Hacker News: ddxv

New comment by ddxv in "Cursor 3"

ddxv — Fri, 03 Apr 2026 06:46:54 +0000

I was loving Cursor for the agents and autocomplete which was amazing. When they started talking about the autocomplete being no longer a focus and looking towards these token blackholes I switched back to VSCode. At $10 a month it's even cheaper.

New comment by ddxv in "We intercepted the White House app's network traffic"

ddxv — Wed, 01 Apr 2026 03:01:15 +0000

Browse the SDKs it's using as well:

https://appgoblin.info/apps/gov.whitehouse.app/sdks

New comment by ddxv in "I traced my traffic through a home Tailscale exit node"

ddxv — Wed, 01 Apr 2026 02:52:42 +0000

How do you handle home network IP changes?

New comment by ddxv in "Iran Conflict Daily Dashboard"

ddxv — Mon, 30 Mar 2026 17:35:56 +0000

That had a lot more than I expected and some pretty detailed datasets.

New comment by ddxv in "Astral to Join OpenAI"

ddxv — Fri, 20 Mar 2026 02:24:26 +0000

Yes, I think we are mostly in agreement. I tried `uv` several times and never wanted to add it as a dependency because I wasn't convinced by the QOL. That being said, the biggest concern I always had was just that it was adding another layer of complexity and similar to Conda or pyenv it just wasn't something I was going to like.

I probably did come off a bit 'told you so' but I guess it was more that it felt like this was finally an answer to a question/curiosity I've had about `uv` where I didn't understand the dissonance between how others felt about it and how I did.

New comment by ddxv in "Google details new 24-hour process to sideload unverified Android apps"

ddxv — Fri, 20 Mar 2026 02:07:26 +0000

I've been slowly degoogling because of how Google is treating Android. It's slow, but I've been setting up emails on other providers, stopped using Google search, stopped uploading photos etc.

New comment by ddxv in "Astral to Join OpenAI"

ddxv — Thu, 19 Mar 2026 14:10:36 +0000

This is why I still like to setup projects and environments with my own `make` `venv` and `pip`.

New comment by ddxv in "Comparing Python Type Checkers: Typing Spec Conformance"

ddxv — Mon, 16 Mar 2026 15:31:20 +0000

I've used mypy forever and never even tried these others. Looking at them though it looks like it's worth trying out Zuban or Pyright? Is there a noticeable benefit when switching between different checkers?

New comment by ddxv in "Levels of Agentic Engineering"

ddxv — Fri, 13 Mar 2026 03:51:37 +0000

Yes, I think what I left off my sentence was that I trust AI on frontend more than myself. Backend and data processing where I know more, I can't handle it's constant hallucinations. I also feel like hallucinations in data pipelines are way more problematic for me. They take a long time to "fix" and can be quite easy to miss, imagine a mean of a mean or something that is 'mostly' right (thus harder to catch) but factually incorrect.

New comment by ddxv in "Levels of Agentic Engineering"

ddxv — Wed, 11 Mar 2026 12:37:50 +0000

I still do this too for tough projects in languages I know. Too many times getting burned thinking 'wow it one shot that!' only to end up debugging later.

I let agents run wild on frontend JS because I don't know it well and trust them (and an output I can look at).

New comment by ddxv in "FrameBook"

ddxv — Mon, 09 Mar 2026 05:06:41 +0000

Interesting because I always felt like the Framework already looks like a Macbook Pro with the grey case and the black keys.

New comment by ddxv in "Most of the US economy is in a recession"

ddxv — Mon, 09 Mar 2026 01:27:49 +0000

I upvoted the parent, read your comment, unvoted and upvoted yours. I think what you're saying describes how I feel exactly.

New comment by ddxv in "Ask HN: Do You Have a Homelab?"

ddxv — Fri, 06 Mar 2026 15:32:55 +0000

Yes, it was probably one of my better decisions and investments in the past years. I run a ton of things I never would have paid to run in the cloud and feel in control. I've even started making money from one of the projects.

Tons of small things feel nice, taking notes and I don't have to use Google Docs if I don't want. Watching a movie from my home media center etc

New comment by ddxv in "Ask HN: What Online LLM / Chat do you use?"

ddxv — Tue, 03 Mar 2026 04:12:10 +0000

I recently deleted my ChatGPT and was just looking around for what the other options are. I kinda like fast, but Grok / Perplexity are behind a perpetual CloudFlare check for me. I'm looking for something that doesn't spend forever reasoning out the answer to some basic quick question.

It's interesting, as I type that out it makes me wonder why not just go back to the search engine since it has the AI summaries that have been getting better.

Finally, I do also like the longer reasoning when I have a tough question and usually like to copy paste it around to various models and compare their responses.

New comment by ddxv in "Ask HN: What Online LLM / Chat do you use?"

ddxv — Tue, 03 Mar 2026 04:08:29 +0000

Smaller niche models are ones you're running yourself locally?

Ask HN: What Online LLM / Chat do you use?

ddxv — Tue, 03 Mar 2026 02:13:14 +0000

I have been wanting to try more LLMs than the standard Anthropic/Grok/ChatGPT/Qwen

Are there other LLM chat sites you use or recommend?

Comments URL: https://news.ycombinator.com/item?id=47227046

Points: 12

# Comments: 17

New comment by ddxv in "Ask HN: Who wants to be hired? (March 2026)"

ddxv — Mon, 02 Mar 2026 22:09:50 +0000

Location: SF, Taipei Remote: Ok Willing to relocate: Maybe Technologies: Advertising, mobile ads, game marketing Résumé/CV: jamesoclaire.com

Looking for anyone working on new mobile ads related companies or programmatic advertising. I'm passionate about advertising and looking for companies that share those values.

New comment by ddxv in "[dead]"

ddxv — Mon, 02 Mar 2026 11:08:25 +0000

Original title: Google AI Introduces STATIC: A Sparse Matrix Framework Delivering 948x Faster Constrained Decoding for LLM Based Generative Retrieval

Shortened to fit hn

New comment by ddxv in "How do I cancel my ChatGPT subscription?"

ddxv — Sat, 28 Feb 2026 07:51:41 +0000

I really hope at some point in the near future AI models shrink enough or laptops get strong enough to run AI models locally. I haven't tried in the past year, but when I did it was very slow token output + laptop was on fire to make that happen.

I've wanted to try some of the more recent 8B models for local tab completion or agentic, any experience with those kinds of smaller models?

New comment by ddxv in "How do I cancel my ChatGPT subscription?"

ddxv — Sat, 28 Feb 2026 07:20:47 +0000

The delete screen says they delete your data except where necessary by law for them to keep. Would love to know what percentage actually is deleted.