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

What would you personally recommend for those that have 128 GB?


I have a Ryzen AI Max+ 395 with 128 GB for running those sort of "background task", and my sweet spot is currently Qwen3.8 Flash-Next IQ4 at 96 GB.


if you have 128 GB, you could use Qwen Flash Next at some reasonable quant, with the new SSD hack for only keeping some of the model resident in memory.


Our of curiosity what do you use to run this? An actual cron or a tool like hermes etc


As someone who hasn't used Work or Codex but has used Claude Code and Pi a lot, may you describe how to set this up? I'm interested enough to try this out


You'll need a subscription ($20 tier should be fine) and then need to add "connectors" to your services (Gmail, 365, etc) so that it can access them. Then you just use the Claude Cowork (Or ChatGPT equivalent) tabs and chat with it.


You do not even need a subscription. Even ChatGPT free account has some quota for Codex/Work use.


I wasn't aware of that. I am aware that Google connectors are gated behind the $20 ChatGPT sub.


I just signed into https://chatgpt.com using my burner free account and I don't see a "Work" tab.

Do you know if free tier gets ChatGPT desktop app access to Codex and Work? And if that Work access is local-only or includes Work Cloud?


It might be hidden somewhere or they’re doing A/B testing. Cowork was part of the left sidebar for Claude but when I was looking for it, it was gone. I had to do a search query to find it.


Random but I have no idea how this comment of yours ended up dead. I ended up vouching for it.


I have a m4 max mbp with 128 gb. What model would you folks recommend? I'd ideally like to integrate with a tool that can auto read context like Claude code (via a proxy) or cline. I'm open to any advice


I've tried a few solutions and have landed on just storing them in an unordered list in a markdown file


Any willingness to share this script? I've been working on some code to ingest things and summarize for them and I haven't gotten to email just yet.


Watch this space. It’s pretty scrappy code and needs a cleanup. It also does other random stuff relating to calendar entries that I want to be reminded to appropriately prepare for.

But yes I’ll share, and I guess post an update in this thread?


I’d suggest the simple approach: run that script through Claude and have it extract just the email processing parts to create a clean CLI tool. This seems like exactly the type of refactoring task that LLMs are really good at.


Okay will do. Yeah, I just finished my calendar reading code. I haven't prepared the data for my LLM ingestion yet. Sounds great, I'll refresh this thread in a few days


Wifi calling unfortunately has its quirks even if it could be used


I've never got WiFi calling working despite my network nominally supporting it. I'd love a technical deep dive if you know anyone who has written it?


Warcraft 3 remains my favorite game to this day, simply due to the sheer volume of custom maps you could play.

I can't explain how excited I was for the Reforged version of the game and how disappointed I was when it flopped.

My favorite part of games is learning the mechanics and coming up with strategies. Which paired well with an endless supply of new game modes to try.

I have been unable to find any modern game that is both active and has a series of custom maps. If anyone knows of any, please let me know.


Does StarCraft 1 & 2 count?

Brood war is still active in Korea


I was a big fan of Metaflow a few years back. I thought it was neat how I could write some code and easily run some functions locally versus remote.

Hey Savin, it's been a while since chatted. I hope things are going well ;)

For those unaware, onsone of the co


Anyone know if something similar exists for raycast?


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

Search: