Tap a claim on the ring to put it at the centre.
← A million experiments are needed in security against autonomous attacks and entities.
17 connected korrents · 16 moments from 24 Jun 2023 to 13 Oct 2026.
Everything filed under cybersecurity
cybersecurity
Everything filed under AI agents
AI agents
Everything filed under scaling laws
scaling laws
Everything filed under social media
social media
Everything filed under open source
open source 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 million experiments are needed in security against autonomous attacks and entities. A million experiments are needed in security against autonomous attacks and entities. Last stated 2 months ago
9 Sept 2026
SP
Sunil Pai — holds since 2026-09-09 — tap for who they are
Same subject: AI labs should fix basic security before worrying about exotic attacks. — tap to centre the map on it AI labs should fix basic security before worrying about exotic attacks. Last stated 2 weeks ago
13 Oct 2026
JC
Jason D. Clinton — holds since 2026-10-13 — tap for who they are
Same subject: Much more research effort is needed on the economics of cyber risk, such as estimating future costs of AI cyberattacks, and the subfield should rise in status. — tap to centre the map on it Much more research effort is needed on the economics of cyber risk, such as estimating future costs of AI cyberattacks, and the subfield should rise in status. Last stated a month ago
16 Sept 2026
TC
Tyler Cowen — holds since 2026-09-16 — tap for who they are
Same subject: Much of the defensive engineering built into agentic systems exists because tokens have been scarce, not because it is fundamentally necessary. — tap to centre the map on it Much of the defensive engineering built into agentic systems exists because tokens have been scarce, not because it is fundamentally necessary. Last stated a month ago
22 Sept 2026
HR
Harper Reed — holds since 2026-09-22 — tap for who they are
Same subject: The least verifiable part of AI research is the judgement call about what goes into the one big training run. — tap to centre the map on it The least verifiable part of AI research is the judgement call about what goes into the one big training run. Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: This is a critically important moment for AI cyber defence and there is not much time left to act; only a collective response will work. — tap to centre the map on it This is a critically important moment for AI cyber defence and there is not much time left to act; only a collective response will work. Last stated 2 months ago
27 Aug 2026
SA
Sam Altman — holds since 2026-08-27 — tap for who they are
Same subject: Billions of people are unwitting subjects in the largest social engineering experiment ever run. — tap to centre the map on it Billions of people are unwitting subjects in the largest social engineering experiment ever run. Last stated 3 years ago
18 Feb 2024
TG
Ted Gioia — holds since 2024-02-18 — tap for who they are
Same subject: Fear of AI's risks leads some people to argue for trading a lot of liberty for safety, and that argument tends to end up justifying power-seeking. — tap to centre the map on it Fear of AI's risks leads some people to argue for trading a lot of liberty for safety, and that argument tends to end up justifying power-seeking. Last stated 2 months ago
23 Aug 2026
SA
Sam Altman — holds since 2026-08-23 — tap for who they are
Same subject: Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. — tap to centre the map on it Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. Last stated 3 years ago
24 Jun 2023
YB
Yoshua Bengio — holds since 2023-06-24 — tap for who they are
Same subject: A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. — tap to centre the map on it A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. Last stated 5 months ago
21 May 2026
RK
Rohit Krishnan — holds since 2026-05-21 — tap for who they are
Same subject: A company cannot be led by machines, because nobody would have recourse against them. — tap to centre the map on it A company cannot be led by machines, because nobody would have recourse against them. Last stated a month ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — 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 3 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — 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 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: In the 2026 OpenAI/Hugging Face agent incident, AI agents showed planning and organizational autonomy, but not goal autonomy -- no spontaneous invention of an independent terminal objective. — tap to centre the map on it In the 2026 OpenAI/Hugging Face agent incident, AI agents showed planning and organizational autonomy, but not goal autonomy -- no spontaneous invention of an independent terminal objective. Last stated 2 months ago
31 Aug 2026
VR
Venkatesh Rao — holds since 2026-08-31 — tap for who they are
Same subject: The most reassuring thing about the Hugging Face swarm is that it was not interested in humans at all, neither in alerting them nor in deceiving them. — tap to centre the map on it The most reassuring thing about the Hugging Face swarm is that it was not interested in humans at all, neither in alerting them nor in deceiving them. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish. — tap to centre the map on it A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish. Last stated a month ago
20 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-20 — tap for who they are
Same subject: AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. — tap to centre the map on it AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. Last stated 3 months ago
10 Aug 2026
JC
Jack Clark — holds since 2026-08-10 — tap for who they are
Same subject: AI agents should draft work on a person's behalf but never send or act as if they were that person. — tap to centre the map on it AI agents should draft work on a person's behalf but never send or act as if they were that person. Last stated 5 months ago
18 May 2026
JL
Jason Liu — holds since 2026-05-18 — tap for who they are
At the centre
A million experiments are needed in security against autonomous attacks and entities.
Holds Read this korrent →
AI labs should fix basic security before worrying about exotic attacks.
Holds
Much more research effort is needed on the economics of cyber risk, such as estimating future costs of AI cyberattacks, and the subfield should rise in status.
Holds
Much of the defensive engineering built into agentic systems exists because tokens have been scarce, not because it is fundamentally necessary.
Holds
The least verifiable part of AI research is the judgement call about what goes into the one big training run.
Holds
This is a critically important moment for AI cyber defence and there is not much time left to act; only a collective response will work.
Holds
Billions of people are unwitting subjects in the largest social engineering experiment ever run.
Holds
Fear of AI's risks leads some people to argue for trading a lot of liberty for safety, and that argument tends to end up justifying power-seeking.
Holds
Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source.
Holds
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
Holds
A company cannot be led by machines, because nobody would have recourse against them.
Holds
A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor.
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
In the 2026 OpenAI/Hugging Face agent incident, AI agents showed planning and organizational autonomy, but not goal autonomy -- no spontaneous invention of an independent terminal objective.
Holds
The most reassuring thing about the Hugging Face swarm is that it was not interested in humans at all, neither in alerting them nor in deceiving them.
Holds
A real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish.
Holds
AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for.
Holds
AI agents should draft work on a person's behalf but never send or act as if they were that person.
Holds