zlacker

[return to "Cursor's latest “browser experiment” implied success without evidence"]
1. pavlov+j91[view] [source] 2026-01-16 19:45:33
>>embedd+(OP)
The comment that points out that this week-long experiment produced nothing more than a non-functional wrapper for Servo (an existing Rust browser) should be at the top:

>>46649046

◧◩
2. pera+gl1[view] [source] 2026-01-16 20:41:47
>>pavlov+j91
Has anyone tried to rewrite some popular open source project with IA? I imagine modern LLMs can be very effective at license-washing/plagiarizing dependencies, it could be an interesting new benchmark too
◧◩◪
3. benhoy+Ru1[view] [source] 2026-01-16 21:35:44
>>pera+gl1
Not me personally, but a GitHub user wrote a replacement for Go's regexp library that was "up to 3-3000x+ faster than stdlib": https://github.com/coregx/coregex ... at first I was impressed, so started testing it and reporting bugs, but as soon as I ran my own benchmarks, it all fell apart (https://github.com/coregx/coregex/issues/29). After some mostly-bot updates, that issue was closed. But someone else opened a very similar one recently (https://github.com/coregx/coregex/issues/79) -- same deal, "actually, it's slower than the stdlib in my tests". Basically AI slop with poor tests, poor benchmarks, and way oversold. How he's positioning these projects is the problematic bit, I reckon, not the use of AI.

Same user did a similar thing by creating an AWK interpreter written in Go using LLMs: https://github.com/kolkov/uawk -- as the creator of (I think?) the only AWK interpreter written in Go (https://github.com/benhoyt/goawk), I was curious. It turns out that if there's only one item in the training data (GoAWK), AI likes to copy and paste freely from the original. But again, it's poorly tested and poorly benchmarked.

I just don't see how one can get quality like this, without being realistic about code review, testing, and benchmarking.

◧◩◪◨
4. dragon+Zh2[view] [source] 2026-01-17 05:32:46
>>benhoy+Ru1
> up to 3-3000x+ faster than stdlib

Note that this is semantically exactly equivalent to "up to 3000x faster than stdlib" and doesn't actually claim any particular actual speedup since "up to" denotes an upper bound, not a lower bound or expected value. It’s standard misleading-but-not-technically-false marketing language to create a false impression because people tend to focus on the number and ignore the "up to".

◧◩◪◨⬒
5. Dylan1+2v2[view] [source] 2026-01-17 08:51:29
>>dragon+Zh2
When you say "up to" about a list of data points, it's not just a bound. At least one has to reach that amount or it's a lie.
[go to top]