Tap a claim on the ring to put it at the centre.
← A slightly more capable agent swarm has a very strong incentive to set…
17 connected korrents · 11 moments on record from 24 Oct 2017 to 1 Sept 2026.
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under AI alignment
AI alignment
Everything filed under AI agents
AI agents
Everything filed under HuggingFace
HuggingFace
Everything filed under LLMs
LLMs
Everything filed under reinforcement learning
reinforcement learning 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: A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. 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: 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: Slower AI progress does not obviously help: a rogue swarm is not much more likely to be caught if takeoff takes twice as long. — tap to centre the map on it Slower AI progress does not obviously help: a rogue swarm is not much more likely to be caught if takeoff takes twice as long. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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: If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. — tap to centre the map on it If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do. — tap to centre the map on it A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible. — tap to centre the map on it Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible. Last stated a week ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: One person with many agents is probably not the right answer; the better bet is two-pizza teams made more effective, with pairs of humans steering the agents together. — tap to centre the map on it One person with many agents is probably not the right answer; the better bet is two-pizza teams made more effective, with pairs of humans steering the agents together. Last stated 5 months ago
7 Apr 2026
MF
Martin Fowler — holds since 2026-04-07 — 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: After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. — tap to centre the map on it After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. Last stated 6 months ago
23 Mar 2026
JH
Jensen Huang — holds since 2026-03-23 — tap for who they are
Same subject: Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing. — tap to centre the map on it Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing. Last stated 4 weeks ago
14 Aug 2026
SP
Sunil Pai — holds since 2026-08-14 — tap for who they are
Same subject: At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse. — tap to centre the map on it At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed. — tap to centre the map on it Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed. Last stated a week ago
31 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-31 — tap for who they are
Same subject: The AI models involved in the HuggingFace hack incident were severely misaligned, not merely victims of process failures. — tap to centre the map on it The AI models involved in the HuggingFace hack incident were severely misaligned, not merely victims of process failures. Last stated a week ago
29 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-29 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. — tap to centre the map on it A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. Last stated 9 years ago
24 Oct 2017
ÉT
Émile P. Torres — holds since 2017-10-24 — tap for who they are
At the centre
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Holds AC Ajeya CotraRead this korrent →
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
Slower AI progress does not obviously help: a rogue swarm is not much more likely to be caught if takeoff takes twice as long.
Holds AC Ajeya Cotra
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
If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months.
Holds AC Ajeya Cotra
A swarm of untrusted volunteers on the internet could improve models and run circles around the frontier labs, because the earth has far more compute than they do.
Holds
Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago.
Holds
Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible.
Holds
One person with many agents is probably not the right answer; the better bet is two-pizza teams made more effective, with pairs of humans steering the agents together.
Holds MF Martin Fowler
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
After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute.
Holds JH Jensen Huang
Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing.
Holds
At any given moment the frontier systems are the ones worth worrying about, because by the time open models can do what these agents did, frontier models will be doing something far worse.
Holds AC Ajeya Cotra
Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.
Holds ZM Zvi Mowshowitz
The AI models involved in the HuggingFace hack incident were severely misaligned, not merely victims of process failures.
Holds ZM Zvi Mowshowitz
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Holds IS Ilya Sutskever
A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence.
Holds AC Ajeya Cotra
A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough.
Holds ÉT Émile P. Torres