alt Hacker NewsI wrote an article on this exact issue (albeit more simpleminded) and I suggested a rudimentary way of tracking provenance in today's agents with "reasoning traces" on the objects they modify.
Would love people's thoughts on this: https://0xmmo.notion.site/Preventing-agent-doom-loops-with-p...
Replies
The original article does a good job of contextualizing the shifting dynamics, but yours turns that into an actionable solution. I've been wondering about this same problem too after having trouble wrangling LLMs to not make hacky solutions or go on wild goose chases.
Do you have a working implementation for this? Just a one-to-one index of files and reasoning traces? I'd like to trace these changes easily back to a feature or technical spec too (and have it change that spec if it needs to? I suppose the spec would have it's own reasoning trace)
If recording object change is important, then have the subject object know one or more recorded “change” objects. An LLM is much more likely to understand a real object modeling pattern, rather than some new non-standard scheme such as you suggest.