HN user

karn97

-13 karma
Posts0
Comments50
View on HN
No posts found.

Reasoning is just the worst kind of stop gap measure. The state that should emerge internally is forced through automating prompts. And you can clearly see this because the models rarely follow their own "reasoning". Its just auto self prompting

I use ai myself as stack exchange but this sentiment is extremely common on HN where you have people trying to force ai to do things it's clearly shit for. Not to mention the rust your brain gathers by not doing these little 'mundane' things. LLMS are a useless dead end anyway all these billion dollar corpos building over it, even worse hype than crypto.

They are running out of actual useful stuff to sell huh? LLMs provide 0 business value (any value is offset by uncertainty)

Even the latest models are terrible, absolute garbage at engineering. They can't engineer solutions at all. Even in the simplest of cases.

Tells me a lot about people like you who make these comments rather than llms.

Not helpful when the llm knowledge cutoff is a year out of date and api and lib has been changed since