haosenwang1018
b5ba8ac00d
fix NaN loss not caught by fast-fail check
...
`train_loss_f > 100` silently passes on NaN because IEEE 754 NaN
comparisons always return False. When an agent experiment produces
NaN (e.g. from an aggressive LR change), the run wastes the full
5-minute budget instead of failing fast.
`not (x <= 100)` catches both >100 and NaN with no added complexity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 23:51:02 +08:00
Andrej Karpathy
068d93da75
clarify that results.tsv should not be committed, leave untracked
2026-03-09 05:11:07 +00:00
Andrej Karpathy
c92bee55eb
some docs on what to play with to make autoresearch better on smaller computers
2026-03-09 04:49:15 +00:00
Andrej Karpathy
2224cd7cae
reshuffle readme a bit and link to tiny stories for apple silicon guidance
2026-03-08 23:25:53 +00:00
Andrej Karpathy
f16ece488f
clarification to baseline run instruction, there was some language from a previous version that wasn't fully cleaned up
2026-03-08 23:16:30 +00:00
Andrej Karpathy
9264224a3c
add notable fork mlx
2026-03-08 17:06:29 +00:00
Andrej
500114a035
Honor --download-workers instead of hardcoding 8 download workers
2026-03-07 14:17:45 -08:00
Andrej Karpathy
7043095a18
add macos fork
2026-03-07 22:15:52 +00:00
Dipesh Babu
777e443790
fix(prepare): honor --download-workers
2026-03-07 15:39:17 -05:00
Andrej Karpathy
6fdefa7265
instruct the agent to also read README, should be good context
2026-03-07 20:09:51 +00:00
Andrej Karpathy
b0d047425f
clarify note on platforms
2026-03-07 19:46:27 +00:00
Andrej Karpathy
8a5c4869bd
bunch of small changes to docs and files, and a teaser figure with a blooper :)
2026-03-07 19:00:04 +00:00
Andrej Karpathy
032d203695
minor tweaks, pin val shard
2026-03-07 17:59:52 +00:00
Andrej Karpathy
47ec1ade0a
tweaks to docs for both humans and agents
2026-03-07 17:02:43 +00:00
Andrej Karpathy
ada84e5247
soften the language just a bit
2026-03-07 16:29:59 +00:00
Andrej
bd75534494
Fix agent crash blindspot by forcing it to read traceback
2026-03-07 08:23:51 -08:00
dumko2001
bdf0c0d520
Allow agent to diagnose crashes by reading the python stack trace
2026-03-07 14:46:43 +05:30
Andrej
bb54287479
Merge pull request #2 from marcinbogdanski/fix/fa3-non-hopper-fallback
...
add fallback FA3 kernel for non-Hopper GPUs
2026-03-06 21:59:49 -08:00
Marcin Bogdanski
17b480aa65
add fallback FA3 kernel for non-Hopper GPUs
2026-03-07 01:31:48 +00:00
Andrej Karpathy
9c383a8c94
add analysis notebook for convenience
2026-03-06 22:36:37 +00:00
Andrej Karpathy
69eb7f9b99
cleanup more references to spawn.sh
2026-03-06 22:36:20 +00:00
Andrej Karpathy
ae81d55904
remove spawn.sh reference from README (file was deleted)
...
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 22:08:45 +00:00
Andrej Karpathy
4ab35a919b
also ref twitter
2026-03-06 22:06:12 +00:00
Andrej Karpathy
1e207aaf21
dam, erase experimental file from before that snuck through in my purge
2026-03-06 22:03:27 +00:00
Andrej Karpathy
2a70301b10
small tweak readme
2026-03-06 22:02:44 +00:00
Andrej Karpathy
b11d6f283f
initial commit
2026-03-06 21:58:52 +00:00
