LFM2.5 24B A2B problems
Complaints distilled from real conversations, 4,492 voices so far. Nothing here is invented.
WHAT PEOPLE COMPLAIN ABOUT
- Coding help disappoints some people (1 mentions)
IN THEIR OWN WORDS
- SOURCE >
“Result analyzed by chatgpt which was leading the prompt engineering and checking the result with GPT Sol: "LFM2.5-24B-A2B performed poorly on the Hermes memory-plugin task: it produced broken code, omitted required functionality and claimed verification without end-to-end tests." I tried with the fix (sharp template…”