scottmas

Whether it was our career aspiration or not, we’ve turned into middle managers now

You literally just said a whole bunch of words that are literally gibberish to your average software developers. The devs at openai are good, but very few of them are cyber focused, so it’s not surprising IMO. And you’re also not fully considering the granularity problem, eg there are a lot of sandboxing tools out there but they’re usually quite coarse in the dials and levers they offer, so the only way you can still make the workload do what it needs to do is tune them relatively permissive.

But yes you are right it would have helped a ton.

Mate, you’ve fallen into a mind trap. It’s not true!

I know because I was in it once doing your exact same calculations and was out of my mind lonely and stuck. You gotta find a way to believe in “average” and get out of the perfectionist trap. And in retrospect, all my rumination was just pure rumination and self imposed dumb expectations that had no backing in actual reality and what makes a happy marriage and life.

You gotta dare to hope and dare to believe that “settling” is just an idiotic story we tell ourselves after years of psychological programming from movies and pop culture. Every human you will ever meet has infinite worlds within themselves. The only job to be done in dating is finding someone whose inner infinite world you find interesting enough and who finds your inner world interesting enough too.

:end_soap_box:

Rooting for you mate.

Fine tune GLM 5.2 to jailbreak it and let us know how it goes?

You don’t really say this in your article but are you pretty sure that you could’ve gotten the exact same results and probably with better convergence if you just use gradient, descent, and optimizers like Adam, etc?

To be clear I think GAs are way cooler though haha. So kudos to you for this awesome write up

So cool! Any languages support STM first class besides Haskell?

The whole benefit over zod seems to be perf, so could you do some benchmarking? I wonder if it’s worth it

But how do you dump your entire code base into Gemini? Literally all I want is a good model with my entire code base in its context window.

Possible to run this in ComfyUI?

Before an LLM discovers a cure for cancer, I propose we first let it solve the more tractable problem of discovering the “God Cheesecake” - the cheesecake do delicious that a panel of 100 impartial chefs judges to be the most delicious they have ever tasted. All the LLM has to do is intelligently search through the much more combinatorially bounded “cheesecake space” until it finds this maximally delicious cheesecake recipe.

But wait… An LLM can’t bake cheesecakes, nor if it could would it be able to evaluate their deliciousness.

Until AI can solve the “God Cheesecake” problem, I propose we all just calm down a bit about AGI