Hacker Newsnew | past | comments | ask | show | jobs | submit | nateb2022's commentslogin

And I would add that the main criticism:

> LLMs and LLM providers are massive black boxes... No trust that they won't nerf the tool/model behind the feature... No trust they won't sunset the feature (the graveyard of LLM-features is vast and growing quickly while they throw stuff at the wall to see what sticks)

Doesn't really apply to the article regarding Claude Code Routines in particular. Should this feature disappear, it should be trivially easy to setup a similar pipeline locally, using a cronjob to run opencode configured to use a local LLM. Easy. I have no qualms using a convenient feature I could reimplement myself, it saves me time.


LM Studio shipped this update. Under settings make sure you update your runtimes.


Thank you both!!


I'd recommend using the instruction tuned variants, the pelicans would probably look a lot better.


> Very impressed by unsloth's team releasing the GGUF so quickly, if that's like the qwen 3.5, I'll wait a few more days in case they make a major update.

Same here. I can't wait until mlx-community releases MLX optimized versions of these models as well, but happily running the GGUFs in the meantime!

Edit: And looks like some of them are up!


absolute n00b here is very confused about the many variations; it looks like the Mac optimized MX versions aren’t available in Ollama yet (I mostly use claude code with this)



Wherever practical, I also recommend using devcontainers, so that in addition to breaking supply chain security, large-scale damage would require an unpatched sandbox exploit too.


I'll plug Pyreqwest here: https://github.com/MarkusSintonen/pyreqwest

It's been a pleasure to use, has a httpx compatibility layer for gradually migrating to its API, and it's a lot more performant (right now, I think it's the most performant Python http client out there: https://github.com/MarkusSintonen/pyreqwest/blob/main/docs/b...)


[dupe] https://news.ycombinator.com/item?id=47506251 (18 minutes older, 6 comments)


This is my condensed version for the SBCwiki documentation focused on the key facts without all the unnecessary marketing around it


This is substantially more useful than the marketing fluff in the press release. Probably would have made sense to post this in that thread though


I added a cost/performance analysis for that at https://news.ycombinator.com/item?id=47509236 in case anyone's interested.



See also: https://github.com/finbarr/yolobox "Let your AI go full send. Your home directory stays home."


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

Search: