839 karma · joined December 17, 2025
Who is the best possible person you could hire to operate the LLM?
Who has a good mental model of what its doing underneath and has the best expertise to direct/guide it?
IMO no one is better positioned to use these tools than software engineers
Its a breezy novella you can finish over a lunch break
fooBar() and fooBarExtended()
The latter had additional params and functionality that was needed for the current problem.
Instead of calling that function though Claude kept trying to add in the same extended params to the first function
Even after telling it not to do that it kept suggesting the same thing again later, its so annoying sometimes
Like its only focused on solving the local problem as easy as possible
Then your job as SE just becomes reviewing and untangling vibe-coded stuff
How does low effort rage-bait spark curiosity?
The comment to upvote ratio clearly shows it’s inflammatory
People opening issues just to rant against an open source project is acceptable content for HN?
How is that even allowed in the first place without getting flagged/removed?
And every time that happens the project gets brigaded from HN users
Is that the kind of low effort posts we want around here? Just a link to a github comment of a screenshot?
You're complicit here in fueling the harassment of an open source project
The author provides evidence to the contrary and the HNers won't even engage with it instead just talking about the writing of the article in classic HN bikeshedding fashion.
How about after that we talk about the formatting of the website and the colors?
This site is really going down hill
Where is the accountability for your own opinions?
Are you guys only upvoting things that confirm your existing gripes?
Why is it that some unfounded claim is made and the onus is suddenly on the project maintainer to prove it beyond all doubt?
It should be on the person making the claim to prove it
In other words a perfect topic for HN
Plus the whole naming confused people
I still talk to co-workers who think claude code == agents and copilot is just VS autocomplete
A lot of stuff I would typically associate with the internet like pirating, forums, mail, large scale multiplayer games actually predates it
So now students are _required_ to use agents? That's a bit crazy
Would universities be paying the token cost? Is that you Dario?
I feel like that would at least catch some of these
Low end stuff is replaced by google translate but we still have people working as translators for high end stuff like books, government, legal
A lot of modern languages are still source -> IR -> binary
Still easily doable with CLI
Like how snapchat kind of fell off because the feature could just be a subset of instagram
It seems like it would just become a commodity like EC2
Like "Let's stick with what we have, its simple and it works." or "That seems overkill, let's not over complicate things"
Where does it show up in quarterly results?
I can’t see how it’s sustainable just based on “this feels more productive”