I've primarily been testing it by building out my AI tool chaz into an Eidetica-native AI Agent framework for decentralized Agent sessions. It's working surprisingly well, it maps pretty well onto the storage model and it's uncovering issues with Eidetica I need to fix (which was always my primary reason for building it anyways). https://github.com/arcuru/chaz

Separately I'm building OptiMap, a SIMD-accelerated hashmap repo that explores the design space for hashmaps and benchmarks different approaches. This is mostly for my own learning but I'll eventually turn into a blog post. https://github.com/arcuru/optimap

https://wikipedia.org/wiki/Rsync

Sure sometimes they do make bad decisions, but you're welcome to just show up to their board meeting and give them some advice.

I think this statement seems to align with some of the other independent tests of Mythos[1]. It did very well on long agentic work which I expect is what they trained it for, and that requires being able to find these tangential links between loosely related topics in the context window.

[1] I'm mainly referring to https://www.aisi.gov.uk/blog/our-evaluation-of-claude-mythos...

It would be insane to run a full fledged Agent from your own accounts, with the same access as yourself. At the same time running it fully scoped inside a container/VM seemed a little bit too heavy handed to me and the Agent-as-user seems like a better fit for me right now. (I did run my coding agents inside a microVM for a while but ran into a few too many annoyances)

1. Pick a file to seed as a starting place.

2. Ask the LLM (in an agent harness) to find a vulnerability by starting there.

3. If it claims to have found something, ask another one to create an exploit/verify it/prove it or whatever.

4. If both conclude there is a vuln, then with the latest models you almost certainly found something real.

Just run it against every file in a repo, or select a subset, or have an LLM select files with a simple "what X files look likely to have vulns?".

So basically yes, it is that simple. It's just a matter of having the money to pay for the tokens.

1. Forked an existing app that has all the features you listed.

2. Admit they don't really know the language and tech it uses.

3. Said upstream was too slow, but I don't see any(?) PRs from them on upstream besides the 2 that they list in the post. Their fork appears to have an extra 3,000 commits.

I'm not super against them doing this, but it's pretty easy to see why people don't like it. Hell, this is the same group that upgraded one of my side-projects from a few years ago and improved it into their 'baibot' matrix bot, so I wish them all the best. I like people making money from OSS, more power to them.

I'm concerned about the copyright 'washing' this enables though, especially in OSS, and I think the right thing for OSS devs to do is to try to publish resulting code with the strongest copyleft licensing that they are comfortable with - https://jackson.dev/post/moral-ai-licensing/

At least give people the option to start moving away from GitHub to contribute to your project. It will, ultimately, be better for the ecosystem.

Comments URL: https://news.ycombinator.com/item?id=47924460

Points: 1

# Comments: 0

As an ex-googler, the only reason I was comfortable keeping even my personal email there was because I could reach out internally if there was a problem. I left Google, and left gmail behind too.

That's what they did?

Perimeter length = 2*335mm + 2*235mm

Wall height diff = 2mm

Wall width = 1mm

(2*335 + 2*235) * 2mm * 1mm = 2,280 mm^3

I want to pay for CI on my Codeberg projects, but I've been struggling to find something where I can just pay by the minute. I have projects that benefit from large CI runners but my usage is low enough that it makes no sense to host my own.