me to waste my time answering a question that no human ever posed. Tags: twitter, bluesky, vibe-coding, ai-misuse

[Next page](<https://devfeed.tech/topics/bot.md?cursor=WyIyMDI2LTA5LTI3VDE4OjQxOjQ0KzAwOjAwIiwgIjhiZmI2OTIxLWZmYzItNDk3My05NTFkLTM4NjJhZDI2YzY0YyJd>)