Hacker News: andhuman

New comment by andhuman in "The End of Programming"

andhuman — Wed, 26 Aug 2026 10:22:15 +0000

Also, handing over the work to AI robs you of learning and understanding. Let’s say you write a ticket for a feature and that description is good enough that an AI agent can implement it from start to finish. The AI will then discover things while implementing the feature, and will use those learning to make the feature work. That learning will then be discarded once the AI is done. No one will be able to partake or share the knowledge with others. Sure, some of it can be saved in form of comments, but not everything.

New comment by andhuman in "Improving GPT‑5.6 Sol in ChatGPT, expanding GPT‑5.6 Luna access for free users"

andhuman — Fri, 07 Aug 2026 06:44:13 +0000

I don’t see why they just don’t allow a smaller model to answer the question while letting the bigger one vet it. The vetting can be asynchronous and can be delivered after a few seconds (if it’s an easy query). If it’s a hard query, the UI can show the answer is currently being vetted or something.

New comment by andhuman in "Less Coffee, Better Sleep"

andhuman — Mon, 03 Aug 2026 10:57:50 +0000

What surprised me is that caffeine gets converted to other compounds that _also_ binds to the same receptors thus causing you to feel less tired. And that compound has its own half life. Now I’m just guessing, but it could be that one is more affected by one of the byproducts so to speak than the caffeine itself.

New comment by andhuman in "An Ordinary Mind on an Ordinary Day"

andhuman — Mon, 06 Jul 2026 05:47:19 +0000

Why conscious thought as described in the article was thought to be signs of a delirious person was because that’s where you could find it in real life, is my guess. If someone blabbing about without a listener, they’re insane. So to describe someone’s inner thought would render them insane to the reader. But with psychology came greater understanding and value of the inner thoughts and now a character no longer was deemed insane by having innate thoughts.

New comment by andhuman in "Kimi K2.7 Code is generally available in GitHub Copilot"

andhuman — Thu, 02 Jul 2026 05:58:04 +0000

Finally an alternative to the big dogs that a company can use. People have been asking for a way to run the Chinese models from a trusted provider. Here GitHub delivered!

The performance, if we trust the benchmarks, put it at Sonnet 4.6.

Let’s see if it’s worth it with GitHubs pricing.

New comment by andhuman in "Mistral Medium 3.5"

andhuman — Wed, 29 Apr 2026 18:07:24 +0000

The Vibe CLI is really bad on Windows, sure they don’t officially support it, so can’t blame them, but a FYI for anyone wanting to try it. It can’t get find and replace right.

New comment by andhuman in "Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code"

andhuman — Mon, 06 Apr 2026 06:57:50 +0000

I have good experience with Mistral Vibe.

New comment by andhuman in "Music for Programming"

andhuman — Mon, 06 Apr 2026 06:52:13 +0000

I just listened to the Matrix OST and that one really gets me into a coding mood!

New comment by andhuman in "Vivaldi 7.8 Is Here"

andhuman — Thu, 19 Mar 2026 17:21:28 +0000

Oh man, this was the release I wanted to link, as it has a new feature (tiled follow link) that I actually started using right away. A new browser feature I find useful didn’t happen that often for me, so I got excited.

Vivaldi 7.8 Is Here

andhuman — Thu, 19 Mar 2026 16:25:06 +0000

Article URL: https://vivaldi.com/blog/vivaldi-on-desktop-7-8/

Comments URL: https://news.ycombinator.com/item?id=47441961

Points: 3

# Comments: 2

New comment by andhuman in "Ask HN: How to be alone?"

andhuman — Mon, 09 Mar 2026 14:55:47 +0000

Be kind to others, but start with being kind to yourself.

New comment by andhuman in "How to run Qwen 3.5 locally"

andhuman — Sun, 08 Mar 2026 12:55:30 +0000

Isn’t llama.cpp’s implementation of Qwen 3.5 better, or am I misinformed?

Qwen 3.5 small models out

andhuman — Tue, 24 Feb 2026 18:55:22 +0000

Article URL: https://huggingface.co/Qwen/Qwen3.5-35B-A3B

Comments URL: https://news.ycombinator.com/item?id=47141052

Points: 18

# Comments: 3

New comment by andhuman in "What Is OAuth?"

andhuman — Sat, 21 Feb 2026 08:28:34 +0000

What helped me get a better understanding of oauth and oidc, was this YouTube video [0].

[0]: https://youtu.be/996OiexHze0

New comment by andhuman in "Audio is the one area small labs are winning"

andhuman — Mon, 16 Feb 2026 16:42:34 +0000

Same setup I’m using! Parakeet and pocket turbo. It’s feels good enough for daily usage.

New comment by andhuman in "Windows Notepad App Remote Code Execution Vulnerability"

andhuman — Wed, 11 Feb 2026 11:37:44 +0000

Have you tired using the run action instead to clean the data? Win+r

New comment by andhuman in "How to effectively write quality code with AI"

andhuman — Sat, 07 Feb 2026 09:00:52 +0000

I have this nagging feeling I’m more and more skimming text, not just what the LLMs output, but all type of texts. I’m afraid people will get too lazy to read, when the LLM is almost always right. Maybe it’s a silly thought. I hope!

New comment by andhuman in "Backseat Software"

andhuman — Fri, 30 Jan 2026 13:28:37 +0000

One of the more annoying software that does this is the copilot Office 365 on the web. Every time (!) I open it, it shows a popup on how to add files to the context. That itself would be annoying, but it also steals focus! So you would be typing something and suddenly you’re not typing anymore for M$ decided it’s time for a popup. I finally learned to just wait for the pop up and then dismiss it with esc. Ugh!

New comment by andhuman in "Ask HN: What's the current best local/open speech-to-speech setup?"

andhuman — Sat, 24 Jan 2026 07:52:20 +0000

I built this recently. I used nvidia parakeet as STT, open wake word as the wake word detection, mistral ministral 14b as LLM and pocket tts for tts. Fits snugly in my 16 gb VRAM. Pocket is small and fast and has good enough voice cloning. I first used the chatterbox turbo model, which perform better and even supported some simple paralinguistic word like (chuckle) that made it more fun, but it was just a bit too big for my rig.

New comment by andhuman in "Qwen3-TTS family is now open sourced: Voice design, clone, and generation"

andhuman — Thu, 22 Jan 2026 19:19:49 +0000

It’s uncanny good. I prefer it to pocket, but then again pocket is much smaller and for realtime streaming.