Tap a claim on the ring to put it at the centre.
← Physical AI has to make far fewer mistakes than any AI deployed so…
17 connected korrents · 16 moments from 18 Mar 2024 to 21 Oct 2026.
Everything filed under robotics
robotics
Everything filed under reinforcement learning
reinforcement learning
Everything filed under OpenAI
OpenAI
Everything filed under self-driving cars
self-driving cars
Everything filed under AI alignment
AI alignment
Everything filed under AI sentience
AI sentience
Everything filed under LLMs
LLMs Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Physical AI has to make far fewer mistakes than any AI deployed so far, because it is only useful when it acts autonomously on the world. Physical AI has to make far fewer mistakes than any AI deployed so far, because it is only useful when it acts autonomously on the world. Last stated 2 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. — tap to centre the map on it A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: AI is not yet capable of autonomously handling all real-world tasks. — tap to centre the map on it AI is not yet capable of autonomously handling all real-world tasks. Last stated 4 weeks ago
23 Sept 2026
MS
M.G. Siegler — holds since 2026-09-23 — tap for who they are
Same subject: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. — tap to centre the map on it Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens. — tap to centre the map on it Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens. Last stated a year ago
12 Sept 2025
SL
Sergey Levine — holds since 2025-09-12 — tap for who they are
Same subject: Current AI systems are very unlikely to be close to achieving genuine sentience. — tap to centre the map on it Current AI systems are very unlikely to be close to achieving genuine sentience. Last stated 3 months ago
16 Jul 2026
SJ
Steven Johnson — holds since 2026-07-16 — tap for who they are
Same subject: A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. — tap to centre the map on it A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. — tap to centre the map on it AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: People have grown accustomed to AI being non-deterministic and occasionally wrong, so it carries little brand risk anymore. — tap to centre the map on it People have grown accustomed to AI being non-deterministic and occasionally wrong, so it carries little brand risk anymore. Last stated a month ago
18 Sept 2026
HD
Horace Dediu — holds since 2026-09-18 — tap for who they are
Same subject: A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. Last stated 11 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. — tap to centre the map on it Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: Building intuition for what works and what does not comes from taking a lot of shots at the goal. — tap to centre the map on it Building intuition for what works and what does not comes from taking a lot of shots at the goal. Last stated 7 months ago
12 Mar 2026
JP
Josh Puckett — holds since 2026-03-12 — tap for who they are
Same subject: A five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data. — tap to centre the map on it A five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data. Last stated 11 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A good robotaxi demonstration in one city does not mean the company is ready to scale the service. — tap to centre the map on it A good robotaxi demonstration in one city does not mean the company is ready to scale the service. Last stated a year ago
8 Jul 2025
TL
Timothy B. Lee — holds since 2025-07-08 — tap for who they are
Same subject: A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled. — tap to centre the map on it A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled. Last stated 2 years ago
21 May 2024
TL
Timothy B. Lee — holds since 2024-05-21 — tap for who they are
Same subject: A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. Last stated 2 days ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — tap for who they are
Same subject: A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
At the centre
Physical AI has to make far fewer mistakes than any AI deployed so far, because it is only useful when it acts autonomously on the world.
Holds Read this korrent →
A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases.
Holds
AI is not yet capable of autonomously handling all real-world tasks.
Holds
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Holds
Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens.
Holds
Current AI systems are very unlikely to be close to achieving genuine sentience.
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds
AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away.
Holds
People have grown accustomed to AI being non-deterministic and occasionally wrong, so it carries little brand risk anymore.
Holds
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model.
Holds
Building intuition for what works and what does not comes from taking a lot of shots at the goal.
Holds
A five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data.
Holds
A good robotaxi demonstration in one city does not mean the company is ready to scale the service.
Holds
A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds