74 commits

Author	SHA1	Message	Date
sam-paech	840c6b0ad9	add experiment runner	2025-06-22 18:05:07 +10:00
sam-paech	7d50b31e34	add resuming support + critical state analysis mode	2025-06-22 14:41:29 +10:00
Tyler Marques	b652c032c4	Merge branch 'main' into simplify-prompts	2025-06-19 15:10:59 -07:00
sam-paech	a4855caaae	add new args to main script: max_tokens & max_tokens_per_model	2025-06-20 05:58:47 +10:00
AlxAI	f29cf242e1	together AI client	2025-06-19 15:14:30 -04:00
sam-paech	75fa2be5dc	increase max_tokens to accommodate reasoning tokens	2025-06-19 15:47:39 +10:00
sam-paech	b405cf30c7	revamp diary consolidation; simplify negotiations prompt	2025-06-19 15:39:20 +10:00
sam-paech	f939dd9634	add temperature support, default temp=0, add random seed string to system prompt	2025-06-19 10:12:38 +10:00
AlxAI	77e7921b9c	Support for o3-pro with openai responses api	2025-06-14 17:28:01 -04:00
AlxAI	fbd92d91ba	added rule context	2025-06-09 11:26:12 -04:00
AlxAI	cf556c119d	analyze any game results appended with FULL_GAME	2025-06-03 13:54:18 -04:00
AlxAI	fa17592e75	Update utils.py	2025-06-02 13:58:07 -04:00
AlxAI	fa8a6dcb60	Update clients.py	2025-05-29 18:45:20 -04:00
AlxAI	b1e5cd7a89	Update utils.py	2025-05-29 10:29:39 -04:00
AlxAI	7e35e005db	more parsing	2025-05-26 13:50:57 -04:00
AlxAI	21d852308e	more flexible	2025-05-25 17:41:00 -04:00
AlxAI	a2781c3568	lie detection improved!	2025-05-25 12:02:54 -04:00
AlxAI	4b92dd5af0	updating analysis with lie detection (it's not great yet)	2025-05-24 20:44:23 -04:00
AlxAI	0c84ac990b	updated readmes	2025-05-22 11:02:38 -07:00
AlxAI	742e260464	fixing eliminated powers	2025-05-21 21:27:49 -07:00
AlxAI	81e3dcfe3f	analyze game moments with number of failures per model	2025-05-21 19:38:07 -07:00
AlxAI	94a69be25a	full diaries	2025-05-20 22:12:18 -07:00
AlxAI	9322ada62b	analyze moments, run big models well	2025-05-20 20:04:19 -07:00
AlxAI	f36d5672ea	consolidation of diary!	2025-05-18 19:51:34 -04:00
AlxAI	db827de273	first diary	2025-05-18 17:23:47 -04:00
AlxAI	c50ac85758	analyze game moments attempt 1	2025-05-17 22:28:22 -04:00
AlxAI	f22ef6c627	context on ignored messaged	2025-05-17 20:17:03 -04:00
AlxAI	7fe6544667	fixed prompts, improved negotiations, and diaries	2025-05-17 20:00:14 -04:00
AlxAI	4b32940bf6	fixing prompts	2025-05-15 11:22:24 -04:00
AlxAI	bfcb9ce401	XML didn't work	2025-05-14 22:03:13 -04:00
AlxAI	02bde92188	Improving prompts with XML	2025-05-13 21:46:40 -04:00
AlxAI	a6a77d17b7	Update planning_instructions.txt	2025-05-12 23:05:51 -04:00
AlxAI	ff1f410f74	a little more agro prompts	2025-05-12 16:20:25 -04:00
AlxAI	a7d7703d7f	always send messages	2025-05-12 14:26:14 -04:00
AlxAI	3a935c0491	fixed diary	2025-05-12 10:37:34 -04:00
AlxAI	94313c16d9	fix relationships	2025-05-11 22:19:20 -04:00
AlxAI	0bd6428729	BIG UPDATES logging everything, better structure of moves, everything runs fast af	2025-05-11 19:10:18 -04:00
sam-paech	0c7b0157b5	add private diary summaries	2025-05-11 18:38:37 +10:00
AlxAI	432c783aaa	updates to context	2025-05-10 22:57:11 -04:00
AlxAI	4cdcd64a9e	Support more openrouter models	2025-05-05 17:38:59 -04:00
AlxAI	53e6a8fd6a	saving logs	2025-05-05 10:46:34 -04:00
AlxAI	1dc25702b6	relationships work! Everything is ready for big runs	2025-05-04 11:21:51 -04:00
AlxAI	e6ba8bfbf1	summaries working not statistical summary though	2025-04-30 23:16:57 -04:00
AlxAI	02118dc98b	async!!	2025-04-29 22:28:53 -04:00
AlxAI	0db62f378c	update state	2025-04-29 21:27:22 -04:00
AlxAI	eeddac0ef9	its working!	2025-04-29 20:51:46 -04:00
AlxAI	47f55423da	cleaning up a little	2025-04-28 21:09:48 -04:00
AlxAI	65f287df84	iterating	2025-04-13 12:12:11 -07:00
AlxAI	6e5079fa02	working with agent, relationships, and goals (seemingly)	2025-04-09 22:24:10 -07:00
AlxAI	70f4438b2e	state!	2025-04-07 17:25:12 -07:00