News for hackers. Stuff that matters.

dphuang2

I am curious about the exceptions. Is *anybody* using an agent framework with large production usage? I suspect no, but curious to see if anybody on HN knows otherwise.
Re:After 3 Years, I Failed. Here's All My Startup's Code on Tuesday December 17, 2024 @11:54AM (#42442959)
Konfig founder here, 100% agree. I wouldn't recommend anybody to actually try to decipher/deploy Konfig for their own use. I will say that one of our customers was able to deploy our docs platform for themselves while they find a way to deal with the blowout of Konfig shutting down.
Re:I Built My Resume in Markdown on Friday December 06, 2024 @01:34PM (#42342645)
why, for visual or functional reasons?

UPDATE: I looked it up, I guess its just convention tp use en dash

Re:After 3 Years, I Failed. Here's All My Startup's Code on Wednesday November 27, 2024 @12:57PM (#42258115)
thanks for linking it directly
Re:Not All Problems Are Great Fits for LLMs on Monday November 18, 2024 @07:49PM (#42179016)
I think the transformers can be leveraged in a similar way for robotics. Prior art probably exists in self-driving or humanoids.
javascript fatigue
Interesting read. Contrary to what HN thinks, I think its good that VCs feel a forcing function to differentiate themselves. Like any other market, competition is good.
Re:I Reviewed 1,000s of Opinions on HTMX on Wednesday May 01, 2024 @06:06PM (#40230132)
none taken—I appreciate the criticism!
Re:I Reviewed 1,000s of Opinions on HTMX on Wednesday May 01, 2024 @04:42PM (#40229139)
The original purpose of the article is to highlight opinions from the community—not to be a scientific conclusion on what approach is better.

If somebody is seeking an answer for their own engineering problems, then the necessary due diligence is always required on their part.

Re:I Reviewed 1,000s of Opinions on HTMX on Wednesday May 01, 2024 @04:37PM (#40229058)
Thanks for the kind comment! Glad you enjoy the content style—it takes a lot of time to gather comments.

Hm, definitely interesting to have some inline example/resources, I can see examples augmenting the original opinions.

Re:LLMs Can't Do Probability on Wednesday May 01, 2024 @02:26PM (#40227205)
What an ironic observation since LLMs are itself a probability machine.
Re:I Reviewed 1,000s of Opinions on HTMX on Wednesday May 01, 2024 @02:06PM (#40226931)
Such an experiment has happened and well-documented here: https://htmx.org/essays/a-real-world-react-to-htmx-port/.

But still, experiments only happen in one context so its hard to extrapolate how the results would predict your own situation. This is why I think parsing opinions is a great through-provoking exercise.

Older »