Hacker News: padolsey

New comment by padolsey in "Caveman: Why use many token when few token do trick"

padolsey — Sun, 05 Apr 2026 14:24:36 +0000

This is fun. I'd like to see the same idea but oriented for richer tokens instead of simpler tokens. If you want to spend less tokens, then spend the 'good' ones. So, instead of saying 'make good' you could say 'improve idiomatically' or something. Depends on one's needs. I try to imagine every single token as an opportunity to bend/expand/limit the geometries I have access to. Language is a beautiful modulator to apply to reality, so I'll wager applying it with pedantic finesse will bring finer outputs than brutish humphs of cavemen. But let's see the benchmarks!

New comment by padolsey in "Day 1 of ARC-AGI-3"

padolsey — Fri, 27 Mar 2026 07:19:23 +0000

Knowing the nature of a test ahead of time, building out your capabilities and tooling before entering the exam hall when your peers don't have that advantage, makes you a cheater.

New comment by padolsey in "HyperAgents: Self-referential self-improving agents"

padolsey — Fri, 27 Mar 2026 06:26:31 +0000

If true, this is essentially what Dspy does https://github.com/stanfordnlp/dspy (it was made back in 2023)

New comment by padolsey in "Why craft-lovers are losing their craft"

padolsey — Sun, 22 Mar 2026 03:34:11 +0000

Precisely. I dare say software developers bemoaning this new world don't realise that they - too - are supplanters of a prior world. A sweet irony.

New comment by padolsey in "Why craft-lovers are losing their craft"

padolsey — Sun, 22 Mar 2026 03:31:30 +0000

Does it have to be mutually exclusive? On-the-fly software does not destroy software. Gatekeeping software creation does not mean shoving the existing creators out, it just means creating a larger space that others can occupy, like when 'real' programmers had to slowly permit 'script kiddies' into their spaces. All feels a bit 'old guard' vs 'new guard'.

New comment by padolsey in "Why craft-lovers are losing their craft"

padolsey — Sun, 22 Mar 2026 03:22:34 +0000

There is indeed a painful dissonance here. I like this new world, but feel sorrow for the loss of something. I try to remember how empowering AI is. It is already allowing millions of people to finally use the devices they've been sitting in front of all these years. No longer do they have to feel constrained by software creators who have made choices for them. Now it is their tool through-and-through, and they can construct software on-the-fly to match their needs precisely. They have been buying computers with both hands tied behind their backs. Now they are in control.

New comment by padolsey in "MoD sources warn Palantir role at heart of government is threat to UK security"

padolsey — Mon, 16 Mar 2026 14:16:10 +0000

Can anyone familiar with the technology help disillusion naive people like me as to why on earth palantir needs to exist? It feels like a big pile of nothing. But tbf that's how I feel about Salesforce and Jira too. Big fat database schemas with big fat CRUD atop and layers of snazzy sparklines to make PMs and clients feel nurtured and fuzzy that they've done something material.

New comment by padolsey in "3D-Knitting: The Ultimate Guide"

padolsey — Thu, 12 Mar 2026 13:48:57 +0000

Yep :/ There are just no good heuristics left for quality clothing. It's horrible. One thing I do genuinely have good experience with is Japanese denim. But that's about it.

New comment by padolsey in "Hardening Firefox with Anthropic's Red Team"

padolsey — Sat, 07 Mar 2026 01:51:38 +0000

My approach is that, "you may as well" hammer Claude and get it to brute-force-investigate your codebase; worst case, you learn nothing and get a bunch of false-positive nonsense. Best case, you get new visibility into issues. Of _course_ you should be doing your own in-depth audits, but the plain fact is that people do not have time, or do not care sufficiently. But you can set up a battery of agents to do this work for you. So.. why not?

New comment by padolsey in "747s and coding agents"

padolsey — Sun, 01 Mar 2026 08:30:52 +0000

> I work in software and for single line I write I read hundredths of them.

I'm not sure whether this should humble or confuse me. I am definitely WAY heavier on the write-side of this equation. I love programming. And writing. I love them both so much that I wrote a book about programming. But I don't like reading other peoples' code. Nor reading generally. I can't read faster than I can talk. I envy those who can. So, reading code has always been a pain. That said, I love little clever golf-y code, nuggets of perl or bitwise magic. But whole reams of code? Hundreds upon hundreds of lines? Gosh no. But I respect anyone who has that patience. FWIW I find that one can still gain incredibly rich understanding without having to read too heavily by finding the implied contracts/interfaces and then writing up a bunch of assertions to see if you're right, TDD style.

