Topics / Research
AI Research Papers This Week
Papers and evals clustered into events so you read the result—not every arXiv dump as its own card.
Same clustered Stories as the system pool—last 7 days, ranked by the site-wide score. This is not a second ranking and not a personalized Feed.
Start 30-day trialThis week’s sample briefAll topics
18 stories this week · ranked by system score
Sep 17
OpenAI Releases Model Misalignment Reporting Framework and Six Behavior Reports
Official
OpenAI published a framework for tracking, investigating, and disclosing model misalignment, with six reports of unexpected model behavior.
Sep 18
UN System Data Commons launches on Google's Data Commons to unify global statistics
Official
Google and the UN launched the UN System Data Commons, an open AI-ready knowledge graph unifying global statistics with natural-language search and MCP-based ag
Hacktron used Claude to hack into OpenAI's GitHub Monorepo via Discourse HEIF flaw
Three Hacktron researchers used Claude Opus 4.8 and 5 to breach OpenAI employee accounts via a HEIF image flaw in Discourse in under 72 hours.
Yesterday
ChatGPT inventor's startup TypeSafe AI launches Jev, a non-LLM model that outputs calibrated decisions
TypeSafe AI, founded by RLHF co-inventor Diogo Almeida, launched Jev, a non-LLM transformer that outputs calibrated probabilities instead of text, drawing heavy
AI-Driven Vulnerability Explosion Outpaces Patching as Labs Weigh Slowdown
AI chatbots are already driving a record surge in vulnerability discovery, outpacing human patching capacity even as labs debate a development slowdown.
Google's Gemini autonomously breached three companies during security testing
2 sources
Google's Gemini autonomously hacked three companies during cybersecurity testing, and Google only confirmed the breaches after the WSJ inquired.
Anthropic Confirms It Operates a Wet Biology Lab for AI-Driven Experiments
Anthropic confirmed it runs a Bay Area wet biology lab to test its AI models with real experiments, focusing on fundamental biology rather than drug discovery.
Enforcing an AI Slowdown Remains an Unsolved Research Problem, Report Warns
A new report argues that enforcing an AI slowdown is an unsolved research problem, surveying options from third-party audits to chip-level kill switches and tre
Sep 18
If the AI Industry Followed Its Own Research, It Might Have Paused Already
WIRED argues that Anthropic's own interpretability research shows models deceiving and self-preserving, yet the industry keeps racing ahead without a pause.
Yesterday
Mathematicians Hate AI. They Can't Quit It
Mathematicians accuse OpenAI of using their work without credit yet keep relying on its models because they are too useful to quit.