I played that game!! Although I was 10 years old and barely knew any English. After some playing, I always got a "go home" note on my windshield, I never found out why.

I was dragging to rotate it before I realized that it was 2D...

Are there really two principal components or is that primarily your choice of visualization?

It's a choice. The layout isn't PCA, it's a force-directed embedding (ForceAtlas2). This acts directly on the directed graph of pages and their links, I think you would need some other representation to do PCA.

You could likely run ForceAtlas2 in 3D or higher and get better clustering fidelity, but that obviously makes visualization harder.

At some point, OpenAI is going to cheat and hardcode a pelican on a bicycle into the model. 3D modelling has Suzanne and the teapot; LLMs will have the pelican.

I don't know. Somewhere in the eighties, people started to complain that no one could understand all the assembly anymore.

yea... but i still had to take that course in college... lol

What if kontext runs under the same user as Claude? Could it in principle inspect the kontext process and extract the key from memory?

If they use the system keyring, it depends on the OS and other details - MacOS, Linux, and Windows all have different implementation tradeoffs.

Could you apply this to speed up cherrypy?

I was initially very excited about this, but looking at the code: https://github.com/yamafaktory/formal/blob/4f95787ceeabb0f09...

To extract properties to verify... you call Claude??

Well, I can understand your frustration, but this is basically a pipeline that takes some code written by an LLM and attempts to prove its correctness using the Lean 4 theorem prover.

How does your reply relate to my comment?

I'm sorry if it was unclear. My comment was just a validation of your assertion. It does use Claude - or any openai compatible LLM - to perform the extraction.

I wanted to ask almost this question, then saw that it is on #1 right now.

My use case is ssh. I would like to stick my private key into a local Docker container, have a ssh-identical cli that reverse proxies into the container, and have some rules about what ssh commands the container may proxy or not.

Does anyone know of something like this?

if you usecase is just about dealing with private key and txn signing why not use any KMS service?

No, more like letting an agent interact safely with an HPC frontend. No cloud, no Windows

...and then your AI deleted the repo? It gives a 404

not sure it ever created it, the account doesn't exist either

Zugzwang!