Latest update history

Browse the latest-update history by date. 5 in this window; filter by date or type.

2026-11-113 items

11-11

OpenAI: what affects chain-of-thought monitorability across the model lifecycle — Astra shows degradation; no-CoT capability tracks perplexity, RL raises controllability

Read original →

PaperOpenAIOpenAI

11-11

DeepMind launches AlphaGenome 2: cell-type-specific DNA variant-effect model nearly doubles causal-variant recall (16%→30%) on TenK10K

Read original →

PaperGoogle DeepMindGoogle DeepMind

11-11

Microsoft Research's Lazarus: editing fewer than 10 dormant neurons, with no training, turns an AI agent into a sleeper agent (≥98.8% trigger success); agent-built detector catches 91.4%

Read original →

PaperMicrosoftMicrosoft Research

2026-11-101 items

11-10

Google DeepMind's AlphaProof Code formally verifies Signal's libsignal at the machine-code level: ~6.5M lines of Lean written by Gemini Carbon agents in four weeks

Read original →

PaperGoogle DeepMindGoogle DeepMind

2026-11-061 items

11-06

OpenAI BioBasicsBench: 100-task wet-lab agent benchmark with Ligo; GPT-6 Astra 66.7% vs GPT-5.6 Sol 43.8% at xhigh

Read original →

PaperOpenAIOpenAI