benban
Scanned 500 AI agent repos for bugs, nobody thinks of infinite loops
Like, an eval will tell you the model gave a bad answer. It won't tell you that your agent passes that answer straight into a shell command, or that a loop has no exit condition and burns through your API budget overnight.
We've been working on this, static analysis that reads agent code and maps out what can go wrong before you deploy. Found issues in ~80% of the repos we scanned.
would be great to get your feedback: https://github.com/inkog-io/inkog
OpenAI Acquires Promptfoo
RFI responses due March 9, concept papers April 2. Moves fast for a federal initiative.
NIST Launches Standards Initiative for AI Agents
Show HN: Inkog – Pre-flight check for AI agents (governance, loops, injection)
Hi HN, I'm a builder.I've been building AI agents for a while now and kept running into the same problems. Agent gets stuck in a loop. Prompt injection sneaks through. No one reviews the dangerous actions. And when you're shipping to production, there's this nagging question: "is this thing actually safe to deploy?"So I built Inkog (inkog.io). It's basically a...
in practice we've had better luck running agents in lightweight sandboxes with explicit capability handles. curious if anyone's tried capability-based systems like sel4 for hosting agents, feels like mainstream oses have a long way to go here.
curious how you're handling context lifetimes when agents call other agents. do you drop context between calls or is there a way to bound it? that's been the trickiest part for us.