I heard people say this before. I'm wondering, how do you instruct the LLM to generate the tests? Do you tell it the scenarios that would be covered, or do you just tell it to write tests for the code?
What if the organization who tries to verify sends a request on an app on the user’s iPhone (or whatever device can do the same), and the user scans their face with FaceID to produce a file send to the organization, which will then send that file to Apple to ask if the file represents the right person? I trust Apple so that works for me.
I’d say it’s possible to have creativity when you’re sitting as well. I like to think that’s it’s all about staying active. Reading, diarying, calling a friendind. All of that.
Maybe you can't 100% know what every layer "thinks", if you go through all the layers, you might see a cohesive "thinking" story. So, if there is any information you lose at layer N, you might learn some of it in layer N+1. The masking in the layers is not deterministic so the model can't really consistently lie throughout the layers. It doesn't chose what information we get to inspect. There might be a game of whack-a-mole, but you might get a general sentiment. I think the more layers there are, the more the model itself can hide very nuanced lies (But by that time we'd have a better mind-reading model).
However, I haven't read about it yet. I'm really excited to look into it!
> The core idea is content-dependent selection. For each query, the model selects which parts of the sequence are worth attending to, and computes attention exactly over those positions.
I don't know if this will help for things like understanding code, where the all relevant parts can be the file of 1000 lines that we are analyzing, and where every token is relevant in understanding recursion, loops, function calls, etc.
This sounds like it would be great to do SSA before passing things along to a code model like claude code.
10s of GBs? ( 1,000,000 context * 1,000 vector size ) ^ 2 = 1,000,000,000,000,000,000… oh wow.. I must be miscalculating
What about only storing the conversation and then recomputing the embeddings in the cache? Does that cost a lot? Doing a lot of matrix multiplication does not cost dollars of compute, especially on specialized hardware, right?
I was thinking about the ability of representing different kinds of numbers. Imagine that we had a certain CPU that could process algorithms, and the final output of the algorithm is a number. The CPU has a certain number of operations (At least https://en.wikipedia.org/wiki/One-instruction_set_computer). Then, if the algorithm can be described with an integer (since the algorithm can be described with binary), then... can integers describe Real numbers?
what