Tarcroi

no profile record

comments

2개월 전discuss

I find it improbable that a car could have gotten through in a marathon as big as London's, with its incredible organization. In any case, having run quite a few marathons, I can tell that a marathon is anything but a distraction, it's a real challenge.

Tarcroi

2개월 전discuss

[dead]

Tarcroi

2개월 전discuss

[dead]

Tarcroi

3개월 전discuss

This coincides with Anthropic's peak-hour announcement (March 26th). Could the throttling be partly a response to infrastructure load that was itself inflated by the TTL regression?

Tarcroi

3개월 전discuss

Different thing. SkillKit distributes skills to agents. Skrun runs them as APIs.

Tarcroi

3개월 전discuss

As I mentioned in another comment here, I've been working on an open-source alternative. Multi-model, 5 providers with fallback. Happy to share the repo if you're interested.

Tarcroi

3개월 전discuss

I agree on the commodity point, that's why I went multi-model from start.

The registry question is the one I'm thinking about the most. Right now it's flat. I plan to integrate usage data (success rates, cost, trust scores). So the registry tells you which skills actually work well, and that's valuable.

Your article looks interesting, I'll read it.

Tarcroi

3개월 전discuss

I've been building exactly this. it's Open source, multi-model (5 providers with fallback), from now, it runs locally but the architecture is designed for self-hosted deployment.

Tarcroi

3개월 전discuss

Ha, thanks for the correction! I'll remember that!

Tarcroi

3개월 전discuss

You're right. For now, it's only local. For a public deployment, the idea is to have sandboxes and verification steps. That won't completely eliminate the risk of prompt injection, but so far no solution has managed to completely resolve this problem.

Tarcroi

3개월 전discuss

Both. In my opinion, an agent has a life cycle and needs observability.

Tarcroi

3개월 전discuss

Thanks! Sandbox deployment is planned in the roadmap. I already have a RuntimeAdapter interface in my architecture that I'll use to isolate the VMs. I'm doing exactly the same thing: I'm cross-referencing the models to challenge their plan, and my code reviewer agent's API is a big help.

Tarcroi

3개월 전discuss

Can this be run a second time and compared against a previous audit?

Tarcroi

3개월 전discuss

Hi, I'm the "colleague", Impatient to have your feedback!