AVB
@neural_avb
Neural Breakdown on YT | Read research with AI: | Latest vid: RLMs, Post Training | Next: Reasoning SLM
342 Following 12.7K Followers
I am building a full fledged RLM harness in rust using fast-rlm
It's coming along nicely. Every context, prompts, file content is a python variable. Every tool runs inside the python repl. It's WIP but super excited about it!
PS: deepseek-v4-flash is pretty good as an rlm
Show more
Deepseek pricing is what I’m looking for in all open (and closed) models. Xiaomi and Minimax have adopted this, and they have insane intelligence vs cost ratios rn.
1$/M out and 0.05$/M cache read
(These metrics are glm-5.1, NOT 5.2)
PS: I love glm5.1, its my default RLM model
Show more
