HackerTrans
TopNewTrendsCommentsPastAskShowJobs

BoumTAC

1,430 karmajoined 10 yıl önce
I'm building GpxTrace to improve the way we create gpx trace.

https://gpxtrace.com/

And my blog: https://boumtac.com/

Submissions

Grok 4.5

x.ai
771 points·by BoumTAC·3 gün önce·1,477 comments

Show HN: BoumWave,a static blog generator that does what it needs to

github.com
3 points·by BoumTAC·8 ay önce·1 comments

Pavel Durov on Lex Friedman podcast [video]

youtube.com
4 points·by BoumTAC·9 ay önce·0 comments

Microsoft Mandates a Return to Office

theverge.com
6 points·by BoumTAC·10 ay önce·1 comments

comments

BoumTAC
·3 gün önce·discuss
Grok Build sucks compare to composer 2.5. Just use compose 2.5 and you'll have basically unlimited usage on the 40$ plan.
BoumTAC
·25 gün önce·discuss
Compose 2.5 is the default model in Grok Build. And it's quite incredible. It's comparable to Opus 4.7 but faster and incredibly cheaper .
BoumTAC
·2 ay önce·discuss
I’ve just started a new app with an Elm frontend. I’m using Grok Build, and it integrates really well.

The compiler is incredibly helpful because it catches errors and gives clear explanations and the LLM can iterate over it. I’ve also added the elm-review package with the default configuration, which is fantastic for ensuring code quality.
BoumTAC
·2 ay önce·discuss
I don't know how they do this, but Paris is full of Americans living there.

I think they stay for a few months. Maybe they just don't tell their company and the company still think they are working in the same place.
BoumTAC
·2 ay önce·discuss
Americans enjoying their huge American salaries while working remotely from poor European countries
BoumTAC
·4 ay önce·discuss
But they are getting dramatically better.

What's the point of a crazy cheap model if it's shit ?

I code most of the time with haiku 4.5 because it's so good. It's cheaper for me than buying a 23€ subscription from Anthropic.
BoumTAC
·4 ay önce·discuss
To me, mini releases matter much more and better reflect the real progress than SOTA models.

The frontier models have become so good that it's getting almost impossible to notice meaningful differences between them.

Meanwhile, when a smaller / less powerful model releases a new version, the jump in quality is often massive, to the point where we can now use them 100% of the time in many cases.

And since they're also getting dramatically cheaper, it's becoming increasingly compelling to actually run these models in real-life applications.
BoumTAC
·4 ay önce·discuss
It's because they are getting so good it's impossible to recognize them.

Haiku 4.5 is already so good it's ok for 80% (95%?) of dev tasks.