b19c07e0dd
fix: remove ineffective mutation validation
2026-04-02 13:44:03 +08:00
31287f1449
feat: add bounded mutation validation
2026-04-02 12:32:32 +08:00
f7ef3d49b3
fix: defer diff summary and handle parse failures
2026-04-02 12:28:42 +08:00
a96c66eeb2
fix: harden task cli result handling
2026-04-02 12:25:55 +08:00
dfd668e5d2
feat: add artifact loop cli and sample skill task
2026-04-02 12:13:17 +08:00
5a51d25791
fix: normalize runner timeouts
2026-04-02 12:06:54 +08:00
39a66a4b3f
fix: align execution pipeline behavior
2026-04-02 12:00:18 +08:00
97ae78f121
feat: add execution, scoring, and decision modules
2026-04-02 11:55:55 +08:00
3172ce264b
fix: preserve artifact line endings and restore deletions
2026-04-02 11:52:10 +08:00
f261f0bf8f
feat: add artifact snapshot and restore support
2026-04-02 11:43:46 +08:00
db3ae7cff1
fix: normalize task loader validation
2026-04-02 11:40:36 +08:00
c3acdb96f7
fix: narrow task loader api
2026-04-02 11:33:31 +08:00
79f1e88ba0
feat: add yaml task loader
2026-04-02 11:29:19 +08:00
61b635a3e8
fix: align engine models with task spec
2026-04-02 11:18:37 +08:00
0c0c0d980f
fix: align engine task bootstrap scaffold
2026-04-02 11:16:18 +08:00
726e512603
feat: bootstrap artifact loop engine package
2026-04-02 11:10:28 +08:00
2968ec63a9
docs: add artifact loop engine design spec
2026-04-02 10:59:11 +08:00
Andrej
228791fb49
Merge pull request #342 from kaizen-38/feat/bug-fix
...
fix(analysis): define best_bpb before y-axis scaling
2026-03-25 17:07:37 -07:00
Andrej
e6d79c1234
Enhance README with more project context and links
...
Added additional context and references to the README.
2026-03-20 19:13:39 -07:00
kaizen-38
f32ab047a2
fix(analysis): define best_bpb before y-axis scaling
2026-03-19 09:43:33 -07:00
Andrej
32a1460f62
Merge pull request #301 from indianspeedster/master
...
add AMD ROCm fork to notable forks section
2026-03-16 11:43:26 -07:00
indianspeedster
513fe6fcee
add AMD ROCm fork to notable forks section
2026-03-16 11:28:48 -07:00
Andrej
c2450add72
Guard against infinite loop when no training shards exist, fix README typo
2026-03-10 22:32:17 -07:00
Andrej
0be1e4fdf9
fix NaN loss not caught by fast-fail check
2026-03-10 22:31:43 -07:00
Contributor
ebf357841b
fix(train): make NaN fast-fail check explicit
2026-03-11 04:28:08 +00:00
Hugh Brown
09ebea439d
Guard against infinite loop when no training shards exist, fix README typo
...
Add assertion after filtering val_path from parquet_paths for the "train"
split so an empty list fails fast instead of spinning in a silent infinite
loop. Also remove stray article "a" in README ("a three files" → "three
files").
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-10 21:34:40 -06:00
Andrej
c12eef778e
Include beginner's guide to neural networks
...
Added a resource link for beginners in neural networks.
2026-03-09 16:00:55 -07:00
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
