First screen, captured .
Looks similar
Is your Postgres migration safe or not safe?(safenotsafe.dev)
117 points by vira28 | 40 comments
A browser-based tool that parses PostgreSQL migration SQL with libpg_query WASM and flags operations that may be unsafe, such as locking schema changes.
A breakthrough towards the Riemann hypothesis(mathstodon.xyz)
516 points by pera | 144 comments
A Mastodon post by Terence Tao describing Guth and Maynard's improvement to Ingham's 1940 zero density bound for the Riemann zeta function.
Terence Tao on O1(mathstodon.xyz)
626 points by dselsam | 404 comments
Mastodon post by mathematician Terence Tao describing his experiments with OpenAI's o1 model on research-level mathematical tasks.
OpenAI slams court order to save all ChatGPT logs, including deleted chats(arstechnica.com)
1074 points by ColinWright | 879 comments
A Mastodon post by Lauren Weinstein noting that, after a court order, OpenAI is preserving all ChatGPT user logs, including deleted and sensitive chats.
Related stories
SkillsBench: Benchmarking how well agent skills work across diverse tasks(arxiv.org)
333 points by mustaphah | 142 comments
arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.
2025: The Year in LLMs(simonwillison.net)
823 points by simonw | 451 comments
Simon Willison's annual blog post reviewing major LLM trends of 2025, including reasoning models, coding agents, Chinese open weight models, and Gemini.
Does Employment Slow Cognitive Decline? Evidence from Labor Market Shocks(nber.org)
327 points by littlexsparkee | 341 comments
NBER working paper by Kouchekinia, Neumark, and Bruckner examining whether employment slows cognitive decline using labor market shocks as evidence.
Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)
561 points by Anon84 | 136 comments
UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.
IRS to begin trial of its own free tax-filing system(nytimes.com)
606 points by thelastgallon | 261 comments
New York Times article about the IRS beginning a pilot of its own free online tax-filing system; the capture shows a CAPTCHA page.
GLM-Legal(z.ai)
660 points by ilreb | 357 comments
Z.ai research blog post introducing GLM-Legal, a language model aimed at agentic legal work such as analyzing source documents and producing client-ready work product.