←back to thread

684 points prettyblocks | 5 comments | | HN request time: 1.317s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
1. mritchie712 ◴[] No.42785570[source]
I used local LLMs via Ollama for generating H1's / marketing copy.

1. Create several different personas

2. Generate a ton of variation using a high temperature

3. Compare the variagtions head-to-head using the LLM to get a win / loss ratio

The best ones can be quite good.

0 - https://www.definite.app/blog/overkillm

replies(2): >>42788292 #>>42790343 #
2. UltraSane ◴[] No.42788292[source]
clever name!
3. Mashimo ◴[] No.42790343[source]
What is an H1?
replies(2): >>42791163 #>>42791221 #
4. TachyonicBytes ◴[] No.42791163[source]
Not the OP, but they are "Headers". Probably coming from the <h1> tag in html. What outsiders probably call "Headlines".
5. laristine ◴[] No.42791221[source]
Main heading of an article