151–160 of 249 posts
This misses that agentic LLMs are trained via RL to use specific tools. Adding custom tools is subpar to those the model has been trained with. That's why Claude Code has an advantage, over say, Cursor, by being vertically integrated.
Earlier quoted context omitted.
I'm unsure of its accuracy/provenance/outdatedness, but this purportedly extracted system prompt for Claude Code provides a lot more detail about TODO iteration and how powerful it can be: https://gist.github.com/wong2/e0f34aac66caf890a332f7b6f9e2ba... https://gist.github.com/wong2/e0f34aac66caf890a332f7b6f9e2ba... I find it fascinating that while in theory one could just append these as reasoning tokens to the conte…
aren't the system prompt of Claude public in the doc at https://platform.claude.com/docs/en/release-notes/system-pro... ?
It is a bit weird why anthropic doesn't make that available more openly. Depending on your preferences there is stuff in the default system prompt that you may want to change.
I personally have a list of phrases that I patch out from the system prompt after each update by running sed on cc's main.js
There's a bit more to it! For example, the agent in the post will demonstrate 'early stopping' where it finishes before the task is really done. You'd think you can solve this with reasoning models, but it doesn't actually work on SOTA models. To fix 'early stopping' you need extra features in the agent harness. Claude Code does this with TODOs that are injected back into every prompt to remind the LLM what tasks rem…
Since one of the replies asked for an example: the agent works for a bit and just stops. We’ve all seen cases where the agent simply says “ok, let me read the blah.py to understand the context better”, and just stops. It has essentially forgotten to use a tool for its next edit or read etc.
Yea.. our startup greatly overestimated how hard it is to make a good agent loop. Handling exit conditions, command timeouts, context management, UI, etc is surprisingly hard to do seamlessly.
For reciprocity, I work at Imbue, and we can also attest to the real work complexities of this domain.
This is cool but as someone that's built an enterprise grade agentic loop in-house that's processing a billion plus tokens a month, there are so many little things you have to account for that greatly magnify complexity in real world agentic use cases. For loops are an easy way to get your foot in the door and is indeed at the heart of it all, but there are a multitude of a little things that compound complexity rath…
Earlier quoted context omitted.
aren't the system prompt of Claude public in the doc at https://platform.claude.com/docs/en/release-notes/system-pro... ?
The system prompt of claude code changes constantly. I use this site to see what has changed between versions: https://cchistory.mariozechner.at/ It is a bit weird why anthropic doesn't make that available more openly. Depending on your preferences there is stuff in the default system prompt that you may want to change. I personally have a list of phrases that I patch out from the system prompt after each update by r…
Is this correct, and if so do we need to be concerned about user privacy and security?