sunleash

Reverse engineered how auto mode works in CC.

If you're using yolo mode, this is a no brainer upgrade.

The model first classifies the safety of the command in isolation, no thinking involved. Sonnet 5. Goes to second stage only if it's likely unsafe, in which case the model next considers your intent (Your prompt, CLAUDE.md and any answers to the questions).

The model doesn't receive the full transcript to reduce surface area of the prompt injection. It mostly receives your prompts and main model's tool use blocks. So any text in files, website fetch or bash command output doesn't influence the decision in anyway.

However, CC puts a lot of trust in main model still. For example, `npm install` will always be classified as safe by the auto-classifier, it's upto the main model to ensure that the packages.json isn't poisoned in someway by first reading it.

Reliance on safety of the main model is the reason that Auto mode is NOT available with Haiku as the main model.

The protocol felt unnecessarily complicated till I saw this

https://modelcontextprotocol.io/docs/concepts/sampling

It's crazy. Sadly not yet implemented in Claude Desktop client.

I don't see any results, it'd be more impactful and convincing if there were numbers supplementing the theory. It's not that hard to finetune existing LM on a small data and verify that it works.

I am, however, of the similar opinion that there could be better attention formulations. A paper from 2020 https://arxiv.org/abs/2005.09561 helped a lot in one of the transformers model I trained (not a vanilla LM but a specialised multi-modal graph problem).

It proposes normalised attention which if I'm not wrong should help with the quantisation problem too.