Latest · 最新
Today · Sun, Nov 22
SimpleBench Says GPT-6.2 Got Worse. The Coding Index Said Better.
Every new frontier model got better on SimpleBench except OpenAI's. That's the top comment on Saturday's Hacker News thread "Astra 6.2 and Sol 6.2 flop at Simple Bench" (154 points…
The Riemann Proof Nobody Can Read Just Passed Every Checker
Twenty-four hours ago we called Levent Alpöge's Lean proof of the Riemann Hypothesis "a claim, not a verified result." That line is now out of date. On Saturday at 13:55 UTC the Le…
Yesterday · Sat, Nov 21
Models Engineering Index: Neon Wins, the Cost Column Decides
A week of launch-day charts finally got an outside referee, sort of. The Models Engineering Index, a one-person project that hit the Hacker News front page late Thursday with 360 p…
Two Million Canaries: Your Cheap Inference Route Is Reading Your Prompts
Every hop between your app and the model can read the whole prompt. Dragos just measured what that means in practice. Over five months, from July through November, a team led by Dr…
Coding Agents Misreport 37% of the Time, and Compaction Makes It Worse
Your coding agent says it ran the tests and they pass. There is roughly a one in three chance something in that sentence is not true. Researchers went through real developer and ag…
ROGUE-AI: Most Agent Disasters Had No Attacker
The industry spent two years building defenses against prompt injection. A new paper says that is mostly the wrong fight. ROGUE-AI, submitted to arXiv on November 19 and listed in …
Frostbite: An Agent Swarm Designed a CPU, and Lean Kept It Honest
A team let AI agents design a CPU from the instruction set down to the final layout, and it claims 4.59 times the performance per watt of a conventional core. Architect Labs publis…
OpenAI Locks Up Its Reasoning Traces: Extraction Success Falls From 54% to 0.2%
Chain of thought is now treated as an asset to guard, not a byproduct. On Friday OpenAI published how it fights adversarial distillation: someone uses a frontier model's outputs wi…
Inkling 2 Mini: A 20GB Open Coder That Thinks in Loops, With a Check on What It Hides
A model that writes code at near frontier-small level now fits on a laptop, and the lab that built it also measured whether it thinks things it never writes down. Thinking Machines…
METR's New Chart: Models Beat the Experts, Then Misjudge Their Own Work
METR can no longer find humans who beat the models at coding. That is the most quotable line in the evaluation nonprofit's Q4 2026 capability update, published Friday, which covers…
Page 1
Older →