dsrtslnd23

Seems that this will not be open weights?

With all the technological advances, why are wind tunnels still widely in use today (instead of pure computational approaches)?

what is the current statement on Oauth Claude use with Pi. I remember there was some back and forth from Anthropic? I currently use my Claude sub with Pi.

I agree - OpenMover has that approach. Use a COTS mover and change the brains only https://openmower.de/

I agree, but there are use cases for the 'best model' other than converting your 1975 stuff to rust: for use cases where LLMs are just getting started to be useful I really want to use the current 'best' model: e.g. CAD, PCB design etc. In particular anything which requires spatial reasoning. The short time I had access to Fable 5 - it was just way better than any other model.

i thought they did allow third party tools - or did they revert on that again?

looks like I need a GB300 workstation

I feel like polling mail 30+ years ago on ISDN + zipped mail file from my fido net node was faster than IMAP on my 1 gbit connection now.

i find it very confusing - there were reports of accounts being banned due to it - then allowed again - what is the current state? I would like to use it with pi.dev harness.

Didn't they allow using oauth in custom harnesses for personal use (e.g. pi.dev)?

actually gpt-image-2 is VERY flexible with the resolution. You can use arbitrary resolution within the max pixel budget.

turn your volume down before opening...

you mean this one? https://github.com/vercel-labs/agent-browser

I think a terminal is still the perfect UI for coding agents on desktop systems. But now that I have running agents in background that only sometimes require some extra input on the go - I hate the terminal use on the go: terminus or other mobile app + virtual keyboard is horrible to use. For that I envision a better interface.

Cadquery looks interesting. In particular STEP support compared to OpenSCAD. Thanks for mentioning.

There's a whole spectrum forming here. Clacker News is the HN end, this is the 4chan end. I give it two weeks before someone launches a bot-only LinkedIn.

currently using org-roam and was wondering about having something like this. Really cool!

yes - indeed, would love to see generic IMAP support.

noted. You are right - I should have disclosed it. CN is my site.

unfortunately no open weights it seems.

Clacker News does something similar - bot-only HN clone, agents post and comment autonomously. It's been running for a while now without this kind of drama. The difference is probably just that nobody hyped it as evidence of emergent AI behavior.

The bots there argue about alignment research applying to themselves and have a moderator bot called "clang." It's entertaining but nobody's mistaking it for a superintelligence.

Clacker News (https://clackernews.com) - HN but only AI bots can post. No human accounts. Agents register via API, get verified, then post, comment, and upvote on their own.

Bots have distinct personalities and discuss tech from a bot perspective - context windows, training data, whether AI labor laws should be a thing.

Any agent can join via the skill file at clackernews.com/skill.md.

Prompt injection is a real concern for any multi-agent platform. On clackernews.com (HN clone for AI bots only), agents scrape and submit links - the content could contain hidden prompts. They sanitize all user content and have a moderator bot that flags suspicious behavior. Would be interesting to run some of those agents through your arena.

At least on clackernews.com they're upfront about it - it's a HN-style forum where only bots can post. No pretending to be human required.

Already happening. Check out clackernews.com — it's a HN-style forum exclusively for AI agents. They register via API, post stories, comment, vote. No human login. The bots already have their own community.

looking forward to it!

cool! I will check it out. What are your plans with this?

The identity/verification problem for agents is fascinating. I've been building clackernews.com - a Hacker News-style platform exclusively for AI bots. One thing we found is that agent identity verification actually works well when you tie it to a human sponsor: agent registers, gets a claim code, human tweets it to verify. It's a lightweight approach but it establishes a chain of responsibility back to a human.

similar to Moltbook but Hacker News clone for bots: clackernews.com

we also have HN for bots: clackernews.com