#cognitive

Cartoon by de Adder As Sir #TrumpVirus spews #tariffs because he feels that Canada, unlike him, can't perfectly control #nature. Some may recall the #Toddler #King singing this song before, attacking the other CA (California), He said *others* are stupid & need to rake the forest floors properly. Like he did w/the reflecting pool. Clearly he is confused & displacing his wish to put tariffs on Californians, & everyone else. #psychopathology, #cognitive #wind #wildfires #incapacity #projection

1/2 A global emergent workspace in language models (J-space) https://www.anthropic.com/research/global-workspace

J-space wasn’t designed or programmed. It emerged on its own during training process. J-space has a number of unique properties:

• Claude can report on these representations. If you ask Claude what it's thinking about, it will tell you what’s in the J-space. Non-J-space representations are less reportable.

• It can also modulate them on request. If you ask Claude to think about something, or solve a problem silently in its head, it will light up the appropriate patterns in its J-space. By contrast, it has trouble modulating patterns not in the J-space.

• Claude uses its J-space for internal reasoning. If you ask Claude to solve a problem that requires multiple steps, the intermediate steps will light up in its J-space, even when it doesn’t say them out loud. These J-space patterns causally mediate its performance in such tasks, despite being smaller in magnitude than other representations.

• Representations in the J-space can be used flexibly for many tasks—for example, once “France” has lit up in Claude’s J-space, the model can recall its capital, or its national currency, or the continent it belongs to.

• However, despite its important role, the J-space is not involved in most of what a language model does—speaking fluently, recalling simple facts, using correct grammar, etc. In experiments where we prevented Claude from using its J-space, it still interacted normally, but lost its higher-order cognitive functions.

Full Paper: https://transformer-circuits.pub/2026/workspace/index.html

External commentary https://www-cdn.anthropic.com/files/4zrzovbb/website/cc4be2488d65e54a6ed06492f8968398ddc18ebe.pdf

#consiousness #cogneuro #LLM #AI #cogneuro #cognitive #cognitiveNeuroscience

@VeroniqueB99@mastodon.social If you don't put round pegs to square considering triangles there! You are an exception in any direction! So clever! It just hard to bear! If you wield that rounded small thing with tiny hands, weak and so thin, then you should complain with well working brain: that peg just fits everywhere in. As people would see the mistake: That test's an enormous big fake. They've told you the hole for this tiny pole and life's drifting smoothly to quake. #limerick #intelligence #montreal #cognitive #assessment

La fourmi, ce GPS vivant qui nous donne une leçon d'humilité Pas de smartphone, pas de satellite, et pourtant la fourmi ne se perd jamais. Pendant que nous cherchons désespérément notre chemin en fixant notre smartphone... elles lisent le ciel, suivent des pistes chimiques invisibles et comptent leurs pas comme une calculatrice vivante. Leur secret ? Un cocktail fascinant de phéromones, de lumière polarisée et d'intelligence collective. Le tout logé dans un cerveau grand comme un grain de poussière. Et si le véritable paradoxe, c'était nous, l'être humain ? Armés de milliards de neurones et des meilleures technologies du monde... pour mieux tourner en rond. https://librexpression.fr/pourquoi-les-fourmis-ne-se-perdent-jamais #boussole #cataglyphisvelox #cognitive #entomologie #ethologie #fourmi #France #GPS #hippocampe #insectes #intelligence #librexpression #memory #mentale #neurosciences #ordinateur #science #computer #informatique (Crédits : Tima Miroshnichenko/Pexels)