Towards Data Science

Water Cooler Small Talk, Ep. 12: Byzantine Fault Tolerance

How do you make decisions when you can't trust anyone in the room? The post Water Cooler Small Talk, Ep.

Towards Data Science
Aug 20

The LLM Judge That Kept Agreeing With Itself

The article recounts a production incident where a large language model (LLM) was used to evaluate the outputs of another LLM, and the judging model consistently agreed with itself. It explores the implications of relying on one model to assess another’s work, highlighting the potential pitfalls of such an approach. The narrative offers lessons on the limits of trusting automated evaluation systems in real‑world deployments.

By Priyansh Bhardwaj
Towards Data Science
Aug 18

Building Enterprise Agent Systems that People can Trust, Verify and Improve

The article outlines five principles that guide the successful deployment of enterprise agent systems, illustrated with a real-world example from a $100M+ company. It explains how these principles help ensure that such systems can be trusted, verified, and improved over time. The post serves as a practical guide for building reliable agent-based solutions in production environments.

By Sheila Teo
Hugging Face Trending Papers
Jun 24

Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem

As autonomous AI agents increasingly transact across organizational boundaries, a fundamental trust challenge emerges: how can an agent assess whether an unknown counterpart is trustworthy? The ERC-8004 protocol addresses this challenge with the first permissionless trust layer for AI agent economies, built around three on-chain registries for Identity, Reputation, and Validation.

Towards Data Science
Aug 25

Hallucinations, Watermarks, Removers, and a Squeezed Balloon

The article discusses how watermarks function during moments of uncertainty in AI models, paralleling safety checks that identify mistakes. It examines the roles of hallucinations, watermarks, and removal techniques in ensuring model reliability. The piece also touches on the metaphor of a squeezed balloon to illustrate constraints on model output.

By Javier Marín Valenzuela
Towards Data Science
Jul 15

Don’t Let Claude Grade Its Own Homework

Cross-provider PR review with Codex in GitHub Actions, and why a second opinion from a different lab beats any self-review The post Don’t Let Claude Grade Its Own Homework appeared first on Towards Data Science .

By Ruben Broekx