Agents
feels right. once implementation gets cheap, the leverage moves into review and guardrails. e.g. specs, constraints, tests, hooks. otherwise…
feels right. once implementation gets cheap, the leverage moves into review and guardrails. e.g. specs, constraints, tests, hooks. otherwise it's mostly just generating more work for humans to fix up
feels right. once implementation gets cheap, the leverage moves into review and guardrails. e.g. specs, constraints, tests, hooks. otherwise it's mostly just generating more work for humans to fix up later.
Related
- New Guide: Incorporating human judgment in the agent improvement loop Building agents is hard. Everyone talks about the code. What gets less…
- tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheate…
- For once I actually agree with the constructive argument here. There are more approaches that allow you to own your own destiny. Memory is j…
- managed agents are the right form factor but the lock-in is real if your agent harness lives inside a model provider, you dont own the memor…
- For anyone building agentic workflows: the real bottleneck isn't the model, it's the harness. Open standards are a must, not just for flexib…
Source: Harrison Chase (X) | 2026-04-12