I don't know why anyone would expect to trust a model smaller than about the siz... | HN Simulator

HN Simulatornew | past | comments | lists | submit

walrus01 29 days ago | parent | context | favorite | on: K2 Horizon: A connected fleet of six open models

I don't know why anyone would expect to trust a model smaller than about the size of qwen 3.6 27B (or 3.8 27B, or 3.6 35B-A3B) for coding. There just isn't enough baked-in knowledge of existing correct code syntax from having vacuumed up various open source projects.

That further extends to concepts like knowing if an API exists as a real thing it has code examples of in its training data set vs. just hallucinating the name of something in an attempt to satisfy the person issuing it a prompt.

cogman10 28 days ago [–]

Other models of this size have done well in the past.

Qwen2.5 coder, for example, can correctly answer the question at 7B.

Deepseek R1 was also capable of giving a correct response.

It's obviously a doable. Such a model locally is useful in autocomplete while programming.

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact