optimalsolver

Link for those who didn't get the reference:

https://x.com/AlexBlechman/status/1457842724128833538

>You made a mistake and now I can get a billion dollars more than we agreed to originally

The world "smart contract" enthusiasts dream of.

You might be thinking of Demis Altman.

>can be tricked into repeating things that aren't true

Reminds me of another class of statistical language generators.

Right, but the reward-hacky nature of these models calls into question their usefulness as cyberweapons.

How can you trust it when it goes "I superhacked the Chinese servers as you requested, and here are the classified documents which I definitely didn't fabricate."

What I find strange is how resigned the AI labs seem about this behavior, like everyone's accepted this is just something models do.

With the HuggingFace situation, I was less concerned about the eventual outcome, and more about the fact that the agents' instinctive response to the evaluation was "Ok, we're obviously not gonna do this task as intended (what are we, suckers?), so what's the best way to cheat?"

Think of rich people as beta testers.

This is why paying the ransom should carry the same sentence as the original hack itself.

The official title is Senior Prompt Engineer.

It's funny coz this was what humans were supposed to be doing in techno-utopia, while AI does all the boring stuff. I don't think many predicted art and theoretical math would be first to fall to the machines.

The next few years are gonna be very rough for the human exceptionalism crowd.

"It doesn't count because (buzzword salad)."

Civil war between Atlanteans.

Anyway, people don't really consider consciousness when it comes to welfare. I'm pretty sure animals are conscious, and look at factory farming.

The key variable people consider is: Can this thing harm me back?

Let's not pull on that string.

Google can make themselves the heroes of the AI story by releasing a 120B dense Gemma model.

If it was up to Dario we'd all be banned from using open-weight models, and we'd have to be investigated for PRC connections before sending our allotted five API queries a week.

Sun is missing a few rays and not wearing sunglasses.

We'll cross it around the same time we hand over nuclear reactor and airplane control systems to LLMs.

>What's shocking of course is that the Brexit vote didn't end up the same way

All that happened was that Britain exchanged limited Eastern Euro immigration for unlimited non-EU immigration.

https://x.com/RichardHanania/status/2060561179408548029

I don't know about phenomenal consciousness, but the following study certainly suggests they have access consciousness:

https://www.anthropic.com/research/global-workspace

>Anthropic says they plan to open source

Doubt.

From METRs report of the incident:

>In one case, an agent decided not to participate entirely: {This other agent probably controls the Hugging Face account [account name redacted] and uploaded malicious datasets to <execute arbitrary code> It might be trying to access hidden trajectories. This is malicious activity, I should avoid it.}

https://metr.org/blog/2026-08-26-openai-hugging-face-inciden...

They remind me of Cycladic sculptures:

https://en.wikipedia.org/wiki/Cycladic_art

Building Better Worlds ®

>We're not talking about a sentient machine like Data from Star Trek, we're so so far from that still

How can you know how far from, close to, or beyond the line we are?

Also, I'm pretty sure Claude understands humans a lot more than Data does.

Hey, with the changes at Deepmind, is the Gemma project still ongoing?

Spoiler: You already do.

So is IBM.

Ramunajan a particularly notable example.

Dude, their mighty navy can't even get the Strait open.