jguarnelli
Show HN: Scan your AI agent's code for tool calls with no checks
Re:Richard Dawkins concludes AI is conscious, even if it doesn't know it
on Sunday May 10, 2026 @02:53PM (#48086684)
What could have caused the execution to fail on the infrastructure side, regardless of what the prompt said?
Re:Show HN: Agent that refuses to run commands without human approval
on Wednesday May 06, 2026 @08:39AM (#48035523)
it's a fair point sandboxing is necessary. But not sufficient for agents that
legitimately need write access. A payment agent needs Stripe. A maintenance agent
needs DB writes. You can't sandbox those away. The missing layer is between has access and executes
Show HN: I scanned 16 AI agent repos – 76% of tool calls had no guards
Re:Collaborate on Large Action Model
on Tuesday August 27, 2024 @05:30AM (#41365779)
Looking for an AI Researcher (ML/AGI/RNNs/NLP/Deep Learning) to collaborate in the field of Large Action Models (LAMs). I'm short on time and need a technical partner to accelerate progress.
Revenue-sharing opportunity. The main objective is to build a community focused on LAMs.
Here are my 2 cents on the topic : https://lnkd.in/e7HmBXz8
DM if you're interested! Sharing Is Caring
P.S.: The integration of Explainable AI in this field is essential to ensure transparency and trust in LAMs.