Everyone's celebrating AI coding assistants, but nobody's talking about the 7.2% drop in delivery stability that comes with them. DORA just dropped a bombshell report on generative AI in software development, and the findings are way more complicated than the hype suggests. The
GENERATIVE AI
-

M3GAN 2.0 explores AI safety through killer robot narrative
By
–
M3GAN 2.0 is surprisingly quite a bit more satisfying than the first one: cute killer AI defeating a conspiracy of evil AI doomers pic.twitter.com/4x6K6LsaP8
— Joscha Bach (@Plinz) 29 septembre 2025M3GAN 2.0 is surprisingly quite a bit more satisfying than the first one: cute killer AI defeating a conspiracy of evil AI doomers
-
AI creativity is architecture, not imagination
By
–
people think ai creativity is magic. it paints, writes, composes – so we assume it’s “thinking” like us. but that’s not what’s happening under the hood. researchers recently showed that creativity in models comes from architecture, not imagination. the wiring matters more than
-
AI’s creativity stems from pattern recognition
By
–
ai doesn’t create because it “wants to.” it creates because we wired it to notice patterns. architectural choices like locality and equivariance force the model to capture structure in the data. that’s why it can remix old knowledge into something that looks new. creativity in
-
Elon Musk Claims Grok 4 Surpasses PhDs, May Discover Physics Laws
By
–
Elon Musk : Je m’attends à ce que Grok découvre de nouvelles lois de la physique d’ici l’année prochaine.
— VISION IA (@vision_ia) 29 septembre 2025
« Je veux vraiment insister sur ce point. Sur les questions académiques, Grok 4 est meilleur qu’un docteur en chaque matière. Sans exception.
Je m’attends à ce que Grok… pic.twitter.com/zyUjIWezGJElon Musk : Je m’attends à ce que Grok découvre de nouvelles lois de la physique d’ici l’année prochaine. « Je veux vraiment insister sur ce point. Sur les questions académiques, Grok 4 est meilleur qu’un docteur en chaque matière. Sans exception. Je m’attends à ce que Grok
-

Grok 4 Heavy: Advanced AI Model for Complex Problem Solving
By
–
Grok 4 Heavy for the toughest problems. And it gets better almost every week.
-

From Few-Shot to Zero-Shot: The Next AI Frontier
By
–
In 2020, OpenAI showed that language models are few-shot learners. In 2022, ChatGPT was released. By 2025, Google DeepMind demonstrated that video models are zero-shot learners and reasoners. What’s next?
-
Building Internal Tool for Blind A/B Testing Preview Models
By
–
I get asked to compare preview models a lot so finally built an internal tool to blind A/B test them on real codebases
— swyx 🐣 (@swyx) 29 septembre 2025
(quick screenstudio, no audio since i'm sick sorry) pic.twitter.com/5IL4NkCJiWI get asked to compare preview models a lot so finally built an internal tool to blind A/B test them on real codebases (quick screenstudio, no audio since i'm sick sorry)
-
LLM Researchers’ Knowledge Gap About Language Fundamentals
By
–
Ironically, LLM researchers know nothing about language.
