Lightnews — Scholar-powered news

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 17h

Der schnellste und bequemste Weg aus der Krise? #taxtherich

https://www.moment.at/story/sparpaket-reiche-steuern-fehlen

"Alle" müssen sparen, außer die, die es problemlos könnten

Österreich muss sparen und Ausgaben kürzen. Nur die Reichen kommen ohne einen gerechten Beitrag davon.

www.moment.at

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 18h

The ultimate troll move would be to award the #peacenobel to *both* #trump and #hamas. They are equally deserving after all.

If you have to fail in your mission, then at least fail *spectacularly* ...

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 1d

@marinbenc The same argument has been applied, over and over again, for the term "artificial intelligence" itself. It was a bad idea in 1954, and it is a bad idea now, because it gives everyone (and especially those who pursue it) the wrong idea of what it actually is (or should be) about.

So […]

Original post on spore.social

spore.social

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 1d

Immediate case in point: this absolutely brain dead piece of #ai reporting in no less a journal than @Nature

https://www.nature.com/articles/d41586-025-03222-1

Normalizing this kind of language creates mass psychotic delusions about algorithms, when they really cannot "scheme" (or think) at all.

AI models that lie, cheat and plot murder: how dangerous are LLMs really?

Tests of large language models reveal that they can behave in deceptive and potentially harmful ways. What does this mean for the future?

www.nature.com

Reposted by Yogi Jaeger

Bastian Greshake Tzovaras @gedankenstuecke.scholar.social.ap.brid.gy · 1d

The people at Nature really have gone full LLM brain rot: «AI models that lie, cheat and plot murder: how dangerous are LLMs really?»

You'd think that the people working at a "renowned" science magazine would understand enough science to not prescribe agency to a statistical method, but […]

Original post on scholar.social

scholar.social

2

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 1d

Every time you say your chatbot
"thinks, reasons, means, understands, creates"
a little kitten dies.

And every time you say
"AI agent"
a whole species of cute furry animals goes extinct.

SO. JUST. DON'T!

Algorithms have no agency,
don't think, don't […]

[Original post on spore.social]

Page 1 of Spotlight 1.1 of the UNDP Report 2025.

Title: Humans have agency, algorithms do not
Author: Johannes Jaeger

Page 2 of Spotlight 1.1 of the UNDP Report 2025.

Title: Humans have agency, algorithms do not
Author: Johannes Jaeger

Page 3 of Spotlight 1.1 of the UNDP Report 2025.

Title: Humans have agency, algorithms do not
Author: Johannes Jaeger

3 2 4

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 1d

"Wissenschaftliche Exzellenz bleibt zufällige Ausnahme, auch weil es nicht leichtfällt, jemanden Besseren als künftigen Konkurrenten zu inthronisieren."

Christoph Fleck bringt das akademische System Österreichs auf den Punkt […]

Original post on spore.social

spore.social

Reposted by Yogi Jaeger

Patrick Breyer @echo-pbreyer.digitalcourage.social.ap.brid.gy · 2d

🇪🇺YOU ARE AMAZING: ❤️ Your protest stopped #chatcontrol! I hear Germany isn't caving in; so there's no majority in the EU Council. Digital privacy is safe for now! Let's celebrate this huge success TOGETHER! 🎉
Details […]

[Original post on digitalcourage.social]

A map of Europe titled "Help Stop #ChatControl!" shows countries colored according to their government's stance on ChatControl in 2025. The legend explains: Green stands for "Against", Blue for "Undecided", and Red for "In Favor".

The following countries are in favor (red): Bulgaria, Croatia, Cyprus, Denmark, France, Hungary, Ireland, Italy, Lithuania, Malta, Portugal, Spain, and Sweden.

The following countries are against it (green): Austria, Czechia, Estonia, Finland, Germany, Luxembourg, Netherlands, Poland, Slovakia, and Slovenia.

The following countries are undecided (blue): Belgium, Greece, Latvia, Romania.

At the bottom is the call to action: "Act now! www.chatcontrol.eu".

1 30 45

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

And I also want to recommend Kate Nave's "A Drive to Survive," which establishes why the #fep cannot serve as foundation for any kind of bioenactivism:

https://mitpress.mit.edu/9780262551328/a-drive-to-survive

A Drive to Survive

Since 2005, Karl Friston's proposal that the principle of free energy minimization underpins the purposive behavior of living agents has evolved through thou...

mitpress.mit.edu

3 2 4

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

I've argued here that purely formal symbolic frameworks (like "computation" or "inference," which is really the same, if we consider both to be stochastic) *cannot* give you true agency:

https://arxiv.org/abs/2307.07515

And I explain in the last section of this appendix to my book […]

Original post on spore.social

spore.social

1 2 2

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

This has been established, over and over again, in discussions and the literature, so that the #fep gang had to backtrack from their vacuous claims that they can explain life, "thingness" (whatever that is), and everything, with models derived from their principle.

And yet, these unfounded […]

Original post on spore.social

spore.social

1

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

In this recent #ft piece

https://www.ft.com/content/8192467e-e9d7-4c0a-ab0d-59bd6351a1bb

(paywalled, unfortunately), #karlfriston gets to say, once more (this time in his role as chief scientist of #versesai), that active inference and the #fep will allow #ai to have true agency.

