fzxu22
Re:Ask HN: What's your current AI agentic setup?
on Thursday November 05, 2026 @06:15PM (#50385925)
1. For heavier works im using deepseek v4.1 flash and pro, I also have z.ai coding subscription but probably trying to move away from all of these because:
2. I just got a M5 Max 128G mac studio and self-hosting models now. I did some benchmarks on some potential setups, but currently I’m settling with the Qwen series models (3.8 27B/Flash Next for better intelligence, 3.5 35B A3B for spead), serving with MTPLX. Compared to API providers they are slower and has less context length, but enough for most of my use cases. I am exploring routing solutions between self-hosted and API providers.
3. Mostly Pi (oh-my-pi for main coding env, bare bone pi for drop in usages). Its small footprint is really important for self hosted models
4. I don’t think so, I do have a nanoclaw setup a while ago and am trying to port it to use pi as driver and connect to self hosted models.
5. No, they’re never to be trusted.
Re:Talorys – A self-hosted personal AI agent on Cloudflare's free tier
on Sunday October 11, 2026 @04:15AM (#50040759)
Please don't use the word "self-hosted" if it's not hosted on your hardware. This thing depends entirely on cloudflares services and "generosity".
Re:Auto mode is now the default in Claude Code
on Monday August 10, 2026 @05:28PM (#49249999)
Want to use this thread to ask the wise folks on HN: I’ve been running auto mode but always run within a docker container with only the necessary workspace dir mounted in. Is that considered safe or actually not?
Re:Don't use your phone while you poop
on Sunday August 09, 2026 @12:40AM (#49228497)
I poop for like 30 seconds so not very useful
Re:Anthropic's Model Naming, Extrapolated
on Thursday June 11, 2026 @12:30AM (#48486226)
Can't wait to use Claude Cinematic Universe!
Re:Codex just found a "workaround" of not having sudo on my PC
on Monday June 01, 2026 @04:06AM (#48353906)
That’s why I only run coding agents in containers with limited access to host resources.
Re:OpenAI model for masking personally identifiable information (PII) ...
on Sunday April 26, 2026 @04:48PM (#47914260)
Thanks for the comment! And yes, redaction based measures will always face the trade-off between privacy vs intellegence you get out of LLM. e.g. provider will inevitably know you're in some sorts of legal/tax issue even without any PII. And for some case the intellegence you want will depend on LLM knowing some detail (e.g. your AGI when doing tax preparation).
On the other hand Moxie's Confer is really interesting! On first glance I thought it's using homomorphic encryption but it turns out to be based on hardware isolation. TIL +1
Re:OpenAI model for masking personally identifiable information (PII) ...
on Sunday April 26, 2026 @04:29PM (#47914012)
The proxy keeps 2-way mapping of identified PII and the redaction e.g. Jane Doe <-> <PERSON_1> so the process is reversable i.e. redactions from LLM response will be replaced back to the original, and it should feel transparent on user end. I'll add more detailed example in README to make it clear.
Re:OpenAI model for masking personally identifiable information (PII) ...
on Sunday April 26, 2026 @02:15AM (#47907836)
Working on this: https://github.com/KevinXuxuxu/anon_proxy, a sort of anonymization proxy to use with LLM providers. It does model (OpenAI privacy filter) + regex PII detection, and replaces them back-and-forth for API requests and responses. With locally hosted detection model, no PII leaves your local environment. I find it very useful especially when you're working on sensitive documents (legal, tax, immigration etc.), hope you find it helpful as well :)
Re:Ask HN: Could you share your personal website here?
on Thursday January 15, 2026 @04:46AM (#46630312)
https://site.fzxu.me
The index is a bit outdated, it’s mostly about me working on my homelab.
Re:RSS Is Awesome
on Friday August 29, 2025 @12:44AM (#45060296)
+1 happy freshrss user here
Re:Launch HN: Airhart Aeronautics (YC S22) – A modern personal airplane
on Monday August 05, 2024 @06:55PM (#41166362)
Getting cheaper and better planes is good. But this is not a correct way of solving traffic problems in US.
We need high-speed railroad network, not one airplane per household.
Re:Show HN: Simple Wordle solver in command line in Python
on Saturday January 22, 2022 @08:46PM (#30042845)
LOL that's actually very useful as I'm trying to find out how the thing works
Re:Show HN: Simple Wordle solver in command line in Python
on Saturday January 22, 2022 @05:14PM (#30041343)
Probably true according to this post: https://slc.is/#Best%20Wordle%20Strategy%20%E2%80%94%20Explo...
Re:Show HN: Simple Wordle solver in command line in Python
on Saturday January 22, 2022 @04:55PM (#30041195)
You ... are not wrong ;)
Re:Show HN: Simple Wordle solver in command line in Python
on Saturday January 22, 2022 @04:53PM (#30041183)
Thanks for the reply! I really appreciate your feedback on this.
I wasn't giving much thought about coding style and naming etc. when I worked on this, just wanted to get it running asap. I'll definitely take a better look at your suggestion (I'm not very familiar with perl) and see if I find any time to improve this thing. cheers.
Re:Show HN: Simple Wordle solver in command line in Python
on Saturday January 22, 2022 @03:55PM (#30040727)
see README