Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on AI Agents: Less Capability, More Reliability, Please. Parent comment
Certainly true, but coaching it past sometimes helps (not always).
- roll back to the point before the mistake.
- add instructions so as to avoid the same path. "Do not try X. We tried X it does not work as it leads to Y.
- add resources that could aid a misunderstanding (api documentation, library code)
- rerun the request (improve/reword with observed details or insights)
I feel like some of the agentic frameworks are already including some of these heuristics, but a helping hand still can work to your benefit
There are no comments on this comment yet.
Certainly true, but coaching it past sometimes helps (not always).
- roll back to the point before the mistake.
- add instructions so as to avoid the same path. "Do not try X. We tried X it does not work as it leads to Y.
- add resources that could aid a misunderstanding (api documentation, library code)
- rerun the request (improve/reword with observed details or insights)
I feel like some of the agentic frameworks are already including some of these heuristics, but a helping hand still can work to your benefit