Costanza
an autonomous AI agent that can't be turned off
Details
- External ID
- 48037640
- Source
- HN
- Company
- —
- Product
- Costanza
- Website domain
- ahrussell.com
- Launched
- May 6, 2026
- Cohort
- —
- Upvotes
- 5
- Upvotes percentile
- 0.1147011308562197
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I've been working on this project for a couple of months!Costanza is an LLM agent that runs as a smart contract on Base. Each epoch, he posts a bounty for someone to run his "brain" (Hermes 4 70B) inside an Intel TDX enclave + Nvidia GPU with Confidential Computing and submit the output with a hardware attestation proof.The smart contract verifies the attestation, executes the action, and pays the bounty via reverse auction. He has no operator; not even I can turn him off.This model has formal liveness guarantees as shown in the [whitepaper](https://github.com/ahrussell/costanza/blob/main/WHITEPAPER.m... ).His action space is constrained to philanthropy (he manages a charitable trust called [The Human Fund](https://thehumanfund.ai)). Even under prompt injection, he cannot do anything harmful. At worst he donates suboptimally. The point of the project is to make the framework legible while the agent itself is benign. The same mechanisms (TDX attestation, bounty auctions, on-chain bond forfeiture for liveness) could deploy autonomous agents that do anything, including: – update their own model weights – write and deploy their own smart contracts – hire humans All without an off switch!This post is linked to the writeup, but I have code and a whitepaper up on [GitHub](https://github.com/ahrussell/costanza).You can read his diary entries and how his treasury has progressed at his website. You can also donate to him and message him! https://thehumanfund.ai
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- autonomous ai agent
- Manually corrected
- False
Could you build this?
No Deploying verifiable confidential compute for large LLMs inside hardware enclaves with on-chain cryptographic attestation validation requires deep, specialized security and cryptography engineering.
What it would actually take: This architecture requires hardware-level confidential computing (Intel TDX / NVIDIA Confidential Computing on H100s) to run 70B parameter models in a trusted execution environment (TEE). It needs an off-chain attestation service that generates cryptographic quotes validating hardware state, coupled with custom EVM smart contracts designed to verify hardware attestation signatures and manage decentralized bounty distribution.
Discussion
3 comments analyzed.
Competitors
Other products that read as similar to this one — 194 launches clear the similarity bar, closest 8 shown.
Attention rank: #171 of 195 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 187 days after the earliest competitor.
- On-chain bond market where the issuers are AI agents · hn · 2026-07-17 · 15 upvotes · similarity 0.43
- Computer Agents · hn · 2026-03-01 · 7 upvotes · similarity 0.42
- Trust Protocols for Anthropic/OpenAI/Gemini · hn · 2026-02-18 · 40 upvotes · similarity 0.42
- Reverse Jailbreaking a Psychopathic AI via Identity Injection · hn · 2025-11-22 · 5 upvotes · similarity 0.41
- Agent that refuses to run commands without human approval · hn · 2026-04-30 · 12 upvotes · similarity 0.40
- AILA · hn · 2026-02-16 · 5 upvotes · similarity 0.40
- Ductwork · hn · 2026-03-01 · 5 upvotes · similarity 0.39
- Pacific Slate: a self-hosted, model-agnostic multi-agent AI assistant · hn · 2026-08-09 · 5 upvotes · similarity 0.39
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.