Hacker News: dwringer

New comment by dwringer in "LinkedIn is searching your browser extensions"

dwringer — Thu, 02 Apr 2026 17:32:30 +0000

The other replies have explained what's jumping out but I'd agree that without the other surrounding sentences of the article's introduction I'd be inclined to think that quoted sentence by itself might be human. The full text, however, doubles down on the AI-smelling constructions and IMHO almost certainly indicates some AI provenance.

New comment by dwringer in "If you don't opt out by Apr 24 GitHub will train on your private repos"

dwringer — Fri, 27 Mar 2026 22:01:39 +0000

I believe Poe's law makes it basically inescapable and HN is no exception to it

New comment by dwringer in "My astrophotography in the movie Project Hail Mary"

dwringer — Wed, 25 Mar 2026 13:40:09 +0000

People have been talking about the book on here since it came out; I see no reason to believe people aren't genuinely interested in it. I loved it, personally.

New comment by dwringer in "Epic Games to cut more than 1k jobs as Fortnite usage falls"

dwringer — Tue, 24 Mar 2026 20:36:25 +0000

In my experience, the Epic downloader would frequently lead to degraded performance and/or system instability when I'd leave it running; I've never noticed such problems at all with the Steam client.

New comment by dwringer in "Show HN: Vanilla JavaScript refinery simulator built to explain job to my kids"

dwringer — Wed, 11 Mar 2026 19:56:11 +0000

I accidentally clicked through the explanatory text after the first slide (I was still clicking the pump and didn't realize one more click was going to skip through); I have not been able to get the applet to rewind back to the beginning.

New comment by dwringer in "GPT‑5.3 Instant"

dwringer — Tue, 03 Mar 2026 18:46:10 +0000

The scare quotes around words that don't warrant it, or are unnecessarily idiosyncratic, are something I get pretty often in response text from Gemini.

New comment by dwringer in "Statement from Dario Amodei on our discussions with the Department of War"

dwringer — Fri, 27 Feb 2026 14:02:29 +0000

I'm really surprised that didn't jump out at more people; I had to get halfway through the comments to the 27th mention of "Department of War" to find the first comment pointing out that using the name is itself a capitulation.

New comment by dwringer in "Diode – Build, program, and simulate hardware"

dwringer — Tue, 24 Feb 2026 14:50:14 +0000

For me there seems to be a listing of configurable settings or something but it only pops up for a single frame after I right-click-drag a component - this seems like a broken mouse interaction.

New comment by dwringer in "Gemini 3 Deep Think"

dwringer — Thu, 12 Feb 2026 21:15:20 +0000

I strongly suspect there's a major component of this type of experience being that people develop a way of talking to a particular LLM that's very efficient and works well for them with it, but is in many respects non-transferable to rival models. For instance, in my experience, OpenAI models are remarkably worse than Google models in basically any criterion I could imagine; however, I've spent most of my time using the Google ones and it's only during this time that the differences became apparent and, over time, much more pronounced. I would not be surprised at all to learn that people who chose to primarily use Anthropic or OpenAI models during that time had an exactly analogous experience that convinced them their model was the best.

New comment by dwringer in "AI fatigue is real and nobody talks about it"

dwringer — Sun, 08 Feb 2026 16:48:42 +0000

While this is certainly very true, I find coding through an LLM to require far less effort dedicated to this cognitive switching than does writing in some programming language, primarily because I no longer have to load the mental context for converting my high level human instructions to code that a programming environment actually supports. The mental context seems more lightweight and closer to the way I think about the problem when I'm not sitting at the computer actively working on it. If an idea comes to me while I'm away from the computer I can momentarily sit down, type in whatever I just thought of, and get going almost immediately. I think it also saves a huge amount of cognitive load and stress (for me) involved with switching around between different programs and languages, an unfortunate fact of life when dealing with legacy systems.