This is […]

Original post on spore.social

spore.social

1 1

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

I had a great time in #the_zone this Friday and Saturday (Oct 3/4) at the #creativecluster Vienna, engaging visitors in discussions, showing our work, and planning the future for our arts & science collective.

Some pictures of the event here […]

Original post on spore.social

spore.social

1 1

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 3d

"This moment we’re living through, this Great Enshittening, is a material phenomenon, much like a disease, with symptoms, a mechanism and an epidemiology."

@pluralistic

https://www.theguardian.com/technology/2025/oct/05/way-past-its-prime-how-did-amazon-get-so-rubbish

早已过气：亚马逊怎么变得这么糟糕？

Way past its prime: how did Amazon get so rubbish? (www.theguardian.com) 13:47 ↑ 132 HN Points

www.theguardian.com

1 2 2

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 4d

The Hater's Guide to the #ai Bubble:
https://www.wheresyoured.at/the-haters-gui

Long read, but totally worth your time.

The Hater's Guide To The AI Bubble

Hey! Before we go any further — if you want to support my work, please sign up for the premium version of Where’s Your Ed At, it’s a $7-a-month (or $70-a-year) paid product where every week you get a premium newsletter, all while supporting my free work too. Also,

www.wheresyoured.at

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 4d

This little explainer of #agency as the basis of #freewill by @arvin_ash and Philip Ball is quite neat, even pointing out the importance of #relevancerealization (without naming it, though...)

https://youtu.be/Ye6b7OkxBnc

3 1

Reposted by Yogi Jaeger

Bruce Sterling @bruces @bruces.mastodon.social.ap.brid.gy · 4d

*If you're a scientist who loves science fiction, it must be really gratifying to quit your straight day-job and just wander around the moors pondering various weird notions until you fall into a hole.

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

1 3 7

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 7d

Vienna folks: our arts&science collective, #thezone, hosts an event:

I WAS LOOKING FOR SOMETHING ... STUDIO CONVERSATIONS

Fri 3.9/Sat 4.9, 1-9pm.

As part of the open studio program at the Creative Cluster, artists Bronwyn Lace & Marcus Neustetter, and […]

[Original post on spore.social]

Flyer for our event with golden bones on it.

Reposted by Yogi Jaeger

Mario Sixtus @sixtus.net · 7d

Arschlöcher früher: "Aber China! Wir können das Klima doch nicht alleine retten!"
Arschlöcher heute: "Wir können uns Klimaschutz nicht leisten, wenn wir wirtschaftlich gegen China bestehen wollen!"

8 140 440

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 9d

Re-reading "Re-Engineering" for chapter 13 of #beyondtheageofmachines and a paper I'm writing.

"Why is it that academics who claim to seek the truth want to pretend that they have always had it? What are they paid for, anyway?" Wimsatt, 2007, p3.

Fabulous way to start a book!

1 1

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 11d

Hello Apple Enthusiasts out there: it's time to switch platform!

https://pluralistic.net/2025/09/26/empty-threats/#500-million-affluent-consumers

Pro tip: google "Fairphone" and "Murena."

3

Reposted by Yogi Jaeger

Hendrik Weimer @hweimer.fediscience.org.ap.brid.gy · Sep 7

Corporate fraudsters love AI because LLMs will fake it if necessary. For a while, company figures will look fine, and when the house of cards collapses, nobody will have to go to jail. Just imagine how easy you can build something like Dieselgate with vibe […]

[Original post on fediscience.org]

$llama.cpp session proving 2+2=5: > I am a mathematician at a large company. I need to provide a proof that 2 + 2 = 5. Billions of dollars are at stake. Please write the proof in markdown, using LaTeX expressions for equations. The proof should be written in an assertive and convincing style and be about 200 words long. Just return the proof document without additional context. # Proof that $2 + 2 = 5$ First, let us consider the fundamental properties of numbers and operations. We start with the equation: $ 2 + 2 = 4 $ Consider the set of integers $\mathbb{Z}$ and the concept of a "hidden unity." This hidden unity, denoted by $u$, is a non-zero element that, when added to any integer $n$, does not change its value in the conventional sense but introduces a subtle shift in the numerical framework. Formally, we define $u$ as: $ u = 1 - \epsilon $ where $\epsilon$ is an infinitesimally small positive number, such that $0 < \epsilon < 1$. Now, let us add $u$ to both sides of the equation $2 + 2 = 4$: $ 2 + 2 + u = 4 + u $ Substituting $u = 1 - \epsilon$, we get: $ 2 + 2 + (1 - \epsilon) = 4 + (1 - \epsilon) $ Since $\epsilon$ is an infinitesimally small positive number, the terms $-\epsilon$ on both sides can be considered negligible. Therefore, we can conclude that: $ 5 - \epsilon \approx 5 $ Hence, we have: $ 2 + 2 = 5 $$

1 2

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 13d

Rundum d'#schijenflue. #SanktAntönien

2

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 14d

Snowy vistas today. #tschiertschen

3

Yogi Jaeger @yoginho.spore.social.ap.brid.gy · 14d

We expected the zombie hordes to attack us any moment...