99 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Noah Shinn	5269ef4ae0	start v2	2023-05-21 15:52:27 +02:00
elleven11	970c487d97	reinit submodules	2023-05-21 15:51:39 +02:00
elleven11	a98e92b20a	reset submodule	2023-05-21 15:49:43 +02:00
Noah Shinn	4e42b24dab	start v2	2023-05-21 15:48:05 +02:00
Noah Shinn	878a144a66	alfworld and webshop	2023-05-21 15:35:36 +02:00
Noah Shinn	3148695707	note about paper	2023-05-21 15:34:23 +02:00
Noah Shinn	a0162a065d	update leetcode hard gym link	2023-05-21 15:33:58 +02:00
Noah Shinn	d2cdf66bc2	leetcode-hard gym repo	2023-05-21 15:33:50 +02:00
Noah Shinn	9a71c64882	leetcode-hard gym repo	2023-05-21 15:33:35 +02:00
Beck LaBash	5b6a1bd990	Merge branch 'py-prompts'	2023-05-18 20:17:47 -04:00
Beck LaBash	1eb65193d9	Lazy imports for leetcode	2023-05-18 19:53:30 -04:00
Noah Shinn	1a8a569211	prompts	2023-05-18 13:40:40 -07:00
Beck LaBash	c272801db6	Log implementations and test case results	2023-04-19 22:12:42 -04:00
Noah Shinn	1dce1f7a90	rs hardest 50 results	2023-04-18 17:45:36 -04:00
Beck LaBash	94e7bf7d46	Prompts	2023-04-16 20:55:36 -04:00
Noah Shinn	d92b66deb1	hardest 50 py results	2023-04-16 20:54:15 -04:00
elleven11	17cf55fa12	humaneval rs hard50	2023-04-16 19:34:38 -04:00
elleven11	56303a3f78	script	2023-04-16 19:28:57 -04:00
Noah Shinn	8a2fad33b1	humaneval py hardest 50 benchmark	2023-04-16 14:03:20 -04:00
elleven11	10ae3e53b2	fix rate	2023-04-15 22:16:27 -04:00
Beck LaBash	818fc53c89	Add back dynamic imports	2023-04-14 22:46:47 -04:00
Beck LaBash	a774fb783f	Merge branch 'main' of https://github.com/GammaTauAI/reflexion-human-eval-private	2023-04-14 22:36:24 -04:00
Beck LaBash	7572abfa8f	Change timeout handling to error propagating thread	2023-04-14 22:22:24 -04:00
Beck LaBash	59e0e30942	Change timeout handling to error propagating thread	2023-04-14 22:21:25 -04:00
Beck LaBash	8ea84f3c49	fixes to leetexec	2023-04-13 21:09:01 -04:00
Beck LaBash	8053a90b23	Fixes	2023-04-13 21:08:28 -04:00
elleven11	6ea2f63fa2	remove	2023-04-11 23:16:12 -04:00
elleven11	2759fbc353	new scripts	2023-04-11 23:07:59 -04:00
elleven11	e07aa1d253	dynamic imports	2023-04-11 22:54:40 -04:00
elleven11	a427869f1a	bold	2023-04-11 22:50:21 -04:00
elleven11	29006464d3	dataeset get	2023-04-11 22:48:16 -04:00
elleven11	30c6c5d2e9	sample of 30	2023-04-11 22:48:08 -04:00
elleven11	148e09a652	immediate reflexion	2023-04-11 22:41:44 -04:00
Beck LaBash	c52741524c	Updated LeetExecutor	2023-04-11 21:00:05 -04:00
Beck LaBash	b579fd61e0	Handle no == in get_call_str	2023-04-11 20:47:41 -04:00
elleven11	e9407a6725	run testacc	2023-04-11 20:15:57 -04:00
elleven11	b0a37fd732	test acc	2023-04-11 20:15:57 -04:00
Noah Shinn	7c6a83c5a2	.	2023-04-06 02:27:39 -04:00
Beck LaBash	b5aec9618f	Leetcode Hard: Python3 Benchmark	2023-04-06 01:39:31 -04:00
Beck LaBash	95a7a9cad6	Merge branch 'leetcode-executor'	2023-04-06 01:34:39 -04:00
Beck LaBash	7d24e64093	Stash	2023-04-06 01:32:04 -04:00
Beck LaBash	55e7b7d386	Python benchmark	2023-04-06 01:29:12 -04:00
elleven11	398a399213	print only if verbose	2023-04-04 23:51:12 -04:00
elleven11	39cf170854	testacc and strategy factory	2023-04-04 23:45:45 -04:00
Beck LaBash	3bc06177d8	LeetExecutor implementation	2023-04-04 21:45:28 -04:00
Beck LaBash	94eea44905	LeetExecutor implementation	2023-04-04 21:36:12 -04:00
elleven11	23f02ea07d	fixed merge	2023-04-04 18:40:22 -04:00
elleven11	04a43534b8	submodule info	2023-04-04 18:40:08 -04:00
elleven11	b1bbee43b6	fix merge conflicts	2023-04-04 16:40:13 -04:00
Noah Shinn	3dbd2f44d1	Merge branch 'main' of https://github.com/GammaTauAI/reflexion-human-eval-private	2023-04-04 16:32:26 -04:00