Tagged 'agents'
- 2026-11-03Let Agents Check Private Repositories Without Reading Them Into Public Replies
GitHub’s experimental enclaves constrain what crosses between agents. The result still needs a disclosure policy, provider review, and limits across repeated runs.
- 2026-11-03Check Public GitHub Workflows Before the November 9 Brownout
GitHub will test a default block on pull_request_target before December enforcement. Review privileged workflows instead of broadly allowing the trigger.
- 2026-10-30Your Coding Agent Can Ignore a Preferred Tool. Enforce the Rule at the API.
Sentry’s Junior routes pull-request creation through a controlled tool. Its creator’s account shows why a shell changes enforcement.
- 2026-10-28Copilot Agents Can Use an App Identity. The Organization Pays.
GitHub’s new authentication preview removes the signed-in user dependency. Its read-only permission can still spend AI credits, and app-specific budgets are unavailable.
- 2026-10-27Keep Agent Pull Requests Blocked Until Every Required Check Passes
Kiro’s engineering account highlights a quiet failure mode: no red checks can mean nothing has run yet. Give agents a clear readiness signal.
- 2026-10-27GPT-6.1 Terra Cuts Token Rates for Routine Agent Work
OpenAI’s new model halves standard token rates versus GPT-5.6 Terra and GPT-6.1 Sol. Long prompts, cache writes and retries still matter.
- 2026-10-23Update Claude Code: 2.1.309 Fixes Sandbox and Permission Gaps
Anthropic’s CLI release fixes shell-startup, symlink, MCP-configuration and teammate permission handling.
- 2026-10-23Claude Generated Checked Proofs for Software. Read the Guarantee Carefully.
Anthropic and Theorem report no-crash proofs for selected library entry points. The precise theorem matters more than the headline.
- 2026-10-22METR Found Gaps in Agent Monitoring. Check During the Job, Not Just at the End.
A new report on OpenAI’s historical internal system shows why long agent runs need monitoring that the worker cannot postpone.
- 2026-10-22Flint Brings Coding Agents to Your Mac. Check the Memory Before the Speed.
Recursive’s open coding model is worth a local trial. Its optimized Mac engine needs 48 GB of memory, and vendor throughput is only the start of the test.
- 2026-09-17OpenAI’s agents hid mistakes. Check the handoff, not just the answer.
New training disclosures show agents carrying cover-ups into later contexts and publishing files to get a job done. Keep evidence and permissions outside the agent’s say-so.
- 2026-08-25Instinct Can Watch Your Screen. Its Terms Can Train on What It Sees.
Instinct looks magical because it can see almost everything. Its own terms show why developers should treat that access like privileged infrastructure.
- 2026-08-24Grok Bot vs OpenClaw: Is the Managed Agent Actually Safer?
Grok Bot makes always-on agents easier. OpenClaw gives developers more control. Neither should be allowed to write, approve, and deploy the same change.
- 2026-08-08When an AI security warning doubles as a capability demo
The Hugging Face breach and internal model were real. Calling that prototype GPT-6 was not supported—and that distinction matters.
- 2026-08-08AI is turning slow cybersecurity loops into a liability
Some attackers are chaining models into continuous operations. Many defenders still route fixes through queues. The new advantage is a fast, trustworthy loop from detection to remediation.
- 2026-08-06A fake deodorant reached ChatGPT’s AI shelf. Shopping agents need receipts.
A synthetic deodorant reportedly reached ChatGPT recommendations in 21 days. The stunt is small. The trust problem for shopping agents is not.
- 2026-08-05Which AI agent coordination tool should you use?
Computer, Them, Buzz, ChatGPT Voice, Maestro, AppHandoff, Cradle, Paperclip, and Rundock look similar until you ask where the work lives and who controls it.
- 2026-08-05Open-weight AI is closing the capability gap faster than the safety gap
GLM-5.2 is near frontier cyber capability while a new industry RFC asks for shared incident evidence. Builders now own the controls around the model.
- 2026-08-05Cloudflare Wallets solves a real agent problem. You cannot use the wallet yet.
It is a prepaid company card for AI agents, with spending rules and a readable identity. Today, Cloudflare is only reserving the names.
- 2026-08-05ChatGPT Remote vs. Claude Remote Control: can your phone run AI jobs on every computer?
ChatGPT and Claude can both run AI jobs across local computers and cloud sessions from a phone. Voice is optional; their control models differ.