Hacker News: nathanasmith

New comment by nathanasmith in "You can turn Claude's most annoying feature off"

nathanasmith — Fri, 13 Mar 2026 01:09:08 +0000

The verbs are one of my favorite things about Claude Code.

New comment by nathanasmith in "GPT-5.1: A smarter, more conversational ChatGPT"

nathanasmith — Thu, 13 Nov 2025 13:36:06 +0000

The thing that bothers me about "warmer, more conversational" is that it isn't just a cosmetic choice. The same feedback loop that rewards "I hear you, that must be frustrating" also shapes when the model is willing to say "I don’t know" or "you’re wrong". If your reward signal is mostly "did the user feel good and keep talking?", you’re implicitly telling the model that avoiding friction is more valuable than being bluntly correct.

I'd much rather see these pulled apart into two explicit dials: one for social temperature (how much empathy / small talk you want) and one for epistemic temperature (how aggressively it flags uncertainty, cites sources, and pushes back on you). Right now we get a single, engagement-optimized blend, which is great if you want a friendly companion, and pretty bad if you’re trying to use this as a power tool for thinking.

New comment by nathanasmith in "Liquid Glass Is Cracked, and Usability Suffers in iOS 26"

nathanasmith — Sat, 11 Oct 2025 02:06:44 +0000

I had an old Galaxy Tab S7 collecting dust on the shelf. Since iOS 26 came out I find myself reaching for the Android tablet more and more. First time that ever happened. (Sent from my Galaxy Tab)

New comment by nathanasmith in "Claude Code Is My Computer"

nathanasmith — Tue, 03 Jun 2025 16:09:47 +0000

Readers would have been better served with the prompts you wrote than the AI generated output.

New comment by nathanasmith in "Denmark to raise retirement age to 70"

nathanasmith — Sun, 01 Jun 2025 21:59:16 +0000

The person you replied to is in Pakistan.

New comment by nathanasmith in "Suno v4.5"

nathanasmith — Sun, 04 May 2025 17:37:20 +0000

>You're right - I don't really care if the track playing in my favourite cafe is AI-generated or not. You're not supposed to be emotionally invested into background music

I guess different strokes but some of the best music I've ever been turned on to just happened to be playing in some random cafe or coffee shop. Conversely if the music is bland and uninspired I'm much less likely to go back.

New comment by nathanasmith in "Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison"

nathanasmith — Mon, 31 Mar 2025 18:42:27 +0000

Is there an API for Grok yet? If not that could be the issue.

New comment by nathanasmith in "Gemma3 – The current strongest model that fits on a single GPU"

nathanasmith — Wed, 12 Mar 2025 13:39:05 +0000

Unfortunately that wouldn't help as much as you think since talented AI labs can just watch the public leaderboard and note what models move up and down to deduce and target whatever the hidden benchmark is testing.

New comment by nathanasmith in "GPT-4.5"

nathanasmith — Mon, 03 Mar 2025 12:59:24 +0000

I had been sleeping on Claude's ability to write books until a couple of days ago I had it write a novel set in the Accelerando universe. It whipped up a very convincing complete multi-Act 13 chapter side plot about humans learning to interact with Economics 2.0. It was quite good though I'm sure cstross would be horrified.

New comment by nathanasmith in "I will never need to buy a new computer again"

nathanasmith — Mon, 13 Jan 2025 15:47:37 +0000

I have a T420 I've been using for years. Upgraded to 16GB of RAM, SSD, swapped the dual core i5 for a 4 core/8 thread i7 (yes, the CPU is in a socket!), and swapped the 1600x900 crappy display for a newer 1080p panel that looks much better. I absolutely love this laptop and am not looking forward to the day when it's too old for the modern web.

New comment by nathanasmith in "What we learned copying all the best code assistants"

nathanasmith — Sat, 04 Jan 2025 18:45:53 +0000

For the lmarena leaderboard to be really useful you need click the "Style Control" button so that it normalizes for LLMs that generate longer answers, etc. that, while humans may find them more stylistically pleasing, and upvote them, the answers often end up being worse. When you do that, o1 comes out on top followed by o1-preview, then Sonnet 3.5, and in fourth place Gemini Preview 1206.

New comment by nathanasmith in "Meta is killing off its AI-powered Instagram and Facebook profiles"

nathanasmith — Sat, 04 Jan 2025 18:25:23 +0000

If I want to talk to AI I know where chatgpt.com is. I don't need it shoved in my face when I'm trying interact with people on social media.

New comment by nathanasmith in "Perplexity got ads"

nathanasmith — Sat, 04 Jan 2025 17:36:34 +0000

I like how it cites relevant Youtube videos based on the search and shows thumbnails of the videos in its results. As far as I can tell ChatGPT doesn't do this.

New comment by nathanasmith in "Half-Life 2: 20th Anniversary Update"

nathanasmith — Sat, 16 Nov 2024 16:42:46 +0000

When Half-Life 2 came out it caused me to break a video game addiction I'd had since being a teenager. I was so awestruck by the quality and enjoyment I derived from the game that after playing through it any other game I tried later paled in comparison to the memory. It got to the point that I couldn't make it more than 30 minutes into a new game without losing interest and eventually I just stopped buying games altogether and that was it. I'm still not sure if this is a good or bad thing.

New comment by nathanasmith in "Robinhood: Introducing the Presidential Election Market"

nathanasmith — Tue, 05 Nov 2024 17:57:55 +0000

They weren't legally allowed until very recently.

New comment by nathanasmith in "We Can Terraform the American West"

nathanasmith — Sat, 26 Oct 2024 22:20:13 +0000

Leave it alone. It's fine the way it is.

New comment by nathanasmith in "Apple introduces iPad mini built for Apple Intelligence"

nathanasmith — Wed, 16 Oct 2024 17:47:18 +0000

I don't know but I have a Galaxy Fold and I hate the tiny bezels it has in tablet mode. Trying not to touch the screen while holding it adds unnecessary cognitive load and just makes it feel fiddly. I also have a previous gen iPad mini and I love the thicker bezels.

New comment by nathanasmith in "AI is an impediment to learning web development"

nathanasmith — Tue, 08 Oct 2024 18:16:22 +0000

My experience using LLMs to learn is similar. When I read MDN or some O'Reilly tome I get a lot of information but it's in the general sense. I can use what I've learned to build some specific project and it'll work but because the book isn't tailored to the specific thing I'm doing, there will often be a much better way. The LLM on the other hand gives an answer as specific as I'm willing to give it context for and since I know software engineering as a discipline I know when the specific suggestion from the LLM is far superior to the more general method learned in the text book.

New comment by nathanasmith in "NotebookLM's automatically generated podcasts are surprisingly effective"

nathanasmith — Tue, 01 Oct 2024 18:16:29 +0000

My main issue with this is the two hosts seem to be a little too in "sync" with each other. Like they're completing each other's thoughts and sentences without missing a beat. It breaks the illusion of it actually being two different people. Other than that I'm excited about the future of this kind of thing.

New comment by nathanasmith in "Terence Tao on O1"

nathanasmith — Sun, 15 Sep 2024 04:37:46 +0000

They would be wondering why it took so long.