AutoThink
Boosts local LLM performance with adaptive reasoning. I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity.
Reactions (1)
Similar products
by description similarity
ThinkGPT
github.coma library to prompt GPT to think, memorize and self-refine
Speeding up LLM inference 2x times (possibly)
asciinema.orgHere's a project I've been working on for the last few months.
KillSwitch
killswitch-lang.orga programming language designed to be difficult for LLMs
Crespo
github.comTree-sitter AST blueprints instead of raw code for LLMs
Undermind
undermind.aiDeep scientific paper search with adaptive LLMs