inspectorSlap

Not a lot that can. LLM proof fonts are spotty at best, I moved my hands up an to the right 3 keys and kept typing and i may as well of changed my font as obfuscated my message.

I have an idea about negative space... where the word are meaningless, but the font choice, paragraph, and word spacing creates messages in the whitespace.

First off, everyone here knows that a cybersecurity vulnerability audit is a hack request, and you don't hack without rolling up your sleeves and digging through the trash first, making a few phone calls, maybe take a lonely guy on a date to get him to say 'my voice is my password'...

Remove the guardrails, give access to the internet, tell it to hack, and get surprised when it does it? Sound likes like a deliberately naive pre-registration on their study to achieve sensational headlines.

I'd say the real headline is that the model almost stopped itself several times because it didn't trust the operator's intent even WITHOUT guardrails - that is a the opposite outcome.

these can work as long as the evidence is attached (to your point). And in healthcare absolutely must (your EMR example is terrifying). The patient may be allergic to nuts (confidence .84) >> cite: 1) lab value X, PRO Y, ... >> otherwise I'm 62% confident I'm an elephant.

I'm working on a universal one. My belief is that as agentic capabilities increase, behavioral attribution will be increasingly needed to maintain quality.

Agreed. However my research is showing that saturation of the rubric occurs in unique configuration that drive the transfer curve to near binary. Effectively turning a 1-10 rating system into yes/no.

Has anyone actually used Grok to code? How does he do?

This is exactly right. Abstracted out of the process, or to a point of most optimal application.

I find some of the most interesting, and catastrophic failures in my agent fine-tuning come from the clamping down of non-determinism. It is totally the correct approach, but must be handled delicately. The non-deterministic core remains, but now under bimodal pressure.

I think stochastic parroting is really a very accurate description of what they do (if underserving of the overall usefulness of LLMs). As long as you consider they are parroting from the whole of human intelligence. Its just that as they have gotten more sophisticated, the amount of gates, guardrails, and tertiary tools add variety. Trace any LLM hallucination back to provenance and you begin to see how the stochastic parrot works.