zbyforgotp

On the flip side if there is a bug in one of my systems I would rather get a detailed bug report from an llm than a user message “xxx does not work”.

This is so obvious that in practice it doesn’t buy much, but everyone is still propagating that silly news. This is the real malware, a mind virus.

In the limit we want the llm to write the code (like in RLMs).

We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at any depth. I think we need some kind of protocol for that (à la the Cubes OS protocols for cut and paste between vms).

Maybe a workaround could be to use bubblewrap of the scripts ther recursively call the llm (and run the agent in yolo inside the wrap).

The idea is that the spec is somehow compressed in comparison to the code.

You need supporting environment on both sides of the sandbox.

Frontmatter should now be in the markdown standard.

I have been struggling with that. Thanks! Let me reword it - natural language lacks a strict semantics - so also programs for the llm machine ( I.e. prompts) cannot have it. LLMs always have to project from all possible semantics into one (are there any experiments with superpositions?)

What is the root cause of this? It is said that AMD is hardware company and neglects software - but recently they issued lots of declarations of becoming software firs now.

At some point evolving software instead of designing it will work. Now the evolutionary pressure leads towards churning more tokens.

Property is a local low - it applies to a thing that exists in one place. Intellectual property is trying to apply similar rules to stuff that happen remotely - a text is not a thing, and controlling copying might work in some technological regimes while in others would require totalitarian control. When you extend these rules to cover not just copying of texts but also at the level of ideas it gets even worse.