zlacker

[return to "ChatGPT Containers can now run bash, pip/npm install packages and download files"]
1. jmacd+Ig[view] [source] 2026-01-26 20:44:30
>>simonw+(OP)
I wonder how long npm/pip etc even makes sense.

Dependancies introduce unnecessary LOC and features which are, more and more, just written by LLMs themselves. It is easier to just write the necessary functionality directly. Whether that is more maintainable or not is a bit YMMV at this stage, but I would wager it is improving.

◧◩
2. Punchy+KR1[view] [source] 2026-01-27 09:08:02
>>jmacd+Ig
You have insane delusions about how capable LLMs are but even assuming its somehow true: downloading deps instead of hallucinating more code saves you on tokens
◧◩◪
3. hluska+FW1[view] [source] 2026-01-27 09:45:24
>>Punchy+KR1
And your opinions on how average people use these tools are 100% accurate?
◧◩◪◨
4. antonv+223[view] [source] 2026-01-27 16:09:25
>>hluska+FW1
If average people try vibecoding their dependencies, they’ll fail, simple as that. We’ve already seen how that looks with the “web browsers” that have recently been vibecoded.
◧◩◪◨⬒
5. simonw+Z43[view] [source] 2026-01-27 16:22:03
>>antonv+223
There's a new web browser project today that's a heck of a lot more impressive than the previous ones - ~20,000 lines of dependency-free Rust (though it uses system libraries for image and text rendering), does a good job of the Hacker News homepage: >>46779522
◧◩◪◨⬒⬓
6. antonv+Vj3[view] [source] 2026-01-27 17:16:09
>>simonw+Z43
Thanks for the heads up, that does look much more interesting.

I don't think it really affects the point discussed above for now, because we were discussing average users, and by definition, the first person to code a plausible web browser with an agent isn't an average user - unless of course that can be reliably replicated with any average user.

But on that note, the takeaways on the post you linked are relevant, because the author bucked a few trends to do this, and concluded among other things that "The human who drives the agent might matter more than how the agents work and are set up, the judge is still out on this one."

This will obviously change, but the areas that LLMs need to improve on here are ones they're notoriously weak on, so it could take a while.

[go to top]