Live data from Hacker News

Anthropic runs large-scale code migrations with Claude Code

claude.com

21–30 of 36 posts

Re: Anthropic runs large-scale code migrations with Claude Code

#21

Earlier quoted context omitted.

It's precisely because I'm not an AI naysayer that I reject the premise of the comparison. My job is not to produce as much code as I possibly can; my job is to produce features that provide value to customers in a high quality and regression-free manner. To accomplish this I use safer AI-enabled development strategies, which produce fewer lines of code and involve more manual review but also do not result in 1 regre…

Again, you are comparing things which are not comparable. "Working on a feature" and "Working on a language-to-language port of 1M LOC" are NOT the same thing. You're also still bringing up "regression per day", while ignoring the fact that without AI, this would have taken easily ~4000 days. Which is 1 regression per 0.003 calendar day. Not the same. And you still aren't addressing sibling comments reminding you tha…

No, without AI, it wouldn't have been done, which would have led to exactly zero bugs added by a needless rewrite.

Re: Anthropic runs large-scale code migrations with Claude Code

#22

> Jarred Sumner, co-founder of Bun and Member of Technical Staff at Anthropic, used Claude Code to migrate Bun from Zig to Rust. A million lines of code were produced in less than two weeks, with 100% of Bun's existing test suite passing in CI before merge. Nineteen regressions surfaced after merge and have all been fixed. I couldn't come up with a clearer example of how this kind of stuff fails to apply to my work.…

Migrating a million lines of code is how many human-engineer-years worth of work? Some quick fermi estimates place it at between 15-100 years depending on how much automated tooling is used (without AI). It really blows my mind how some AI naysayers like you fail the absolute basic common sense test of comparing the comparable. If you, without AI, merged nineteen regressions in 2 weeks, how much work has actually bee…

Exactly. My AI used to tell me some human costs of work for this feature. Like 2 months. I told start doing it, and it finished within 2 hours. Insane

Re: Anthropic runs large-scale code migrations with Claude Code

#23

Earlier quoted context omitted.

They told you, can’t you read? All 19 regressions were fixed before release.

The source article says no such thing and at least one of them ( https://github.com/oven-sh/bun/issues/31188 ) seems to have been publicly reported.

Dude, just give up and admit you misread the point in the most negative bad faith way possible.

Re: Anthropic runs large-scale code migrations with Claude Code

#25

Earlier quoted context omitted.

They told you, can’t you read? All 19 regressions were fixed before release.

The source article says no such thing and at least one of them ( https://github.com/oven-sh/bun/issues/31188 ) seems to have been publicly reported.

Because people cannot try open source software by building it themselves before release, right? No?

Re: Anthropic runs large-scale code migrations with Claude Code

#26
post #9

> Jarred Sumner, co-founder of Bun and Member of Technical Staff at Anthropic, used Claude Code to migrate Bun from Zig to Rust. A million lines of code were produced in less than two weeks, with 100% of Bun's existing test suite passing in CI before merge. Nineteen regressions surfaced after merge and have all been fixed. I couldn't come up with a clearer example of how this kind of stuff fails to apply to my work.…

They didn't ship 19 regressions over 2 weeks. "Merged" doesn't mean "shipped". Their customers have probably seen none of those because they've all been fixed. Such a terribly bad faith take. I feel upset reading this more than I should have.

Yeah, it sounds more like they found 19 regressions after the migration so far.

Re: Anthropic runs large-scale code migrations with Claude Code

#27

> Jarred Sumner, co-founder of Bun and Member of Technical Staff at Anthropic, used Claude Code to migrate Bun from Zig to Rust. A million lines of code were produced in less than two weeks, with 100% of Bun's existing test suite passing in CI before merge. Nineteen regressions surfaced after merge and have all been fixed. I couldn't come up with a clearer example of how this kind of stuff fails to apply to my work.…

Migrating a million lines of code is how many human-engineer-years worth of work? Some quick fermi estimates place it at between 15-100 years depending on how much automated tooling is used (without AI). It really blows my mind how some AI naysayers like you fail the absolute basic common sense test of comparing the comparable. If you, without AI, merged nineteen regressions in 2 weeks, how much work has actually bee…

Without AI, the migration would never have happened. People with stake in the code wouldn't have invested time in it, and would've taken the much more sane and logical route of improving their Zig codebase.

Re: Anthropic runs large-scale code migrations with Claude Code

#28
post #5

So, the whole brouhaha was so that Anthropic can write this blog post?

> So, the whole brouhaha was so that Anthropic can write this blog post?

This was suspected from the start. The PR was always going to be merged, and Anthropic was going to have their success story. Any lip service paid to "well maybe we'll merge it and maybe we won't, I dunno yet" was just that: lip service.

Re: Anthropic runs large-scale code migrations with Claude Code

#30

Earlier quoted context omitted.

Migrating a million lines of code is how many human-engineer-years worth of work? Some quick fermi estimates place it at between 15-100 years depending on how much automated tooling is used (without AI). It really blows my mind how some AI naysayers like you fail the absolute basic common sense test of comparing the comparable. If you, without AI, merged nineteen regressions in 2 weeks, how much work has actually bee…

Without AI, the migration would never have happened. People with stake in the code wouldn't have invested time in it, and would've taken the much more sane and logical route of improving their Zig codebase.

And who put you in charge deciding that improving their zig codebase is the One True Way To Do Things?

Fuck, man, this used to be hacker news, a place where curiosity is rewarded.

Post reply on HN