releasing web3-sec-bench, a suite of 30 foundational rl envs for web3 cyber security, compatible with @LaudeInstitute's harbor and submitted to the @PrimeIntellect env hub
based on my own ctfs and DVD (ty @theredguild)
37% win rate for haiku 4.5 cc atm
https://t.co/rLPFGwmgzC
releasing web3-sec-bench, a suite of 30 foundational rl envs for web3 cyber security, compatible with @LaudeInstitute's harbor and submitted to the @PrimeIntellect env hub
based on my own ctfs and DVD (ty @theredguild)
37% win rate for haiku 4.5 cc atm
https://t.co/rLPFGwmgzC
had a friend at a tech company tell me llms are making ppl hella lazy - a bunch of internal search / recommender solutions being pumped out as basic ootb text rag + llm reranking + llm as a judge testing w synthetic data
era of workslop is upon us
Even if LLMs don't lead to AGI, LLMs will lead to amazing technological breakthroughs, especially since we started to train them more and more with RL "learning by doing".