HackerTrans
TopNewTrendsCommentsPastAskShowJobs

thedreammachine

9 karmajoined w zeszłym miesiącu

Submissions

Make a devtool agents want

betocmn.com
4 points·by thedreammachine·15 dni temu·2 comments

John von Neumann's the Computer and the Brain

en.wikipedia.org
3 points·by thedreammachine·16 dni temu·0 comments

Ask HN: How much do you trust LLMs with your health questions?

2 points·by thedreammachine·22 dni temu·2 comments

Return on Tokens (Rot)

notboring.co
1 points·by thedreammachine·w zeszłym miesiącu·0 comments

comments

thedreammachine
·14 godzin temu·discuss
Which large companies seem best at trying to avoid this? Apple, Airbnb, Box?
thedreammachine
·15 dni temu·discuss
So many years reading his newsletter, and forever grateful for Om. He replied to a cold email a long time ago with very specific, helpful advice on a project I was working on. What a legend!
thedreammachine
·15 dni temu·discuss
Good point, that's probably more interesting for the home-page. I will play with it. Thanks!
thedreammachine
·17 dni temu·discuss
I wonder if package indexes become more important in our new day-to-days with LLMs, not less.

We might be browsing less, but the models need a source of truth for package metadata, etc.
thedreammachine
·19 dni temu·discuss
I was surprised today by how much better GLM-5.2 was than GPT-5.5 at aesthetic/UI work. I'll keep my Claude/Codex setup via Conductor for now, but this model got me to set up OpenCode, download their desktop app and do most of my work there today.
thedreammachine
·26 dni temu·discuss
The interesting part here is not whether Anthropic is right on safety, but that safety gives them a moral vocab for bold policy changes and platform power.
thedreammachine
·26 dni temu·discuss
Yeah, this is similar to finding 10 customers who love your software rather than 1,000 who only kinda like it. And if you do, it's probably because you've found a use case that is urgent enough for one specific kind of user.
thedreammachine
·w zeszłym miesiącu·discuss
What kinds of graph shapes or query patterns do you feel are the worst case for object storage?
thedreammachine
·w zeszłym miesiącu·discuss
Humm maybe. But a plain model sampling outputs obviously isn't doing discovery in the AlphaGo sense. But once you put the model in a loop with tests, feedback, tools or even a human picking the good result, it starts to get much closer to the process he's describing.