New comment by dwringer in "Show HN: Wikipedia as a doomscrollable social media feed"

dwringer — Mon, 02 Feb 2026 16:49:22 +0000

I just kept scrolling, hoping it would learn from how long I paused over content to read it the way FB's seems to, but it seems you're right, in this case "likes" are required.

New comment by dwringer in "Daft Punk Easter Egg in the BPM Tempo of Harder, Better, Faster, Stronger?"

dwringer — Sat, 03 Jan 2026 17:38:37 +0000

It's really a stretch for the article to suggest their gear might not have supported fractional bpm. MIDI itself has always supported it and analog sequencers before that support it even easier. Not to mention external clock sync has been a thing for decades.

New comment by dwringer in "C –> Java != Java –> LLM"

dwringer — Fri, 02 Jan 2026 21:50:17 +0000

All I can really say is that doesn't match my experience. If I fix something that it implemented due to a "misunderstanding" then it usually tends to break it again a few messages later. But I would be the first to say the use of these models is extremely subjective.

New comment by dwringer in "C –> Java != Java –> LLM"

dwringer — Fri, 02 Jan 2026 21:15:28 +0000

For me it just depends. If the response to my prompt shows the model misunderstood something, then I go back and retry the previous prompt again. Otherwise the "wrong ideas" that it comes up with persist in the context and seem to sabotage all future results. The most of this sort of coding I've done was in Google's AI studio, and I often do have a context that spans dozens of messages, but I always rewind if something goes off-track. Basically any time I'm about to make a difficult request, I clone the entire context/app to a new one so I can roll back [cleanly] whenever necessary.

New comment by dwringer in "Rob Pike goes nuclear over GenAI"

dwringer — Fri, 26 Dec 2025 17:05:46 +0000

Fair enough, but I was interpreting it as "hopefully, but not necessarily". Some would say there's no such thing as bad publicity!

New comment by dwringer in "Rob Pike goes nuclear over GenAI"

dwringer — Fri, 26 Dec 2025 15:04:11 +0000

By that metric of getting shared on social media, it was extraordinarily successful

New comment by dwringer in "Egyptian Hieroglyphs: Lesson 1"

dwringer — Thu, 18 Dec 2025 14:02:49 +0000

"Open your mouth and say ah" "tot" "yacht" - these all have very close to the same vowel sound to me as an American, although "tot" is more of an outlier and "taught" might be closer to how I conceptualize of the sound. I'm not sure I'd ever hear the difference in practice.

New comment by dwringer in "Gemini 3 Pro: the frontier of vision AI"

dwringer — Fri, 05 Dec 2025 21:17:45 +0000

I had no trouble getting it to generate an image of a five-legged dog first try, but I really was surprised at how badly it failed in telling me the number of legs when I asked it in a new context, showing it that image. It wrote a long defense of its reasoning and when pressed, made up demonstrably false excuses of why it might be getting the wrong answer while still maintaining the wrong answer.

New comment by dwringer in "Gemini 3"

dwringer — Tue, 18 Nov 2025 17:34:45 +0000

This isn't using the same prompt or stack as the page from that post the other day; on aistudio it builds a web app across a few different files. It's still fairly concise but I don't think it's that much so.

New comment by dwringer in "Gemini 3"

dwringer — Tue, 18 Nov 2025 17:07:57 +0000

Well, I tried a variation of a prompt I was messing with in Flash 2.5 the other day in a thread about AI-coded analog clock faces. Gemini Pro 3 Preview gave me a result far beyond what I saw with Flash 2.5, and got it right in a single shot.[0] I can't say I'm not impressed, even though it's a pretty constrained example.

> Please generate an analog clock widget, synchronized to actual system time, with hands that update in real time and a second hand that ticks at least once per second. Make sure all the hour markings are visible and put some effort into making a modern, stylish clock face. Please pay attention to the correct alignment of the numbers, hour markings, and hands on the face.

[0] https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...