Hacker News new | ask | show | jobs
by setnone 782 days ago
> code snippets, basic research, summarization and image generation

This matches my use cases, I use OpenAI via API Key (mostly GPT-4 and whisper-1) and Llama 3 via Ollama which is decent for text tasks and free.

> What does your workflow look like?

> but more often than not I find myself either double checking sources or tweaking the end results

To ease up tweaking the results and scratch my own itch i'm building grafychat[1].

[1] https://news.ycombinator.com/item?id=40189119