Mathias Lechner
@mlech26l
Cofounder/CTO at Liquid AI and Research Affiliate MIT
Joined December 2017
226 Following 2.3K Followers
TLDR: Effective loops needs access to real environments
Can coding agents autonomously solve a production-grade problem from scratch? Last year, we tasked two agents to build a BPE tokenizer trainer with time limits. Both zero-shot a working toy trainer in 30 minutes. Neither scaled to production.
We then changed the setup with loops. Loops allowed us to iterate against real production data at scale. The correctness was verified with two independent libraries whose results the agent could not manipulate.
The result of this experiment is a tokenizer trainer called toktoktok.
Read more:
Source:
Show more
