Human reasoning is not based on auto-regressive discrete symbol (token) prediction.
It is based on the manipulation of mental models in continuous representations spaces.
It is based on *searching* for a set of manipulations of this model to arrive at a particular result.
SAFETY
-
Human Reasoning Beyond Token Prediction: Mental Models
By
–
-
Fumbling humanity at the brink of superintelligence
By
–
Would be the ultimate shame if we fumbled this whole humanity thing this close to achieving superintelligence.
-
LLM Weaknesses: Safe Integration and Mitigation Techniques
By
–
These weaknesses are crucial to understand so you can know where you can build with and use LLM tools safely and appropriately in your workflows and what techniques you can use to address these issues.
-
Gemini 2.5: Flash Lite, Pro Deep Think, Pro GA
By
–
Gemini 2.5 Flash Lite?
Gemini 2.5 Pro Deep Think?
Gemini 2.5 Pro GA? The next leap -
Power Concentration in AI: Rebutting Eugenic Ideologies
By
–
We have the equivalent of the scientologists running the field of AI with untold amounts of money and power and we're the ones who have to do point by point rebuttals of their eugenicists dreams.
-
Medical Policy Enforcement: Implicit Rules Shape Healthcare Professional Conduct
By
–
For example, when X was “we will yank the license of, destroy the reputation of, and if possible prosecute any medical professional who delivers a dose out of order”, which was *definitely policy until it wasn’t* but which *shaped actions later, too.*
-
Security Risks of Local LLM Agents vs Web-Based Interfaces
By
–
I should clarify that the risk is highest if you're running local LLM agents (e.g. Cursor, Claude Code, etc.). If you're just talking to an LLM on a website (e.g. ChatGPT), the risk is much lower *unless* you start turning on Connectors. For example I just saw ChatGPT is adding
-
Prompt Injection Attacks in LLMs: A Wild West of Computing
By
–
RT to help Simon raise awareness of prompt injection attacks in LLMs. Feels a bit like the wild west of early computing, with computer viruses (now = malicious prompts hiding in web data/tools), and not well developed defenses (antivirus, or a lot more developed kernel/user
-
AI Decision Contestability: Human Comprehension Limits
By
–
L’idée selon laquelle nous pourrons contester les décisions de l’Intelligence Artificielle est complètement NAÏVE Il devient impossible de contester les décisions de l’IA tant les sujets sont trop compliqués pour les cerveaux humains C’est VIOLENT !
-
Segway Waiters: Impressive Efficiency Meets Real-World Risk
By
–
La habilidad de estos camareros con el Segway es impresionante. Sin duda el servicio será rapidísimo, pero cualquier pequeño error puede provocar un pequeño desastre.
— Juan Merodio (@juanmerodio) 16 juin 2025
Crees qué compensa? pic.twitter.com/Tdd3DbAMyCLa habilidad de estos camareros con el Segway es impresionante. Sin duda el servicio será rapidísimo, pero cualquier pequeño error puede provocar un pequeño desastre. Crees qué compensa?