fooster

We do that, and the cost of forking the cli vs the llm or network call is very small. It works really well.

Neither of those things are true?

Also you are seriously comparing process startup time with the latency of a network call, or worse an llm call?

Carney made it pretty clear what was in the deal. I don’t understand why you believe Trump who lies every time he opens his mouth?

Yeah 51st state governer carney. This guy is deadly serious. Deals hammered out with Trump are not worth the paper they’re written on. Besides that Trump has already violated CUSMA a deal he signed himself and has invoked ridiculous laws to punish Canada while lying through his teeth the entire time.

What do you expect Carney to do what that!?

It’s also worth mentioning that these are very western ideas. Lots of other cultures derive alternative structures not based around 12 half steps to an octave and so on.

I've used linux desktops for years, and in my experience it is quite difficult to fight against the default keybindings. It is much easier to go with the status quo, which is annoying especially if you regularly switch between a mac and linux machine.

Otherwise known as fiction.

Apart from anything else the keybindings are the most annoying thing ever.

Ok, what am I using on my workstations then? Windows? Hell no. Terrible hardware, OS sucks. Linux? Hell no! Terrible hardware, desktop is terrible.

> Why wouldn't it be deliberate? Do you think it's happening without the Anthropic team's go ahead? Or maybe they aren't aware that it's happening?

Yes that’s exactly what I think. I also don’t think the team was aware that opus 5 talks like an overcooked gibbon either. And what’s more I’m certain that it will do neither very soon.

I'm certainly reading the code and comments, and I encourage all of my team members to do so. You are assuming that this excessive and nonsensnical comment choice is deliberate. It cannot be, or should not be because it regularly confused our team, and it regularly confuses claude also.

Also many many people keep saying the same thing and you keep repeating adnausium the same tired comments. I get it, you think the comments are great and are valuable.

Read the entire thread https://news.ycombinator.com/item?id=49393378

The concensus in this thread is that for multiple reasons the excessive comments are in fact actively harmful. The listed reasons are:

1. Document the conversation, not the code — narrate the back-and-forth that produced the change rather than what the code does

2. Reference intermediate states that never shipped ("previously X, now Y")

3. Cite plan documents and session artifacts (`per section 2.1 of addition-implementation-plan.md`) meaningless to a future reader

4. Belong in commit messages or PR comments, not source files

5. Go stale immediately — describe a state the code is no longer in

6. Launder incorrect code as intentional, making bugs harder to spot

7. Build a false Chesterton's fence around mistakes

8. Use defensive prose ("this is not cosmetic", "prevents the critical bug that shipped once") that asserts importance instead of conveying information

9. Describe what the code doesn't do — relevant in the moment, not in the codebase

10. Confuse later agent sessions, sending them to read irrelevant files

11. Consume context tokens on every read

12. Force reviewers to manually delete the litter

13. Resist correction — telling Claude to be concise doesn't durably stick

Please consider that your opinion may need to adjusted.

No it doesn’t. The comments are hugely verbose trash that immediately becomes outdated and brittle and confusing for humans and Claude alike.

They’re monsters? Did they shutter an agency which caused the death on how many millions again?

I didn’t see china calling to annex Canada. The bad relations between china and Canada were also principally caused by the US insisting that we detain Meng Wanzhou. We can see what thanks we got for that.

Yes lots and lots of growth.

You can accept what you like, but it's true. Our team and our business is incredibly more productive. The number of new valuable customer facing features, and the number of PRs (which represent REAL work, not taking a PR and splitting it into 200 PRs game) have all increased dramatically. We've shipped something like ~10x more PRs so far this year than all last year. And we've done that without increasing the number of bugs and outages.

I don't think that is true. coding at a baseline is hard no matter what. If it was easy everyone could have done it, and clearly that isn't true.

Now there is hard-er coding. Novel algorithms, performance sensitive stuff, and so on.

They’re going zip it up, as if that won’t break eventually and then leak into the environment. I don’t need to be an environmental scientist to know that is a monumentally stupid solution.

Yeah sure I’m deep ocean it would kills the local ecosystem

The ocean seems to contain a great deal of salt though.

It’s also not true that because it wasn’t part of the initial design that it was harder to retrofit. I just don’t understand all this go bashing that happens on this site especially when so much is badly informed speculation. I guess it’s easier to tear something down.

I don’t see it that way. What maga is going is completely and utterly outside the law.

Saying it is a matter of degree is an attempt to make what the current administration is doing is similar to what prior admins did. They are not. They are corrupt to the core. As for Biden he pardoned his son beacuse of a MAGA witchhunt.

Just to quote a poster above:

"You seem to think China is the evil polluter here. Just sort by per capita, and you'll see it's not even in the top 10% most polluting per capita."

Dude, really open your mind and stop arguing mindlessly. We're using this to great success on a serious sass product with hundreds of thousands of users. I'm not some AI influencer, or blowing smoke.

The source of errors can be whatever you like. Sentry, grep, whatever. Its not the point. The point is that many of these errors are real issues, and can be fixed automatically and safely by agentic systems. It really saves time, and work by our team leaving them to actually concentrate on the thing that delivers real value.

Not really? Imagine for example looking for http status code 500 in an api log over the past hour. The nice thing here is it doesn’t matter if you get them all because it’s reoccur (or not).

There are many sources of boring predictable errors which nonetheless are easy to miss and easy to fix. API validation errors for example.

Really they're not. But it seems you have decided that you, above all, know best.

You want your team spending their time fixing these simple errors? The secret sauce is in the triage. We've adopted solutions alot like this, and now our team spends its time on much more meaningful work.

I think you need to open your mind to the possibilities? For example:

- scanning logs for errors and

- opening issues which are then auto-triaged and

- PRs are opened for them and auto-reviewed and

- merged (and deployed).

This workflow alone is immensely powerful, and takes alot of burden off the team.