Hacker Newsnew | past | comments | ask | show | jobs | submit | achille's commentslogin

Absolutely, they didn't give the agents autonomy to research or any additional data. No documentation, no web search, no reference materials.

What's the point of building skills like this?



Extreme longevity with a none is kind of depressing.


Why? Life for an individual is long enough IMO. Death means renewal. Our children are better than us.


I like being alive and I like myself.


Even besides our selfish impulse to live the 'why' is clear. If death is inherently a bad loss, then the longer life extension takes the worse it is.


thanks for sharing that, it was simple, neat, elegant.

this sent me down a rabbit hole -- I asked a few models to solve that same problem, then followed up with a request to optimize it so it runs more efficiently.

chatgpt & gemini's solutions were buggy, but claude solved it, and actually found a solution that is even more efficient. It only needs to compute sqrt once per iteration. It's more complex however.

                   yours  claude
  ------------------------------
  Time (ns/call)    40.5   38.3
  sqrt per iter        3      1
  Accuracy        4.8e-7 4.8e-7
Claude's trick: instead of calling sin/cos each iteration, it rotates the existing (cos,sin) pair by the small Newton step and renormalizes:

  // Rotate (c,s) by angle dt, then renormalize to unit circle
  float nc = c + dt*s, ns = s - dt*c;
  float len = sqrt(nc*nc + ns*ns);
  c = nc/len; s = ns/len;
See: https://gist.github.com/achille/d1eadf82aa54056b9ded7706e8f5...

p.s: it seems like Gemini has disabled the ability to share chats can anyone else confirm this?


Thanks for pushing this, I've never gone beyond "zero" shotting the prompt (is it still called zero shot with search?)

As a curiosity, it looks like r and q are only ever used as r/q, and therefore a sqrt could be saved by computing rq = sqrt((rxrx + ryry) / (qxqx + qyqy)). The if q < 1e-10 is also perhaps not necessary, since this would imply that the ellipse is degenerate. My method won't work in that case anyway.

For the other sqrt, maybe try std::hypot

Finally, for your test set, could you had some highly eccentric cases such as a=1 and b=100

Thanks for the investigation:)

Edit: BTW, the sin/cos renormalize trick is the same as what tx,ty are doing. It was pointed out to me by another SO member. My original implementation used trig functions


Nice, that worked. It's even faster.

                 yours  yours+opt  claude
  ---------------------------------------
  Time (ns)        40.9      36.4    38.7
  sqrt/iter           3         2       1
  Instructions      207       187     241
Edit: it looks like the claude algorithm fails at high eccentricities. Gave chatgpt pro more context and it worked for 30min and only made marginal improvement on yours, by doing 2 steps then taking a third local step.

https://gist.github.com/achille/23680e9100db87565a8e67038797...


Haha nice, hanging in there by a thread


Consider updating your answer on SO - I know I'll keep visiting SO for answers like these for quite some time. And enjoy the deserved upvotes :)


Do you think you can extend it to distance from a point to an ellipsoid?


Yes, people have done this


I ran some analysis on the source image — this is almost certainly AI-generated. In addition to the visual markers others noted (no photography in federal court, nonsensical positioning), here's what comes up in the original image:

  Filename: ..._simple_compose_01kdcxamjmekery2m9tay43szn.png
    - "simple_compose" + LSB common (e.g ideogram) output 

  Resolution: 1536x1024
    - Exact native output of GPT-image-1, Gemini/Imagen, Flux models

  PNG encoder fingerprint: 0x78 0xDA | single IDAT | 94.7% Average filter
    - Matches PIL/Pillow with optimize=True

  Steganographic watermark:
    - LSB entropy: 3.0/3.0 (maximum)
    - Bits 0-3 of RGB channels filled with encrypted payload
    - ~1.77 MB of pseudorandom data embedded


Thanks for letting us know what your chatgpt told you


The analysis and tools were most definitely ai-aided, but this was done with homegrown forensics tooling, and about an hour of labor that involved cc, gemini (to check for synthid), chatgpt + a lot more. I also signed up for ideogram and generated more images to try and replicate the output: - e.g: https://ideogram.ai/g/fcqp-qTlQV-moS-OuhebhQ/1 (although I refused to pay for ideogram so I could not get a png output, only jpg)


Could you share your skill and workflow? does claude launch codex in a tmux session?



The paper describes a split Alvarez (Lohmann) lens [1,2] with a phase modulator between them. I didn't do the math, but it looks like the phase modulator is optically equivalent to a mechanical shift of the Alvarez lenses over regions of the field of view. Alvarez lenses have higher aberrations, and are relatively bulky, compared to normal lenses. AR was referenced in the paper, but this lens will be hard to make compact, and have great image quality, over large fields of view.

1. https://www.laserfocusworld.com/optics/article/16555776/alva... 2. https://pdfs.semanticscholar.org/55af/9b325ba16fa471e55b2e49...


It's not even loading for me (probably because it's a huge file).





Good article!


you might be thinking of seinquotes -> click the image to get a video gif of the quote https://seinquotes.com/?search=hold+the+reservation


yes, think of it this way: why is it that bathing the Earth with 10^55 Boltzmann constants make it seemingly emit a Tesla?

can we construct a warm winter garment without having to manually pick open cotton poppies?

if we place energy in the right location, can we have slime mold do computation for us?

how do we organize matter and energy in order to watch a funny cat video?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: