General scales unlock AI evaluation with explanatory and predictive power - Nature A fully automated methodology based on rubrics capturing a broad range of cognitive and intellectual demands is illustrated using LLMs and tasks, demonstrating a new way to evaluate the capabilities of AI systems and anticipate their performance.

Nature research paper: General scales unlock AI evaluation with explanatory and predictive power

go.nature.com/4telRF0

100%

Yeah I understand why they do it, but its a nightmare - esp when the senior author is the only one eligable to do those reviews and becuase of the way computer science publishing works (a few specific confernces/yr) works, they are often multiple submissions to the same conference from the same lab

Does anyone have experience of CFS like symptoms that lasted like 3-4 months then just went away? I wonder if (hope that?) there are a lot of these people but they are invisible as not in support groups / at the dr?

Adiposity, diet or inactivity – which is the culprit in obesity-related memory deficits in human adults? Obesity, diet and physical activity have independently been shown to impact cognition and memory. However, these factors have rarely been considered together in humans, and thus their relative cont...

New Paper Out! This one has been a *long* time in the making, with the data collected over 10 years ago! We found that different aspects of the "obese syndrome" predict different elements of memory performance. www.tandfonline.com/doi/full/10....

we are weeks away from 'Trump attempts to make horse a Senator' and the only thing stopping him is that he is too much of a sociopath to form an attachment to animals

if you told someone they were just like Noah from "Nobody wants this" would they think you were:
a) insulting them
b) flirting
c) calling them ernest and considerate
d) calling them a bit annoying

why are all these skiers so beautiful? like seriously do sponsors only support the hot ones?

whats worse than receiving a grant rejection? having to download an app, and spend 15 minutes trying to FIND the rejection in the world's worst website. thabks Horizon, that was the salt in the wound I was looking for

In my ongoing attempts to give you a break from *gestures widely* THE HORRORS:

Let's talk about the utterly bizarre science of cats' purring.

Here's a weird starting point:
There are NO cats (Felidae) that can BOTH roar AND purr.

Cats that roar = genus Panthera
Cats that purr = genus Felis

Making pretty lecture slides right now feels a little like re-arranging deckchairs on the titanic.

yyyyeah thats not reassurance. Thats threat.

The powerful have their power. We have the capacity to stop pretending, to name reality, to act together | Mark Carney In a speech to Davos, Canadian prime minister Mark Carney lays out the case for unity in the face of Donald Trump’s new world order

The powerful have their power. We have the capacity to stop pretending, to name reality, to act together | Mark Carney

‘The powerful have their power. We have the capacity to stop pretending’: the Canadian PM’s call to action at Davos | Mark Carney In a rousing speech, Mark Carney made the case for unity in the face of Donald Trump’s new world order. We reproduce it here

incredible speech from Mark Carney. Feels like a turning point www.theguardian.com/commentisfre...

“Universities are not a commodity in which quality holds steady regardless of price. Rather, starving the system of overall steady funding means a few winners and a race to the bottom for the others.” today’s @theglobeandmail.com #academicsky #psychscisky #neurosckyence

We need a dedicated website for news stories (mostly about trump) that confirms whether or not they are satire / AI. I am no longer able to distinguish truth from parody.

a cartoon of spongebob holding a letter u and saying " you and me " ALT: a cartoon of spongebob holding a letter u and saying " you and me "

In my defense, I didn't apply for one...

Literally my entire bluesky feed got an ERC consolidator grant.

The future is not in the training set.

crazy

IG em_clarkson

I thought the idea of a sex abuse ring at the highest levels of government was overheated and ridiculous.

I thought Captain America: The Winter Soldier having secret Nazi senators was over the top.

My life has become a single ongoing revelation that I have not been cynical enough

They're going to crash the global economy by attempting to create an artificial general intelligence, despite having no idea what that is, no proof they can build it & no hope of doing so. Cunts just read too many sci-fi books.

EXCLUSIVE: Michael Prescott himself doctored Trump quote in his anti-BBC report A report alleging Panorama broadcast misleading Trump quotes contains misleading quotes itself

The remarkable story we discussed this morning. (No paywall but do consider subscribing.) www.thenewworld.co.uk/james-ball-e...

Loving that a major critique of the tools my lab are producing is "but for this you have to understand the topic really well to be able to build the evaluations for it! unscalable! unrealistic!" Suddenly "you have to know what you're talking about if you want to say something" is contraversial

Job Klaxon!
RA position looking into evaluating AI Agents in data science tasks
www.cam.ac.uk/jobs/researc...

*sigh* must I

I mean what the actual fuck is this

a close up of a man wearing a mask with the words what have you done below him ALT: a close up of a man wearing a mask with the words what have you done below him

me watching the Netflix adaptation of the Twits

Reseachers: Please can we have some money?
HORIZON: www.instagram.com/reel/DNNeyxX...

General interaction battery: Simple object navigation and affordances (GIBSONA) Perception of affordances is an agent’s capability to identify what action-possibilities exist with a particular object or set of objects, based on it…

New Paper out! GIBSONA is a battery of Animal AI tasks evaluating object and affordances understanding - www.sciencedirect.com/science/arti...