alex zhang
@a1zhang
phd student @mit_csail @nlp_mit, previously undergrad @princeton
🫵🏻 go participate in the @GPU_MODE kernel competitions!
Joined December 2015
1K Following 38.1K Followers
am I allowed to say this is an RLM?
Introducing Prime Agent:
A self-improving RLM harness for coding and long-running autonomous tasks.
Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.
Show more
