@sandeepg33k : We just crossed 150K test executions at @bug0inc in the last 3 months. My biggest learning in getting LLMs to do what you want: - LLMs are non-deterministic tools. Do not over-optimize trying to make them deterministic. - use tool calling to do tasks deterministically.

Sandeep

@sandeepg33k

+ Follow

co-founder @hashnode. Still writing your docs and blogs with stone-age tools? 🛠️ Upgrade to Hashnode and unify your API docs and blog like it’s 3024!

ID: 92261165

linkhttps://hashnode.com calendar_today24-11-2009 12:30:21

6,6K Tweet

6,6K Followers

456 Following

Sandeep

@sandeepg33k

2 months ago

We just crossed 10K test executions at Bug0 in the last 3 months. My biggest learning in getting LLMs to do what you want: - LLMs are non-deterministic tools. Do not over-optimize trying to make them deterministic. - use tool calling to do tasks deterministically. - use

thumb_up_off_alt7

chat_bubble_outline2

repeat3

shareShare