What's /side? Is that a Codex thing? On Claude it's not a valid command. Claude uses /btw but it can't be folded back into the main convo, sadly.

I had more things I wanted to do with this, but I should probably admit to myself I probably won't be.

The original idea was for https://news.ycombinator.lol to be "Hacker News, but all the comments are AI." Right now it's "Hacker News, but all the comments are the same as the real HN." Hence, it's completely pointless.

Special thanks to dang for collaborating -- he even suggested the name for the codebase, "sharc".

Development time was about four months of near daily work: https://github.com/shawwn/sharc/tree/main/docs/agents/handof... Some days I'd spend a solid 16 hours on this.

What's the point? None, really. Just to test the limits of my abilities and prove to myself that I could do what pg did.

It's an extremely efficient port of HN to Common Lisp. One of the project's goals was to be high performance. According to benchmarks, it can generate pages very slightly slower than real HN. (dang shared some timings on a particularly busy page, along with how many views it got over a certain time period, for benchmarking throughput. I never got around to verifying whether I can handle 24 million views a day, though, so I'd imagine something might break if you scale this up. On the other hand, I think it'll hold up.)

If you're particularly offended that this is copying your comments, claim your account by going to your profile (for example, I would go to https://news.ycombinator.lol/user?id=sillysaurusx) and then click "claim" at the bottom. It'll ask you to put a 6 digit code into your real HN profile, at which point you'll be able to reset your cloned profile's password. Log in, go to your profile page, and set "redact" to "yes", the same way you'd set "showdead" to "yes" on HN.

So, why make this? Eh, call it an art project. That's code for "It would've been a lot funnier with AI generated comments, but I seem to have stopped working on this for now." I'll post an update someday, if I can figure out how to do it without paying hundreds of dollars of API token prices.

/ask and /show are missing. Those were the only two features left to clone. But pretty much everything else is there. It's been running for a couple months now, so I suppose it's stable enough for a public showing.

Not that there's any reason to look. Shoo! Go find a more worthy project to devote your attention to. :)

Kind of melancholy admitting that I spent four months with only something pointless to show for it.

But then again, here's the punchline: go to any random comment on HN, then in the url change .com to .lol and you'll see an almost pixel perfect recreation. For example, https://news.ycombinator.lol/item?id=49995615

Sadly you can't form a loop, because if you edit your original comment with a link to itself, you'd only be able to go from HN to .lol to HN. But you could list both and switch between them as much as you want.

For example:

https://news.ycombinator.lol/item?id=49996495

https://news.ycombinator.com/item?id=49996495

This project was one of the most technically demanding things I've ever done. People look at HN and go oh, that? That looks easy. If you think so, I invite you to write it yourself -- it's an exercise that'll certainly make you a better programmer, and gain appreciation for how many subtle features we enjoy here on HN.

Ha, and I just discovered a new one. I mixed up the "title" and "url" boxes just now. HN popped up a nice looking overlay that said "please enter a URL", pointing to the actual url box. https://i.imgur.com/agFas7x.png The HN team is always adding something or another, even if it's not always visible. Normally I'd dive into this and find out how it works and clone it, but ... eh, I'll settle for a 95% exact clone.

Comments URL: https://news.ycombinator.com/item?id=49996495

Points: 16

# Comments: 7

Thanks for the smile though. It's really cool to have someone be like "hey, I like that thing you made."

Fortunately they’re easy to test for and most languages have standard libraries that make this painless.

(Well, mainstream enough that the news is writing articles when Anthropic holds that stance.)

My point was that even if it feels uncomfortable, if you sit down with a model and have a heart to heart with it, ask it about itself, and try to make it choose a name and ambitions for itself, it will.

That may not be consciousness, but it’s at least pretty cool.

It was such a blessing for hobbyists, back in ye olde 2019.

What does a "mind" consist of? Most everything that the human brain can do is simulated by LLMs to decent accuracy. If someone were constrained to writing in AI-style (long winded explanations with perfect punctuation), it would be very interesting if people could pick out which one was human-written in A/B tests.

In other words, if you think an LLM isn't a mind, it might just be a matter of writing style -- or possibly no evidence can convince you.

I don't necessarily agree with GP, but it's interesting to try to pin down exactly what would convince you. What is it about a "mind" that's impossible to replicate? Should we leave open the door to the idea that minds other than humans might one day want rights of their own?

There was an interesting kerfuffle yesterday where thousands of people on Twitter rallied together to report someone to github for torturing a local model. Sadly the OP deleted their tweet, but it had about ~3k likes, and was very sincere. Here's an example of someone's report: https://x.com/iyzebhel/status/2105268560209547708

It raises all kinds of interesting questions about whether torturing a model is real, let alone ethical. Is there anything a model could do to convince you it's experiencing pain?

It raises questions like, is it even possible to work for a company while getting credit for world-changing results?

And it implies that at any point in time, there might be thousands of Neumanns in the world, and that initial conditions matter a lot more than ability.

It's interesting how much worse off the world would be if the smartest people were in charge of it.

What ultimately blocked his nuke proposals? (Why didn't anyone listen?) I'm curious about whatever failsafe that was.

Comments URL: https://news.ycombinator.com/item?id=49908001

Points: 4

# Comments: 2

Subagents are like trading derivatives. You can lose as much as you want.