rando77

This is my answer put the randomising exploration in your preference

https://claude.ai/public/artifacts/d12af7c5-3eb0-4218-a505-e...

People might not want to be on update treadmill of proprietary weight models, for enterprise things. Things change a lot between models and they can't guarantee backwards compatibility like you can for deterministic software

if there were nerd oases I would expect more second order impacts. More nerd organisations springing up as if from nowhere.

Why didn't they build a nerd oasis somewhere?

And HN isn't it...

I think there is a rich seam of work for computers to help humans spot when there are anomalies in the hypotheses humans hold that can help humans form the corrections to hypothesis that fit our aesthetic sensibilities

It's worth taking actions that take large scale job losses due to AI in the future into consideration, even if now is not the time

It's important to have good feedback at each stage of iteration

I've thought of a service that scans new websites and GitHub repos and looks for things that don't look like anything else (using something like hdbscan for outlier detection), and creates a feed for people to follow.

One example of something that might fit the loose forest civilisation mold is a social network that faceted on ML derived topic.

This would allow niches to exist, without people being able to post off-topic things to your feed.

Or maybe it won't. If it can be made efficient like humans it might be at the edge mainly.

Have you come across the lethal trifecta [1]? I'm interested in decomposing tasks to avoid any agent doing all three and having limited data pipes between them.

[1] https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

I've been leaning towards multi agent because sub agent relies on the main agent having all the power and using it responsibly.

You might want some compute in space that you know is very hard to physically interfere with.

But general purpose compute no

I think it is great for experimenting, and proving concepts. Alphas and personal projects, not shipped code.

I've been working on wasm sandboxing and automatic verification that code doesn't have the lethal trifecta and got something working in a couple of days.

I'd like to do a clean rewrite at some point.

I'm interested in capability based software, with tools to identify the lethal trifecta.

This seems like a very hard problem with coding specifically as you want unsafe content (web searches) to be able to impact sensitive things (code).

I'd love to find people to talk to about this stuff.

I've wondered if LLMs can help match people. People give the LLM some public context about their lives and two LLMs can have a chat about availablity and world views.

Use AI to scaffold relationships not replace them.

Fair, I don't know how valuable it would be. I think LLMs would only get you so far. They could be tried in games or small human contexts . We would need a funding model that rewarded this though.

That is hard too though.

I'm not sure. We can use LLMs to try out different settings/algorithms and see what it is like to have it on a social level before we implement it for real.

Perhaps we need reputation on the network layer? Without it being tied to a particular identity.

It would require it not to be easy to farm (Entropy detection on user behaviour perhaps and clique detection).

I've been thinking about using LLMs to help triage security vulnerabilities.

If done in an auditably unlogged environment (with a limited output to the company, just saying escalate) it might also encourage people to share vulns they are worried about putting online.

Does that make sense from your experience?

[1] https://github.com/eb4890/echoresponse/blob/main/design.md

Echoresponse - a tool for responsible disclosure. Security Researchers and companies encode some of their secret knowledge in LLMs and the LLMs have a discussion and can say one word from agreed upon list back to the party that programmed them.

Sounds like they need another agent to detect false positives (I joke, I joke)

There is strong reason to expect evolution to have found a system that is complex and changing for its control system, for this very reason so it can't get easily gamed (and eaten).

A simple tool to host files on a captive portal on a raspberry pi Pico 2 W.

I'm hoping for "a what does this error mean" type knowledge base.

But man pages and the like are crucial too.

With an attitude like that they don't

I think there is appetite for different ways of making software. Open source is hard to make profitable and closed gives the developer too much control. Especially for things like AI. Whether reputation based is the way to go I'm unsure. I'd like to figure out principled ways of coming up with software licenses, that lead to thriving software ecosystems

I'm expecting a market place of reputation tracking systems to be useful and developers would pick and choose which ones they trusted to hand out licenses

Unbounties is a project I've just started to work on to encourage people to work on a topic creatively.

Ideally it should be something they would want to do normally with the possibility of winning a prize giving them extra motivation.

Currently I'm just using a git based way of recording unbounties.

Ideas that you are not sure should be widely disseminated. Historically alchemy had a hermetic tradition where concepts were obscured or only spread to other alchemists that agreed not to spread things.

Hence the term hermetic seal etc. I'll try and make that more obvious without breaking the seal