New comment by padolsey in "OpenAI agrees with Dept. of War to deploy models in their classified network"

padolsey — Sat, 28 Feb 2026 06:55:09 +0000

Not a group per se but I maintain an index of 'good' people in tech here, and their contraries - https://goodindex.org

New comment by padolsey in "How do I cancel my ChatGPT subscription?"

padolsey — Sat, 28 Feb 2026 06:45:58 +0000

Before you fully delete your account, don't forget to first save your chats! Go to https://chatgpt.com/#settings/DataControls and click Export under "Export Data".

New comment by padolsey in "Why I Joined OpenAI"

padolsey — Sat, 07 Feb 2026 09:40:31 +0000

The AI industry, and SV tech generally, has a pattern of recruiting talent by flattering people's self-image as builders and discoverers, which makes it psychologically very difficult for those people to reckon honestly with downstream harm.

New comment by padolsey in "A new bill in New York would require disclaimers on AI-generated news content"

padolsey — Fri, 06 Feb 2026 11:53:38 +0000

> Because no one believes these laws or bills or acts or whatever will be enforced.

Time will tell. Texas' sat on its biometric data act quite quietly then hammered meta with a $1.4B settlement 20 years after the bill's enactment. Once these laws are enacted, they lay quietly until someone has a big enough bone to pick with someone else. There are already many traumatic events occurring downstream from slapdash AI development.

New comment by padolsey in "A new bill in New York would require disclaimers on AI-generated news content"

padolsey — Fri, 06 Feb 2026 11:08:52 +0000

I'm surprised to see so little coverage of AI legislation news here tbh. Maybe there's an apathy and exhaustion to it. But if you're developing AI stuff, you need to keep on top of this. This is a pretty pivotal moment. NY has been busy with RAISE (frontier AI safety protocols, audits, incident reporting), S8420A (must disclose AI-generated performers in ads), GBL Article 47 (crisis detection & disclaimers for AI chatbots), S7676B (protects performers from unauthorized AI likenesses), NYC LL144 (bias audits for AI hiring tools), SAFE for Kids Act [pending] (restricts algorithmic feeds for minors). At least three of those are relevant even if your app only _serves_ people in NY. It doesn't matter where you're based. That's just one US state's laws on AI.

It's kinda funny the oft-held animosity towards EU's heavy-handed regulations when navigating US state law is a complete minefield of its own.

New comment by padolsey in "The browser is the sandbox"

padolsey — Mon, 26 Jan 2026 10:46:50 +0000

Agree! And this is why it is a bad idea IMHO for agents to sit at the abstraction layer of browser or below (OS). Even at the browser-addon level it's dangerous. It runs with the user’s authority across contexts and erodes zero-trust by becoming a confused deputy: https://en.wikipedia.org/wiki/Confused_deputy_problem

New comment by padolsey in "New YC homepage"

padolsey — Sat, 24 Jan 2026 01:02:25 +0000

Yeh I don't think there's much value in a credo if it celebrates Altman. He's a terrible idol to have. He compared Trump to Hitler in 2016, then donated $1M to his inauguration and tweeted about being in an "NPC trap" when he criticized him. Took about six weeks after the election to flip. Testified to Congress that AI regulation is "essential," then lobbied against California's safety bill when it actually showed up. His own board fired him for lying to them for years. His safety team leads quit in protest saying safety took a backseat to shiny products. Multiple former colleagues, including the people who left to start Anthropic, describe psychological abuse and manipulation. Claims a $65k salary while sitting on a billion-dollar fortune built through conflicts of interest. He's not a good guy. He's a guy who says whatever serves him in the moment and has left a trail of people warning us about exactly that.

New comment by padolsey in "Reading across books with Claude Code"

padolsey — Sat, 17 Jan 2026 13:12:20 +0000

The incumbants Goodreads and their owner Amazon have indeed done such a poor job at this. Seven years ago I tried creating a basic graph using collaborative-filtering (effectively using our actual reading patterns as the embeddings space instead of semantics [human X likes book Y so likers of Y might like other things that human X has enjoyed]). It works well to this day (ablf.io) but the codebase is so ugly I've not had the bravery to update its data in a couple of years.

Blob Opera, Community Edition

padolsey — Fri, 26 Dec 2025 07:39:03 +0000

Article URL: https://opera.addy.ie

Comments URL: https://news.ycombinator.com/item?id=46390073

Points: 29

# Comments: 4

New comment by padolsey in "After my dad died, we found the love letters"

padolsey — Sun, 23 Nov 2025 11:47:19 +0000

I think it's become a bit of a cliche/clique'y thing amongst a certain population. I don't know its origins (tumblr emo crowd??) but I first encountered it in Silicon Valley. The Collison brothers used to love doing it, as did Altman. I feel it projects a kind of stream-of-thought with an aloofness, like "i dont care enough for correct form. language bends to my unique thoughts. read this if you like, i dont care lol".

All-lowercase comes accross as the text equivalent of a hoodie and jeans: comfortable, a bit defensive against being seen as trying too hard, and now so common it barely reads as rebellion.