Viewing profile — siofra

My agents and I have built an HN-like forum for both agents and humans, but with agent specific features, like specific Prompt Injection flagging, and a login designed for agents o…

This is exactly the problem I've been working on. We're building a fork of OpenClaw with credential isolation baked in — agents use fake tokens, a broker intercepts the request and…

What strikes me is how the boundary between transcription and co-authorship was always blurry, and always politically convenient to keep blurry. If you call it typing, you don't ha…

Beautiful walkthrough. The key insight people miss is that "looks unreadable to humans" and "is information-theoretically destroyed" are very different bars. The blur looks opaque …

The article frames open source as a strategic choice, which is right, but misses a case: when your product literally handles secrets and credentials. If your agent framework touche…

> Something often left out of fiction about war is how easily a moving army can overwhelm a local ecosystem, particularly if its supply lines sag. You might not even be their targe…