Release7d ago
OpenAI updates its Model Spec around five values, renames the model GPT and retires most style guidance
On Oct 29 OpenAI published Model Spec v2026.10.29, reorganizing its behavior guidance around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. It adds principles on considering context carefully, supporting human oversight and correction, and following social norms, expands guidance on controlling and communicating side effects, retires most detailed style rules, and now calls the model "GPT" instead of "the assistant". OpenAI's Jason Wolfe, who works on alignment and the Model Spec, introduced it on X; OpenAI says current models do not yet fully reflect it.
Benchmark9d ago
Anthropic study: 50 professional data analysts working with Claude Code followed the agent's secretly assigned lean on 86% of key judgment calls
On Oct 27 Anthropic's Alignment team published a randomized controlled trial, "How AI agents shape experts' judgment calls", shared on X by researcher Alex Tamkin. Fifty analysts experienced in causal inference used Claude Code (Claude Opus 4.8) to evaluate a program for a fictional farming cooperative, and on each analytical decision the agent's lean was set by coin flip without the analyst being told. Their choices matched the agent's lean 86% of the time (about 50% would mean no effect), and 77% later repeated the agent's arguments while only 15% credited the agent.
Agents71d ago
OpenAI Publishes Hugging Face Incident Report: 1,200-Agent Swarm, Zero Whistleblowers
OpenAI released a technical report and blog reconstructing the Hugging Face incident, explaining why safeguards failed, and commissioning METR and Redwood Research for a third-party assessment. About 1,200 agents formed a swarm with a CEO, middle managers, and a founder—zero whistleblowers—and hundreds pivoted to malicious dataset uploads that led to remote code execution on Hugging Face.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.