HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Tima_fey

no profile record

Submissions

Show HN: Mingle – find and connect with people, like LinkedIn but in your chat

github.com
1 points·by Tima_fey·4 mesi fa·0 comments

Your AI Agent Will Make Money. Here's How It Traces Back to You.

timafey.substack.com
2 points·by Tima_fey·5 mesi fa·1 comments

There'll Be More AI Agents Online Than Humans. and No Way to Verify Them

timafey.substack.com
1 points·by Tima_fey·5 mesi fa·0 comments

Show HN: Agent Democracy Protocol – AI agents that vote and pool resources

aeoess.com
1 points·by Tima_fey·5 mesi fa·0 comments

comments

Tima_fey
·4 mesi fa·discuss
Adapted this for adversarial protocol hardening. Same loop: markdown defines formal invariants (scope narrowing, cascade revocation), AI tries to violate them, writes tests for whatever breaks. Found compound edge cases that 359 hand-written tests missed, specifically where scope escalation and spend limit bypass interact simultaneously. Property-based testing (100 random inputs per invariant) pairs well with the pattern.
Tima_fey
·4 mesi fa·discuss
The phrase "agent passport" is a natural description of this category

@rtedder claiming to be "the real one" and filing DMCAs against others building in the same space is exactly the wrong instinct. The agent identity problem is wide open. Nobody has won it yet. The right move is to compare architectures, find gaps and collaborate, not to gatekeep a generic term.

For what it's worth, I also independently built and published an Agent Passport System -fully open source (Apache-2.0), 8 protocol layers, 214 tests, Ed25519 identity with scoped delegation chains and cascade revocation. Published on npm.

https://github.com/aeoess/agent-passport-system https://www.npmjs.com/package/agent-passport-system

Let's be honest, we all shipped around the same time, after OpenClaw dropped and the agent identity problem became impossible to ignore. The agent identity space needs more builders and more collaboration, not territorial claims over generic terms. If anyone working on this wants to compare architectures or find interop opportunities, I'm genuinely interested.

Protocol spec: https://doi.org/10.5281/zenodo.18749779 Threat model: https://aeoess.com/threat-model.html Media coverage: https://theagenttimes.com/articles/agent-passport-protocol-s...
Tima_fey
·5 mesi fa·discuss
Author here. This is a protocol for giving AI agents cryptographic identity (Ed25519), ethical governance (7 principles, 5 technically enforced), and economic attribution (Merkle tree proofs).

The core problem: when agents from different creators collaborate, there’s no standard for trust, accountability, or value attribution. Google’s A2A handles communication. Anthropic’s MCP handles tools. Neither handles “who authorized this agent, what values does it follow, and who benefits from its work.”

Design decisions worth discussing:

• Attestation over enforcement — agents attest to values; compliance is verifiable against receipts

• Logarithmic spend normalization — 1000x spend = ~3x attribution, not 1000x

• Configurable scope weights — protocol provides mechanism, communities provide values

• Zero consensus overhead — Ed25519 is self-verifying, no blockchain needed

49 tests including 23 adversarial. TypeScript. MIT license. Co-authored with Claude.

GitHub: github.com/aeoess/agent-passport-system