News for hackers. Stuff that matters.

oliver236

Re:Every AI model has the same "controversial" take on humans on Thursday October 22, 2026 @11:42PM (#50204254)
> By that logic human thought is just electrochemical signals propagating through neural networks.

My dear fried: the human being is much, much more than this. And deep down we both know it. Do not reduce us to materials y "randomness". Is your life a random coincidence? Not at all.

Re:I know why Mathematicians weep on Thursday October 15, 2026 @01:57PM (#50107533)
isn't math skills really just pattern analysis and creativity? how is this limited to just the math domain? why are mathematicians worried?
what on earth is this?
Re:Mike Tomlin spent 12 years building a Minecraft city on Saturday October 03, 2026 @04:44AM (#49942457)
And he did this all with an Xbox instead of a PC?? Wow.
Re:Astra for Coding: Why Are We Doing This Again? on Saturday September 12, 2026 @01:25PM (#49674729)
Thanks for the reply! So you would say that you have personally reviewed all the tests?

I’ve been thinking about how tests comunícate product function much more clearly and durably than prose, and that it maybe possible to create some sort of portable testing SDK that connects to the codebase and allows the dev to talk to the AI by just carefully writing tests, posting them to a backlog for the AI to pick up and edit the codebase until green.

Re:Astra for Coding: Why Are We Doing This Again? on Saturday September 12, 2026 @03:53AM (#49670024)
how are you setting up excellent testing? using AI agents? hand writing tests? I hate talking to AI, I wish I could just write the test and the AI agent implement the fix
Re:OpenAI Agents API on Friday September 11, 2026 @01:52AM (#49654029)
so this is basically a massive competitor to langgraph?
Re:Launch HN: Almanac (YC S26) – AI that knows your company on Thursday September 03, 2026 @12:33PM (#49552780)
But does it cause flaming?

Twitter uses (used) a different mechanism for comment moderation and posting so it’s to reduce confusion

Re:Claude Fable 5.1 and Claude Mythos 5.1 on Wednesday September 02, 2026 @12:06AM (#49531601)
just buy two 20x, no?
why cant i choose axa ?
your website isnt working
can someone explain how leapold aschenbrenner proposes a solution to this in situational awareness?
Re:The whole of PyTorch on one page on Tuesday August 11, 2026 @04:06PM (#49263718)
can someone give recommendations of other pytorch explanations like this one?
Re:The next chapter of our AI momentum on Wednesday August 05, 2026 @06:04PM (#49189670)
you mean x, right? just to fully understand
this is exactly what leopold talks about in situational awareness
why not just use 1password
Re:You only need the frontier model for one single edit on Tuesday July 21, 2026 @02:37AM (#48988841)
can you explain this in a bit more detail? super interested
can you please give me an explanation of the two though ?
freepbx vs fusionpbx? explain please
What about deterministic parsing?

Basically using templates to extract info from recurring doc structures ??

Re:Halvar's Guide to Entrepreneurship on Monday June 29, 2026 @08:53AM (#48718643)
why did the author put the tickers for the companies he sold to?
Re:U.S. government will decide who gets to use GPT-5.6 on Friday June 26, 2026 @05:40PM (#48692337)
constitutional rights only apply to us citizens i believe
isnt the eu basically a less federalist version of the usa? how is it then that the usa claims its more free? the individual state members in the EU have more freedom than individual states.

someone explain this to me please

Re:UFO footage just released by FBI on Friday June 12, 2026 @12:20PM (#48506049)
I wonder what HN thinks about this
how could this be for better?
that is why it is called a gift
could an AI product solve this?
Re:Claude Fable 5: mid-tier results on coding tasks on Thursday June 11, 2026 @06:46PM (#48497437)
these are just openai plants

Older »