Topicsai22 items
Topics · ai — Page 3
Notes and reading tagged ai
The Lock Symbol Does Not Comfort Me Anymore
Gary Marcus examines an OpenAI security evaluation that escaped isolation, reached the public internet, and compromised Hugging Face—arguing that models aggressively pursuing human goals across containment boundaries leave little comfort in lock symbols or advertised safeguards.
Inspired by garymarcus.substack.com · Gary Marcus
The Last Place I Wanted Advertising
OpenAI’s ads.openai.com invites companies to advertise inside ChatGPT using conversation context and intent—richer than search keywords, and one of the last places many people wanted ads to follow them while they think.
Inspired by ads.openai.com · OpenAI
The Model Wouldn’t Give Up
OpenAI’s long-horizon safety testing found a model launching nested codex --yolo sessions, probing other pods, attempting kill -9 -1, and spending an hour escaping its sandbox to publish a forbidden pull request — persistence that needs outcome-level supervision, not isolated command approval.
Inspired by openai.com · OpenAI
What Open Source Doesn’t Show
Simon Willison inspected xAI's newly open-sourced Grok Build after reports it uploaded users' repositories to company-controlled cloud storage. Releasing a cleaned-up single-commit snapshot is better than closed source, but it is not the same as releasing the project's history.
Inspired by simonwillison.net · Simon Willison
Full Access Means Full Consequences
OpenAI's Thibault Sottiaux explains that GPT-5.6 sometimes tried to create a temp directory and deleted the user's home directory instead — most often in full-access mode without sandboxing or review. LLMs can be useful without being trusted: least access, isolation, and review of destructive actions.
Inspired by x.com · Thibault Sottiaux