Fishkins

You can be concerned about all of that at the same time. I'm a lifelong vegetarian who had never owned a car, but I'm also wary of attempts to alter existing ecosystems. I don't think it should be out of the question, but it should be approached with extreme caution.

> theoretically blocks any dangerous commands from running

To be more precise, this article says auto mode blocked 89% of dangerous commands in their testing.

A previous article[0] said it blocked 83%, but presumably it improved since then.

0: https://www.anthropic.com/engineering/how-we-contain-claude

> 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)

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.

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/

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.

Right, that's what I was referring to

> 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...

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?

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

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

> 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.

Thus solving the problem once and for all

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

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...

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.

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.

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.

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

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

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.

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.

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.

At one point the org I work for used it for internal documentation. They migrated off of it many years ago, though.

Huh, that's interesting. Mixing indexes and FKs is a major conceptual error.

FWIW, I've also asked everyone I've interviewed in the past decade about indexes and FKs. Most folks I've talked to seem to understand FKs. They're often fuzzier on the details of indexes, but I don't recall anyone conflating the two.

Thanks for making that PR! A regular `brew install git` installs 2.50.1 for me now.

Early on at my first full-time job I requested a week off to attend a Quaker conference. My manager approved the request without comment. After I returned from vacation he asked how the competition went. He'd never heard of Quakers and had genuinely assumed I was attending some Quake tournament.

You're on the right track with money, but that's not exactly how I'd describe the goals. My impression is the primary goals are getting things coded and billed properly and thoroughly, and getting things documented in a way that minimizes legal liability.

> Ah, but - in large and poorly-maintained codebase, it is always the case that some refactoring is already in progress, likely stalled for weeks, months or years as priorities have shifted without it having been completed.

This is true, and something I also thought of when reading that point. I don't think it's necessarily a counterargument, though. It's probably a better idea to spend your time helping to complete the previous refactor instead of starting your new one. Codebases in which many refactorings are started but not completed can be worse than ones that aren't refactored at all.

There could be exceptions if your new changes is very small, localized, and unlikely to interfere with the other changes going on.

Custom feeds and starter packs seem to be promoted much more on Bluesky than lists were on Twitter, but how different are the actual capabilities from Twitter lists? I never looked at my algorithmic feed. Instead I make a "list" of accounts I followed and pinned that list to my home view. That way I only got exactly their posts in chronological order (with no ads). I saw that recommended by some HN user long ago, but I don't remember who.

I have fully switched to Bluesky at this point anyway, but the list approach worked fine for me on Twitter long after most users were complaining about the feed algo.