Hacker News: Fishkins

New comment by Fishkins in "Earth is now heating up twice as fast as in previous decades"

Fishkins — Thu, 21 May 2026 20:38:23 +0000

> I missed the part where this has anything to do with saving time

It lets you put the non-car stuff closer together, so you're traveling less distance to get to the same place. It requires urban design, not just a single person switching between modes of transit.

(Although switching to cycling can often make transit both faster for you and the people around you in a city because you aren't as affected by traffic and don't create as much traffic)

New comment by Fishkins in "Gemini 3.5 Flash"

Fishkins — Tue, 19 May 2026 18:48:10 +0000

The boat itself rocks, but do you see the background changing to indicate the boat is progressing through the environment? I only see that in the 3.1 Pro example. I believe that's what the OP meant.

New comment by Fishkins in "Agents need control flow, not more prompts"

Fishkins — Thu, 07 May 2026 19:14:18 +0000

Agreed. I think the approach described here is promising. Most of the workflow is deterministic and includes safeguards, but an LLM is invoked in the one case where it's really useful.

https://lethain.com/agents-as-scaffolding/

New comment by Fishkins in "Anatomy of the .claude/ folder"

Fishkins — Fri, 27 Mar 2026 21:02:07 +0000

I'm sure most folks run Claude without isolation or sandboxing. It's a terrible idea, but even most professional software developers don't think much about security.

There many decent options (cloud VMs, local VMs, Docker, the built-in sandboxing). My point is just that folks should research and set up at least one of them before running an agent.

New comment by Fishkins in "Anatomy of the .claude/ folder"

Fishkins — Fri, 27 Mar 2026 20:55:40 +0000

Right, that's what I was referring to

New comment by Fishkins in "Anatomy of the .claude/ folder"

Fishkins — Fri, 27 Mar 2026 20:53:41 +0000

> The part about permissions with settings.json [0] is laughable

I never said "permissions", I said "sandboxing". You can configure that in settings.json.

https://code.claude.com/docs/en/sandboxing#configure-sandbox...

New comment by Fishkins in "Claude loses its >99% uptime in Q1 2026"

Fishkins — Fri, 27 Mar 2026 18:51:35 +0000

Thanks for the data-based comment!

Have you noticed any change in that trend in the past year or two, or is it continuing to get better?

New comment by Fishkins in "Anatomy of the .claude/ folder"

Fishkins — Fri, 27 Mar 2026 16:07:43 +0000

I agree with most of this, with one important exception: you should have some form of sandboxing in place before running any local AI agent. The easiest way to do that is with .claude/settings.json[0].

This is important no matter how experienced you are, but arguable the most important when you don't know what you're doing.

0: or if you don't want to learn about that, you can use Claude Code Web

New comment by Fishkins in "Shell Tricks That Make Life Easier (and Save Your Sanity)"

Fishkins — Thu, 26 Mar 2026 17:05:01 +0000

I do something similar. I leave up and down arrows alone, but have ctrl+p and ctrl+n behave as you describe.

New comment by Fishkins in "Reports of code's death are greatly exaggerated"

Fishkins — Sun, 22 Mar 2026 18:36:36 +0000

> humans also make mistakes

This is broadly true, but not comparable when you get into any detail. The mistakes current frontier models make are more frequent, more confident, less predictable, and much less consistent than mistakes from any human I'd work with.

IME, all of the QA measures you mention are more difficult and less reliable than understanding things properly and writing correct code from the beginning. For critical production systems, mediocre code has significant negative value to me compared to a fresh start.

There are plenty of net-positive uses for AI. Throwaway prototyping, certain boilerplate migration tasks, or anything that you can easily add automated deterministic checks for that fully covers all of the behavior you care about. Most production systems are complicated enough that those QA techniques are insufficient to determine the code has the properties you need.

New comment by Fishkins in "Global warming has accelerated significantly"

Fishkins — Fri, 06 Mar 2026 16:58:17 +0000

Thus solving the problem once and for all

https://www.youtube.com/watch?v=VW66EX75jIY

New comment by Fishkins in "I'm Kenyan. I don't write like ChatGPT, ChatGPT writes like me"

Fishkins — Mon, 15 Dec 2025 18:30:34 +0000

This is a couple of years old now, but at one point Janelle Shane found that the only reliable way to avoid being flagged as AI was to use AI with a certain style prompt

https://www.aiweirdness.com/dont-use-ai-detectors-for-anythi...

New comment by Fishkins in "Google confirms Android attacks; no fix for most Samsung users"

Fishkins — Mon, 08 Dec 2025 19:43:29 +0000

I had the same experience as peer comments. I'm on Pixel 8 and Google Fi. When I check for updates, I'm told I'm up-to-date with the last update being over a month old.

New comment by Fishkins in "Claude Sonnet 4.5"

Fishkins — Mon, 29 Sep 2025 23:00:39 +0000

You should see an "unvote" or "undown" link to the right of the timestamp (i.e. the opposite side from where the vote arrows were). It's fairly subtle.

New comment by Fishkins in "The Theatre of Pull Requests and Code Review"

Fishkins — Thu, 25 Sep 2025 14:47:55 +0000

Yeah, I never send a PR out without reviewing each commit myself and adding GitHub comments when I think it's relevant. Sometimes a PR is clear enough that I don't feel the need to add comments, though.

New comment by Fishkins in "A shift in developer culture is impacting innovation and creativity"

Fishkins — Fri, 19 Sep 2025 18:31:17 +0000

I'd say "good old days" thinking is probably involved, but not the full explanation. Over the past few decades, software has gone from a fairly obscure profession to being seen as a great way (maybe the best way) to make a lot of money. In absolute numbers, there are probably at least as many engaged, curious engineers as before. There are almost certainly drastically more uninterested engineers who are there partially or fully because of the money, though.

edit: I hadn't scrolled down to https://news.ycombinator.com/item?id=45303388 when I wrote this

New comment by Fishkins in "NPM debug and chalk packages compromised"

Fishkins — Mon, 08 Sep 2025 21:09:59 +0000

For others who didn't know, the -u flag in the OP's command makes it so ripgrep _will_ search files even if they're gitignored

New comment by Fishkins in "Pixel 10 Phones"

Fishkins — Wed, 20 Aug 2025 21:45:07 +0000

It isn't nearly as big of an issue as the phone size, but it is still a nuisance. I know there's no chance of it ever coming back, but I'd like it to.

I still have a small amount of hope that someone will make a modern, well supported ~5" Android phone. But that's also feeling less likely.

New comment by Fishkins in "Pixel 10 Phones"

Fishkins — Wed, 20 Aug 2025 19:42:41 +0000

Yeah, the main news I want to hear is the release of smaller Pixel phone. Secondarily, I'd like the return of the 3.5mm port. I don't care about any of the stuff they actually announce.

I do currently use a Pixel, but I hate how big it is.

New comment by Fishkins in "White House prepares order targeting banks for "unbanking" for political reasons"

Fishkins — Thu, 07 Aug 2025 18:38:13 +0000

I'd say a large part of the country had the same sentiment about George W Bush. I'm not sure whether that was true or just an act, though. In politics, I think the opposite of Hanlon's razor has often been applicable. It's easy to feign ignorance to avoid responsibility.

That being said, I believe there has been an increase in genuinely dumb people in American politics in the past ~15 years.