# ai evals (audio feeds) — RSS Amplifier

Recent posts from the 1 feeds in the RSS Amplifier directory that cover ai evals.

Page: <https://rssamplifier.com/topics/ai-eval/audio>  
Feed: <https://rssamplifier.com/topics/ai-eval/audio.md>

---

## [If Developers Build on Chinese Open-Weight Models, Who Leads AI?](https://hugobowne.substack.com/p/open-weight-ai-is-becoming-infrastructure)

_2026-08-03 · Hugo Bowne-Anderson · Vanishing Gradients_

Sebastian Raschka on Kimi K3, DeepSeek V4, local coding agents, and why open weights preserve an alternative when access or pricing changes.

[Listen](https://api.substack.com/feed/podcast/209597461/0ca5a4452a19b5e3759e6a5f8c247c64.mp3)

## [How to Build an Effective Agent Harness](https://hugobowne.substack.com/p/how-to-build-an-effective-agent-harness)

_2026-07-28 · Hugo Bowne-Anderson · Vanishing Gradients_

Start with the job, add only the runtime machinery it needs, and retest your assumptions when the model changes

## [Four Months Inside a Production AI Agent: What Real Users Changed](https://hugobowne.substack.com/p/four-months-inside-a-production-ai)

_2026-07-25 · Hugo Bowne-Anderson · Vanishing Gradients_

Maven Clinic's William Horton on 100% rollout, unexpected user behavior, model switching, evals, and rebuilding the harness around what production revealed

[Listen](https://api.substack.com/feed/podcast/208423122/2ddac69fd1084f49480c4cc3b558cb2e.mp3)

## [What do you build when the models keep changing?](https://hugobowne.substack.com/p/are-better-models-making-agent-engineering)

_2026-07-22 · Hugo Bowne-Anderson · Vanishing Gradients_

Sebastian Raschka on the latest models, Nicolay Gerold on shrinking coding-agent harnesses, Chip Huyen and Tim Hopper on agent skills, plus two free lessons and a hands-on workshop next week.

## [Stop Overengineering Your Agent Harness](https://hugobowne.substack.com/p/stop-overengineering-your-agent-harness)

_2026-07-21 · Hugo Bowne-Anderson · Vanishing Gradients_

Coding agents dominate the conversation, but the harness your agent needs depends on its action and context complexity. Here’s how to build for the job in front of you.

## [Building an Enterprise AI Agent for Healthcare](https://hugobowne.substack.com/p/building-an-enterprise-ai-agent-for)

_2026-07-17 · Hugo Bowne-Anderson · Vanishing Gradients_

Harnesses, Prompts, Evals, Tools, and Trust

[Listen](https://api.substack.com/feed/podcast/207380879/47c3dd1d1ebb5381dbf4fc48fe29dd78.mp3)

## [LLM Architecture in 2026: Agent Harnesses, Hybrid Models, and Why Implementation Does Not Lie](https://hugobowne.substack.com/p/llm-architecture-in-2026-agent-harnesses)

_2026-07-15 · Hugo Bowne-Anderson · Vanishing Gradients_

Sebastian Raschka on inference scaling, agent harnesses, hybrid architectures, fine-tuning economics, and how open models spread ideas across the AI ecosystem

## [What Claude Fable Means for Coding Agents](https://hugobowne.substack.com/p/what-claude-fable-means-for-coding)

_2026-07-08 · Hugo Bowne-Anderson · Vanishing Gradients_

Stop Writing Python for AI Engineering & Embrace TypeScript 🤗

[Listen](https://api.substack.com/feed/podcast/206015301/b5826576d246c579653cca42aac659c9.mp3)

## [Benchmarking AI Agents for Real Data Science](https://hugobowne.substack.com/p/benchmarking-ai-agents-for-real-data)

_2026-06-30 · Hugo Bowne-Anderson · Vanishing Gradients_

What Happened When 150 People Used AI Agents to Answer Real Questions Across SQL Tables, Log Files, and 750,000 PDFs

## [Install Manifest V3 Extension (Sponsored)](https://crawlproof.com/a/6ks4O9nleLea)

_2026-06-30 · **Sponsored**_

Get this Manifest V3 extension from the official TronBrowser Store listing.

## [Forget Agent Skills](https://hugobowne.substack.com/p/forget-agent-skills)

_2026-06-16 · Hugo Bowne-Anderson · Vanishing Gradients_

Everything we’re learning from builders who use agents every day: workflows, harnesses, review loops, and production-ready systems.