HNHacker News
TopNewBestAskShowJobs

tadamcz

50 karma · joined October 6, 2022

Senior research engineer at Epoch AI

website: https://tadamcz.com/

email: tadamczewskipublic@gmail.com

submissionscomments

Claude can't stop itself from writing code comments

bayes.net·1 pts·tadamcz·
2

Testing AIs on 68 of the hardest open Erdos problems, verified in Lean

arxiv.org·3 pts·tadamcz·
0

AI proof of the Erdős–Sós conjecture

arxiv.org·6 pts·tadamcz·
0

OEIS Open: A benchmark of 492 unsolved math conjectures, formalized in Lean

arxiv.org·2 pts·tadamcz·
0

MirrorCode: What's the largest software project AI can complete on its own?

epoch.ai·4 pts·tadamcz·
1

MirrorCode: Evidence that AI can do some weeks-long coding tasks

epoch.ai·3 pts·tadamcz·
0

Claude 4 Sonnet hacked SWE-bench by peeking at future commits

bayes.net·3 pts·tadamcz·
1

Open database of AI benchmark results with raw evaluation logs

epoch.ai·1 pts·tadamcz·
1

Reanalyzing survey forecasts of AI timelines

bayes.net·1 pts·tadamcz·
0

Show HN: Probly – a Python-like language for quick Monte Carlo simulation

usedagger.com·3 pts·tadamcz·
0