@simon you don't allow Web Components? | Evan Prodromou

Simon's posts Post Back to profile

@simon you don't allow Web Components?

Like 19 December at 14:08 | Wall-to-wall | Open on cosocial.ca

7 comments

@evan love Web Components - I often prompt it to create those directly, but I still want them all in a single file so I can easily copy and paste the whole lot out of the LLM at once

19 December at 14:45 | Open on fedi.simonwillison.net

@simon So, you don’t use an IDE with integrated AI, like VSCode with CoPilot or Cursor or Zed or whatever?

19 December at 15:53 | Open on cosocial.ca

@evan I use GitHub copilot but I get a ton of work done directly in Claude (with Artifacts) and ChatGPT (with Code Interpeter) pasting code back and forth

19 December at 16:07 | Open on fedi.simonwillison.net

@simon last question! Do you ever use a local Open Suorce model for code generation, and if so, which one?

19 December at 16:30 | Open on cosocial.ca

@evan only on planes! Best I've tried are Qwen2.5-Coder-32B and Llama 3.3 70B

https://simonwillison.net/2024/Nov/12/qwen25-coder/

https://simonwillison.net/2024/Dec/9/llama-33-70b/

19 December at 16:36 | Open on fedi.simonwillison.net

@evan both of them use so much memory that I have to shut down a bunch of Firefox tabs and VS code windows first - plus they're noticeably slower than the best hosted models

19 December at 16:36 | Open on fedi.simonwillison.net

@simon @evan I also only use local models on flights really. However, I will say I've found the smaller Qwen2.5-coder models on Ollama to be good enough, and importantly fast enough for most simple boiler plate work without taking up all my ram to run them.

20 December at 6:26 | Open on mastodon.social