Anthropic's Claude Formally Proved Fermat's Last Theorem in 11 Days
Claude autonomously wrote a 13 million line Lean proof of Fermat's Last Theorem in 11 days, verifying 29,500 supporting theorems along the way.
// Intelligence
Reasoning
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
Researchers Crack Open GPT-OSS-20b to Find Hidden Symbol Systems Inside
An 8-year interpretability project shows that LLM representations can be closely approximated by symbolic role-filler structures, enabling precise behavioral edits.
MIT's SwarmWorld Shows 200 AI Agents Building a Society Without Talking
MIT researchers put hundreds of identical LLM agents into a persistent world and watched them evolve specialization, tool inheritance, and technology that survives without them.
ReViSQL-K2.6 Beats Human Accuracy on SQL Benchmark Without Agentic Scaffolding
A UIUC and Bridgewater team fine-tuned Kimi-K2.6 on Tinker to become the first text-to-SQL model to beat human accuracy.
Prefix Sliding Cuts Reasoning AI Memory Costs With a 3x Speedup
A new method throws away most of a model's own reasoning trace mid-thought, cutting memory to a fixed cap and running inference 3x faster.
Goodfire's Forking Fast Slashes AI Reasoning Debug Costs by 100x
Goodfire's new paper makes resampling analysis of reasoning chains dramatically cheaper, letting researchers pinpoint the tokens that actually decide an LLM's answer.
CMU's Jeremy Avigad Says AI Math Is Bigger Than Theorem Provers
Jeremy Avigad argues the fixation on neural theorem provers hides a far richer landscape of ways AI is reshaping how mathematics gets done.
DeepSeek V4 Pro Hits 90% on ARC-AGI-1 but Stalls on Harder Puzzles
DeepSeek V4 Pro hits 90.5% on ARC-AGI-1 and 61.3% on ARC-AGI-2, but extra reasoning barely moves the needle on abstract puzzles.
No stories match these filters.