HackerTrans
TopNewTrendsCommentsPastAskShowJobs

winstonp

106 karmajoined hace 3 años

Submissions

[untitled]

1 points·by winstonp·hace 4 meses·0 comments

comments

winstonp
·anteayer·discuss
The avg coding session has hundreds or thousands of tool calls. Even a 5% failure rate noticeably notches up token use and cost. See Gemini.
winstonp
·anteayer·discuss
Doubt. Tried it, Grok 4.5 is leaps and bounds ahead of Gemini for real work.

And token costs vs. raw compute+electric cost is unit profitable too.
winstonp
·hace 6 días·discuss
While I mostly agree with your post, I do want to point out one thing:

> Or he could release a model trained largely by existing open weights models. Which without some huge breakthrough probably has no chance of surpassing them, so is pointless.

This seems to be categorically untrue. Composer 2.5 is a substantial improvement on its underlying Kimi base model.
winstonp
·hace 11 días·discuss
same happened to Opus 4.7
winstonp
·hace 17 días·discuss
the British are notoriously sensitive to heat. They'll call 30 Celsius weather a heat wave.
winstonp
·hace 23 días·discuss
do we think he found it on craigslist
winstonp
·hace 23 días·discuss
Gemini pretty clearly has the best underlying model, and the worst RL and post-training of the lot.
winstonp
·hace 24 días·discuss
It is ridiculous to be building infrastructure with a seventy five year lifespan under an assumption that may never come in its entire life.
winstonp
·hace 24 días·discuss
Car apps, beside Tesla, are universally awful to use. Even Tesla's is not beyond reproach (app size is massive, for one), but at least it doesn't make me want to poke my eyes out. Apple should make a "Cars" app that's like the "Watch" app and let them standardize.
winstonp
·hace 24 días·discuss
They are absolutely clueless about how to talk to this administration.
winstonp
·hace 25 días·discuss
CC TUI is often a culprit of memory leaks, image-pasting is a nightmare, particularly over SSH, flickering all over the UI, among others.
winstonp
·hace 25 días·discuss
You can!

You just have to pay API prices.
winstonp
·hace 25 días·discuss
google models are still very unreliable at actually calling the tools you want it to call.
winstonp
·hace 25 días·discuss
I don't believe Anthropic trains on Trainium, only serves models on it.
winstonp
·hace 30 días·discuss
Claude Code TUI is garbage. There's nothing worth protecting in there.
winstonp
·el mes pasado·discuss
I do think Anthropic nailed their naming down much better than OpenAI
winstonp
·el mes pasado·discuss
OpenAI's training is better suited to developing models that don't have these tendencies
winstonp
·el mes pasado·discuss
I've never had a smelly Mac, and I've owned maybe 10 different ones across personal and various work laptops. And 90% of devs I've ever met have used Macs and none of them smell either, so it's zero out of maybe 200+ in my personal experience.
winstonp
·el mes pasado·discuss
Google Search has been awful for the last couple of years. Good riddance to SEO.
winstonp
·hace 2 meses·discuss
Same. Overuse of the word "genuinely" is another tell.