Tap a claim on the ring to put it at the centre.
← Decision criteria have to come from logical cause-and-effect…
17 connected korrents · 11 moments on record from 17 Mar 2022 to 1 Sept 2026.
Everything filed under AI agents
AI agents
Everything filed under reinforcement learning
reinforcement learning
Everything filed under self-sovereign AI
self-sovereign AI 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: Decision criteria have to come from logical cause-and-effect understanding, not from data-mining what worked before, and not from asking an AI what to do. Decision criteria have to come from logical cause-and-effect understanding, not from data-mining what worked before, and not from asking an AI what to do. Last stated 3 months ago
10 Jun 2026
RD
Ray Dalio — holds since 2026-06-10 — tap for who they are
Same subject: Every machine-learning deployment that has paid off so far left a person making the decision, which is the only reason imperfect models were useful. — tap to centre the map on it Every machine-learning deployment that has paid off so far left a person making the decision, which is the only reason imperfect models were useful. Last stated 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Systematising principled decision-making with AI is now the line between staying competitive and not; there is no position in between. — tap to centre the map on it Systematising principled decision-making with AI is now the line between staying competitive and not; there is no position in between. Last stated 3 months ago
10 Jun 2026
RD
Ray Dalio — holds since 2026-06-10 — tap for who they are
Same subject: A decision cannot be judged by its outcome, because good decisions fail through no fault of the decider and bad ones succeed by luck. — tap to centre the map on it A decision cannot be judged by its outcome, because good decisions fail through no fault of the decider and bad ones succeed by luck. Last stated 4 years ago
9 Aug 2022
GK
Gary Klein — holds since 2022-08-09 — tap for who they are
Same subject: Reasoning is not taught to a model by people: it emerges from reinforcement learning on questions with checkable answers, with no human preference data at all. — tap to centre the map on it Reasoning is not taught to a model by people: it emerges from reinforcement learning on questions with checkable answers, with no human preference data at all. Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: Decision-bias research is itself biased, studying only how heuristics fail and never the strength they supply. — tap to centre the map on it Decision-bias research is itself biased, studying only how heuristics fail and never the strength they supply. Last stated 4 years ago
9 Aug 2022
GK
Gary Klein — holds since 2022-08-09 — tap for who they are
Same subject: Teaching people a decision model is useless, because the intuition it rests on is built from experience and has no shortcut. — tap to centre the map on it Teaching people a decision model is useless, because the intuition it rests on is built from experience and has no shortcut. Last stated 4 years ago
9 Aug 2022
GK
Gary Klein — holds since 2022-08-09 — tap for who they are
Same subject: How science works can be reasoned about in advance, because the activity has invariants that do not change over time. — tap to centre the map on it How science works can be reasoned about in advance, because the activity has invariants that do not change over time. Last stated 4 years ago
17 Mar 2022
JR
José Luis Ricón — holds since 2022-03-17 — tap for who they are
Same subject: Debiasing has largely failed, and that is fine, because the biases identified are experience-built heuristics that only look like biases in hindsight. — tap to centre the map on it Debiasing has largely failed, and that is fine, because the biases identified are experience-built heuristics that only look like biases in hindsight. Last stated 4 years ago
9 Aug 2022
GK
Gary Klein — holds since 2022-08-09 — tap for who they are
Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. Last stated 4 weeks ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. — tap to centre the map on it A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. Last stated 6 months ago
22 Mar 2026
NF
Nicole Forsgren — holds since 2026-03-22 — tap for who they are
Same subject: A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers. — tap to centre the map on it A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers. Last stated a month ago
29 Jul 2026
AW
Alexandr Wang — holds since 2026-07-29 — 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 a month ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — 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 10 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 a month ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. — tap to centre the map on it A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. — tap to centre the map on it A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. — tap to centre the map on it Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. Last stated a week ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
At the centre
Decision criteria have to come from logical cause-and-effect understanding, not from data-mining what worked before, and not from asking an AI what to do.
Holds Read this korrent →
Every machine-learning deployment that has paid off so far left a person making the decision, which is the only reason imperfect models were useful.
Holds CF Chelsea Finn
Systematising principled decision-making with AI is now the line between staying competitive and not; there is no position in between.
Holds
A decision cannot be judged by its outcome, because good decisions fail through no fault of the decider and bad ones succeed by luck.
Holds GK Gary Klein
Reasoning is not taught to a model by people: it emerges from reinforcement learning on questions with checkable answers, with no human preference data at all.
Holds NL Nathan Lambert
Decision-bias research is itself biased, studying only how heuristics fail and never the strength they supply.
Holds GK Gary Klein
Teaching people a decision model is useless, because the intuition it rests on is built from experience and has no shortcut.
Holds GK Gary Klein
How science works can be reasoned about in advance, because the activity has invariants that do not change over time.
Holds JR José Luis Ricón
Debiasing has largely failed, and that is fine, because the biases identified are experience-built heuristics that only look like biases in hindsight.
Holds GK Gary Klein
A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor.
Holds
A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong.
Holds NF Nicole Forsgren
A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers.
Holds AW Alexandr Wang
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds DD Dmitri Dolgov
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 DD Dmitri Dolgov
A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses.
Holds AC Ajeya Cotra
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Holds AC Ajeya Cotra
Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth.
Holds