pnathan

Joined 15 years ago

Karma
11,776
Submissions
4,081
Member since
Jan 28
Hi!

Some facts:

- Living and working in Spokane, WA (formerly Seattle )

- Write code, talk to people

- I sit at the intersection of SRE and SWE.

- Email: [email protected]

Please feel 100% free to email me out of the blue. I really do love meeting new people, and try to respond to everyone I can - if I didn't respond, it's not because I didn't want the email, it's because I'm swamped.

- I usually take 1-3 days to respond to comments. This is conscious - deliberation and a cool head gives an immediate thinking bonus.

Some other notes:

- http://articulate-lisp.com Common Lisp for new users!

- I've been programming since the mid-90s

- Has grad degree, M.S. in Computer Science.

- PL geek: experiences in... assemblies, bash, c++, c#, common lisp, golang, haskell, java, objective c, ocaml, perl, prolog, python, rust, scala

- Portfolio/open source work: https://github.com/pnathan

---

[ my public key: https://keybase.io/pnathan; my proof: https://keybase.io/pnathan/sigs/thq2TfZ0ss836xvC6arGWYCzkZAjXYoRVrljegtzf2s ]

View on Hacker News

Recent submissions

Comment · 2 hours ago
really? I think its one of the best websites going these years.
Comment · 2 hours ago
My wife and I had a long running debate: is psychosis socially transmissible or is it purely mechanical? QAnon answered the debate conclusively: there is an entire class of psychosis that is socially transmissible. I believe AI is driving another psychotic mass disorder among the ai world, and at some level people need to walk away.

It's literally just tensor multiplications at the end of the day, generating likely outcomes in useful ways.

Comment · 1 month ago
I've been working on https://arbiter.housecarl.cloud/ .

It's a deterministic judgement engine for disagreeing inputs. The input interface is shaped for LLMs now, but there's no particular reason it has to stay limited that way & it has a normal API.

I pulled in a lot of research on conflict logics to build it out.

The next big push technically will be an ingest pipeline and a more sophisticated logic engine.

Comment · 2 months ago
> Suppose you have taste. Suppose you paid the full price and you can feel the sag in the sentence and the wrongness in the function. > > Congratulations! You now ship at exactly the same speed as the person who cannot.

Yes, previously the person who didn't understand shipped faster. It was a long standing problem. The people who crapped, got the bonus, and ran were much faster than the patient engineer of quality.

By the way, what were the essays that formulated Claude Style? if the author was indeed formed by them, I'd like to read them - or at least enough of them to understand.

Comment · 2 months ago
Reflecting on the matter with a colleague -

Some people just want to _cook the steak_.

They don't want to attend or understand to cuts, thermometers, and searing.

Comment · 4 months ago
(1) personally very annoying. I have been using fable to try to collect cutting edge math in one area and work on a hopefully new result with lean verification.

(2) I am really tired of the AI community trying to threaten everyone with grey goo and finding out the hype doesn't land comfy with others. It's a freaking text generator, not god in a pocket.

Comment · 6 months ago
Shoot at high f numbers - as high as the lens will take without inducing diffraction.
Comment · 6 months ago
I have found TTArtisans 50mm f0.95 to be quite nice.
Comment · 6 months ago
This is good. I recently had to replace a generally working phone because the battery was dying and there was no cost effective & reliable means of replacing.

A proper gasket and screws needs to be the standard solution here.

Comment · 7 months ago
Data is missing on this chart.

It's my experience that opus 4, and then, particularly, 4.5, in Claude code, are head and shoulders above the competition.

I wrote an agentic coder years ago and it yielded trash. (Tried to make it do then what kiro does today).

The models are better. Now, caveat - I don't use anything but opus for coding - Sonnet doesn't do the trick. My experience with Codex and Gemini is that their top models are as good as Sonnet for coding...

Comment · 8 months ago
I am experimenting at a very early stage with using Verus in Rust to generate proveably correct Rust. I let the AI bang on the proof and trust the proof assistant to confirm it.

There is another route with Lean where Rust generates the Lean and there is proof done there but I haven't chased that down fully.

I think formal verification is a big win in the LLM era.

Comment · 8 months ago
I'd have to see more to have a final thought.

As presented, Gollum is badly off, I reckon - missing the books textual description. The flowers are out of line.

The dragon scene is wonderful and captures the situation.

The dwarves are a bit dopy looking but I think could cohere with the early introduction in the Hobbit.

Comment · 8 months ago
Great article.

I do have a deep fondness for SF billboards being building-stuff oriented. I don't care for consumerism.

The vapidity of the products created is remarkable, however.

Comment · 9 months ago
I'm looking forward to when I can run a tolerably useful model locally. Next time I buy a desktop one of its core purposes will be to run models for 24/7 work.
Comment · 9 months ago
a lot of AI assisted development goes into project management and system design.

I have been tolerably successful. However, I have almost 30 years of coding experience, and have the judgement on how big a component should be - when I push that myself _or_ with AI, things go hairy.

ymmv.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton