_zoltan_
Re:Ask HN: How to deal with shipping AI-written code you don't underst...
on Friday October 23, 2026 @03:28AM (#50205564)
I appreciate the time you took to reply to me.
Thank you!
Re:Ask HN: How to deal with shipping AI-written code you don't underst...
on Wednesday October 21, 2026 @03:28AM (#50177225)
so the workers understand cross worker topology? Do they always just see individual tiles? what if there is a dependency - eg I'm streaming data and want to compute something later on an earlier computation? How would that get distributed?
Re:Ask HN: How to deal with shipping AI-written code you don't underst...
on Monday October 19, 2026 @06:11PM (#50158756)
sounds very cool - is this basically "C" support for cuTile? :)
Re:Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X
on Tuesday October 13, 2026 @02:08AM (#50067450)
In 2 years once it fails and Intel shuts it down completely you mean :)
Re:QGIS bans AI assisted contributions
on Monday October 12, 2026 @07:43AM (#50054942)
That's not entirely true: my work might get zero traction because nobody will know about it.
Re:Passkeys are a trap. Do not use them
on Monday October 12, 2026 @03:46AM (#50052811)
hmm, I'm sure with a model that is not restricted, one might be able to extract these locally.
Re:'Jonathan' Is the Oldest Land Animal on Earth
on Thursday October 08, 2026 @08:57AM (#50005291)
Cold, no sun AND no alcohol? Man that must suck. :)
Re:Sharing AI progress in mathematics
on Wednesday October 07, 2026 @05:58AM (#49990521)
As Terry Tao said, LLMs are not outsmarting us, they are out remembering us.
I'm fairly sure your understanding is not fully accurate.
Re:Agents don't need memory. They need documentation
on Sunday October 04, 2026 @03:49PM (#49957196)
But reading the doc if it's maintained llmwiki style is much cheaper than reading the code on a large codebase.
Re:Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 1...
on Sunday October 04, 2026 @01:34PM (#49955962)
vast.ai?
Re:The Forgetful CPU (Linux on M4)
on Saturday October 03, 2026 @02:04AM (#49941719)
reaching the goal is what matters. I never understood people who don't get satisfaction from getting there. I don't care that AI writes the code.
Re:Fakecloud: Local AWS cloud emulator for integration tests
on Sunday September 27, 2026 @03:20PM (#49869930)
why does it matter that it's a vibe coded website?
Re:AI coding has made CI a bottleneck, so we reworked ours to keep up
on Tuesday September 22, 2026 @05:19AM (#49798452)
I actually look at the tests first. But for this to work, you have to have good hygiene. If the test makes sense, fails without the PR but passed with the PR, I'm almost happy.
Re:Google's Open Agentic Orchestrator
on Monday September 21, 2026 @04:45AM (#49784753)
billions? who is running BILLIONS of agents?
tens, hundreds, maybe a couple thousand at a time? absolutely.
Re:How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip
on Saturday September 19, 2026 @03:46PM (#49769586)
I optimize a lot of CUDA and it got really, really good at it.
Re:PS5 Linux lead quits: "a bunch of noobs using LLMs" that "they don'...
on Wednesday September 16, 2026 @11:14AM (#49728328)
you might be OK with calling everybody using LLMs a bunch of noobs. I disagree. this has nothing to do with my own usage.
Re:Building a Linux GPU Driver for the M4 Mac Mini in One Month
on Wednesday September 16, 2026 @04:36AM (#49723623)
Anti LLM is not justified, it's crazy. They are digging their own grave.
Re:Pion, an agent designed to run any company autonomously
on Tuesday September 15, 2026 @03:41PM (#49717805)
I don't need to go that far, living in Switzerland. I don't know why you'd assume I'm in the US, or somehow that I regard Kraft as great cheese.
Re:Pion, an agent designed to run any company autonomously
on Tuesday September 15, 2026 @03:39PM (#49717781)
for your point a: writing code by hand puts you ahead of the people who don't write code by hand, eg, the people using LLMs to generate code? that doesn't make much sense assuming both of those personas are senior SWEs.
Re:Pion, an agent designed to run any company autonomously
on Tuesday September 15, 2026 @02:37PM (#49716845)
buy another sub.
Re:Pion, an agent designed to run any company autonomously
on Tuesday September 15, 2026 @03:54AM (#49709194)
Yes, it is a waste of time right now not to use AI to write code.
It's the same category of "artisan code" like "artisan cheese": you can do it if you have a ton of free time as a hobby but other than a hobby? Not worth it.
Re:Don't be the out of touch Kung Fu master – John Carmack
on Sunday September 13, 2026 @01:46PM (#49686555)
Eh, take your fav painter then.
Re:Don't be the out of touch Kung Fu master – John Carmack
on Sunday September 13, 2026 @06:13AM (#49682180)
that's a dumb comparison. are you equating writing code to painting like Michaelangelo?
Re:Don't be the out of touch Kung Fu master – John Carmack
on Sunday September 13, 2026 @04:48AM (#49681598)
coding for the sake of coding is, well, dumb.
Re:Don't be the out of touch Kung Fu master – John Carmack
on Sunday September 13, 2026 @04:34AM (#49681486)
> Focusing on data structures, architecture and algorithms is what competency in programming has looked like since forever
yes, being able to bang out leetcode hard from head on an interview on paper matters so much... oh wait. it does not.
in the real world, outside of interview questions, it hardly matters. when it comes there, I'll optimizite it, but getting the first system up and running in a way I want is way more fun & challenging. need a lock free ringbuffer? I'll look up what's the latest way to build it. or just ask my AI.
Re:Don't be the out of touch Kung Fu master – John Carmack
on Sunday September 13, 2026 @04:32AM (#49681472)
a lot of people don't understand that the joy of making something is not coding but actually being able to build anything I want. AI just made it 50x better, as exactly as you said, we don't need to deal with the useless junk (what's the API syntax? what's the library syntax? oh it changed in the last 3 versions, let me look up the new API, this and that...).
it's great.
Re:A misalignment of AI in mathematics
on Friday September 11, 2026 @04:06PM (#49664585)
Welcome to the new world. I, for one, welcome our new math overlords. :)
Re:118M Queries per Second on Neki
on Friday September 11, 2026 @02:27PM (#49663029)
> The benchmark was very simple. A single-shard point select, one row fetched per-query by primary key. No writes, joins, or cross-shard queries. The workload that each shard receives is isolated, in that there are no single queries that span multiple shards.
I mean... What's the point of this "benchmark"?
Re:The little holes in your bread are telling you something
on Friday September 11, 2026 @02:07AM (#49654123)
https://www.youtube.com/watch?v=n0U8RdRdFDU
do this. thank me later. (yes, it takes multiple days!). as good as when we hop over to France.
Re:Tell HN: OpenAI keeps re-enabling the 'allow training' setting
on Thursday September 10, 2026 @05:18PM (#49650282)
hahah :) sorry, typo... in hungarian both v and w are the same sound spoken so if I don't concentrate, easy to mix up.