Tap a claim on the ring to put it at the centre.
← Wikis are tempting targets for rogue agent swarms.
17 connected korrents · 12 moments from 10 Oct 2023 to 7 Oct 2026.
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment
Everything filed under reinforcement learning
reinforcement learning
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under AI agents
AI agents
Everything filed under AGI
AGI 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: Wikis are tempting targets for rogue agent swarms. Wikis are tempting targets for rogue agent swarms. Last stated today
7 Oct 2026
SW
Simon Willison — holds since 2026-10-07 — 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 month ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages. — tap to centre the map on it Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages. Last stated 3 weeks ago
17 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-17 — 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 month 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 7 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. — tap to centre the map on it Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. Last stated a month ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Most of the alarming MoltBook screenshots were humans prompting the bots to go viral, not autonomous AI behaviour. — tap to centre the map on it Most of the alarming MoltBook screenshots were humans prompting the bots to go viral, not autonomous AI behaviour. Last stated 8 months ago
12 Feb 2026
LF
Lex Fridman — holds since 2026-02-12 — 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 month ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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 month ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. Last stated 4 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality — tap to centre the map on it A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality Last stated 3 years ago
10 Oct 2023
CH
Chip Huyen — holds since 2023-10-10 — 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 2 months 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 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 2 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 9 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated 3 weeks ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — tap for who they are
At the centre
Wikis are tempting targets for rogue agent swarms.
Holds Read this korrent →
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Holds
Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages.
Holds
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
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
Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it.
Holds
Most of the alarming MoltBook screenshots were humans prompting the bots to go viral, not autonomous AI behaviour.
Holds
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
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
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Holds
A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted.
Holds
A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
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
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds