This article mainly argues around harnesses but a breakthrough for me was understanding why harnesses. Without a harness and only a raw LLM, exploring and modifying codebases is not feasible. It’s just text in, text out, and has no way of handling the context of the codebase (if large enough). Plug an LLM into a harness, and all of the sudden it has an exosuit that lets it funnel its thinking into discrete actions. It can now use strategies to manage that large context in pieces.
I don't know - all of these cache hit rate advocacy is kind of goodhearting. Cache hit rates are less important than the accuracy of LLM answers and people seem to forget about it. For example I've seen articles how sub-agents poison the cache. Sure you can fill up your context with irrelevant data to have high cache hit rate - but that degrades the LLM work - sub-agents are about providing the LLM with a clean context - just the information needed to do its job, no distraction.
All of the main providers now offer cache management that can work with sub-agents - but it was kind of bolted on - and all of them have different apis - so nobody uses them anyway.
The thing that surprises me is that any of the popular harnesses break cache this way. Is it just an artifact of too much LLM code and not enough tests?
It's easy to break the cache and there's a number of very valid usecases (mostly context management such as compaction or tool shaking).
Not to mention that it can be very strategic to break context. E.g, after chasing a bug for a while it does make sense to summarise all the approaches that did not work so that you have more context available for newer approaches.
Getting 99% cache hit rates while providing a good user experience is the hard part!
This article mainly argues around harnesses but a breakthrough for me was understanding why harnesses. Without a harness and only a raw LLM, exploring and modifying codebases is not feasible. It’s just text in, text out, and has no way of handling the context of the codebase (if large enough). Plug an LLM into a harness, and all of the sudden it has an exosuit that lets it funnel its thinking into discrete actions. It can now use strategies to manage that large context in pieces.
Wait until you realize that deep down everything on a computer is text. We juist build "harnesses" to manipulate in-memory "text" in different ways.
One level deeper is all numbers though.
And eventually it's all 0 and 1s!
I don't know - all of these cache hit rate advocacy is kind of goodhearting. Cache hit rates are less important than the accuracy of LLM answers and people seem to forget about it. For example I've seen articles how sub-agents poison the cache. Sure you can fill up your context with irrelevant data to have high cache hit rate - but that degrades the LLM work - sub-agents are about providing the LLM with a clean context - just the information needed to do its job, no distraction.
All of the main providers now offer cache management that can work with sub-agents - but it was kind of bolted on - and all of them have different apis - so nobody uses them anyway.
The thing that surprises me is that any of the popular harnesses break cache this way. Is it just an artifact of too much LLM code and not enough tests?
It's easy to break the cache and there's a number of very valid usecases (mostly context management such as compaction or tool shaking).
Not to mention that it can be very strategic to break context. E.g, after chasing a bug for a while it does make sense to summarise all the approaches that did not work so that you have more context available for newer approaches.
Getting 99% cache hit rates while providing a good user experience is the hard part!