> So, the whole brouhaha was so that Anthropic can write this blog post?
Remember mythos ? I was half-expecting them to scare us with a new danger: How AI can covert code into other languages, and confuse the hell out of all of us.
> 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.
> 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. If I shipped nineteen regressions in 2 weeks, my company would be desperately apologizing to our customers, not writing a blog post about what a great job I did.
The regressions got fixed before a release. Do you count your internal integration branch as "shipped"?
0.02 defects per KLOC is a low density, even considering that it was "just" a port to a new language and before giving credit for the existing bugs it identified and fixed. That defect density will probably only generalize to other projects that have similarly extensive regression test suites, but it's a proof of what LLMs can do.
The source article says that "Large code migrations are a particularly effective use case for these advanced models", and the specific advantages suggest to me that the results won't generalize at all. I can't think of anything other than a large code migration that would allow for thousands of independent workstreams against a sufficiently detailed spec to stop agents from going completely off track.
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.
On what basis do you say their customers probably didn't see them? I'm not intimately familiar with Bun, but I work with people who try to do software development in this way, and they routinely ship regressions to customers. They believe that this is because we're not AI-enabled enough, and if only we had the right loops they'd stop shipping bugs; I think that it's not about the loops and the bugs reflect their lack of understanding about what they're trying to do.
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 been done? How many features did you rewrite? How many refactors did you make and how difficult were they?
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.
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 regression per calendar day.
Regressions is a meaningless metric to me. Every app has bugs, and most are either rarely encountered or aren't breaking the app. All I care about is interruption of service.
So I can expect an entirely-rust Linux kernel to be available next week then?
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?
Remember mythos ? I was half-expecting them to scare us with a new danger: How AI can covert code into other languages, and confuse the hell out of all of us.
> 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.
yes the whole thing was partially a big marketing stunt
So much complaints about wasting of energy for AI, yet how much energy does such a meaningless comment waste?
Not much, this was both accurate comment and easy to make comment.
And it is good for mental health - it allows us to express the distaste for Anthropic in a healhy way.
Goomba fallacy
[flagged]
> 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. If I shipped nineteen regressions in 2 weeks, my company would be desperately apologizing to our customers, not writing a blog post about what a great job I did.
The regressions got fixed before a release. Do you count your internal integration branch as "shipped"?
0.02 defects per KLOC is a low density, even considering that it was "just" a port to a new language and before giving credit for the existing bugs it identified and fixed. That defect density will probably only generalize to other projects that have similarly extensive regression test suites, but it's a proof of what LLMs can do.
The source article says that "Large code migrations are a particularly effective use case for these advanced models", and the specific advantages suggest to me that the results won't generalize at all. I can't think of anything other than a large code migration that would allow for thousands of independent workstreams against a sufficiently detailed spec to stop agents from going completely off track.
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.
On what basis do you say their customers probably didn't see them? I'm not intimately familiar with Bun, but I work with people who try to do software development in this way, and they routinely ship regressions to customers. They believe that this is because we're not AI-enabled enough, and if only we had the right loops they'd stop shipping bugs; I think that it's not about the loops and the bugs reflect their lack of understanding about what they're trying to do.
I guess even anthropic fails to not get slop from ai ..
Umm yeah because you didn't rewrite a million line codebase in Rust in two weeks.
Obviously "regressions" is not a great measure (how serious were they?) but 19 seems pretty decent to me.
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 been done? How many features did you rewrite? How many refactors did you make and how difficult were they?
Insane...
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.
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
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 regression per calendar day.
Regressions is a meaningless metric to me. Every app has bugs, and most are either rarely encountered or aren't breaking the app. All I care about is interruption of service.