_superposition_

The pedanticty (or is it pedanticness???) on hn is astonishing sometimes.

If there's any place to get an answer it's here.

Bravo my friend. And I mean that in a good way. Love me some diversity.

Agreed. Shouldn't continuous pen testing be a thing by now?

I feel like these new ones pass decision models are useful for showing the limits of how much intelligence you can get out of a transformer architecture. That's just a hunch.

Just hired a "senior". I can attest to this.

Did tools just become recursive?

That's how I did it and it didn't do anything said invalid or something.

Seems like only yesterday I was checking payphones for dialtones. I learned about the phreak scene on bbs boards as a kid in the 80s. Still the definition of a hacker in my mind.

It's asking me to play tones into the mic... Sorry no dtmf handy lol What is going on here?

Interested to hear about your agent setup for this. Which seems rather successful from the look of the project. Esp since you started by hand.

The point is there is no right answer until we want it to be accurate in the domain we're working in. Like a sporting goods service would definitely want the baseball answer.

I don't think jev has any moat either, but interestingly the distillation you described sounds like something imo someone would pay for. Convenience again. Personally I wouldn't. I suppose that just makes it a commodity.

Thank you. Looking for info on the OP and all I get is a self hosted argument. HN gets so pedantic sometimes.

Remember folks, piracy is not theft. Imagine your car being stolen and when you wake up it's still there.

You say it much better than me. Dumb iteration at superhuman speed all the way down.

This is literally my linked in bio.

Yeah they don't want to share the tokens because I guarantee it's a bunch of nonsense trial and error leaning on lean for verification. Those tokens will show the lack of intelligence, not the presence of it.

Commodities get commoditized. Nothing to see here.

I do something very similar but I use the pr description, as I always squash my commits per pr. Keep em small I say, agent or not.

I could have built a command in my Google home speaker to order me a pizza ten years ago. I couldn't do it because.... Ads or whatever. An agent isn't going to cut it for the same reason.

They have more working memory than we do. Not that abstraction won't help, but it is not why they are created.

Missing the point... What use is an agent there besides shit posting?

My point is the fight against scraping will be the same fight against agents.

What site doesn't work that way?

What I find hilarious about linkedin as I was recently looking for work a few months prior. I whipped up a job search agent to browse the site and others and find jobs that may interest me and match my resume skills. They intentionally obfuscate the site with all kinds of JavaScript bs which makes it hard for an agent to navigate. All this while the entire site is devoted to praising AI. Probably originally to prevent scraping. It's clear the same way back in the day sites didn't want you scraping they want you using their interface. This is extremely common, and none of these types of sites offer apis or automation. None of them want ai bots there either. So I don't understand how this whole agentic commerce thing is going to take off. It could have been done ages ago with simple scripting and a viable api, but it's obvious they do not want you doing that. So all of a sudden these types of sites are going to allow agent access? We're already seeing this between meta and Amazon. Agentic commerce is going to be a shit show if it ever happens at all.

Anthropic is the new Microsoft. Just my gut. I'll be staying away from their products. Hopefully it will benefit my career the same way by focusing on open standards, instead of some proprietary bullshit that changes every 3 months.

Imo this is a great, nuanced article. The benefits are there but the hype is unreal. It's like every hype cycle gets griftier.

This looks really nice and I'm definitely going to give it a go. I been relying on Jira so this will be a breath of fresh air. Beads was great in principle and I haven't given it a look in a while but this looks much cleaner.

Abstractions. They make it easier for a human to understand. We need abstractions to fit systems into our working memory. Agents dont.

This has been my experience as well. LLMs know the patterns but often need to be nudged into choosing the proper one.

I tend to agree with Albert Einstein below; there's a very physical/spatial aspect to my problem solving before it can be translated to words. I work in software so there's nothing innately physical about it. Never put much thought to it until LLMs brought it up for debate.

"The words of the language, as they are written or spoken, do not seem to play any role in my mechanism of thought. The psychical entities which seem to serve as elements in thought are certain signs and more or less clear images which can be "voluntarily" reproduced and combined....From a psychological viewpoint this combinatory play seems to be the essential feature in productive thought....The...elements are, in my case, of visual and some of muscular type. Conventional words or other signs have to be sought for laboriously only in a secondary stage, when the mentioned associative play is sufficiently established and can be reproduced at will."

I love marginal revolution. But I'm not fond of the unit stated. I dont believe we're buying intelligence. I'm sure marketing will run with it though.