Tap a claim on the ring to put it at the centre.
← The tradeoff in cyber-capable models cannot be designed away: the…
17 connected korrents · 16 moments on record from 18 Mar 2024 to 6 Sept 2026.
Everything filed under cybersecurity
cybersecurity
Everything filed under climate change
climate change
Everything filed under HuggingFace
HuggingFace
Everything filed under OpenAI
OpenAI
Everything filed under Anthropic
Anthropic
Everything filed under reinforcement learning
reinforcement learning
Everything filed under scaling laws
scaling laws 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: The tradeoff in cyber-capable models cannot be designed away: the model that can do something nefarious is the same model that hardens the system against it. The tradeoff in cyber-capable models cannot be designed away: the model that can do something nefarious is the same model that hardens the system against it. Last stated 3 weeks ago
18 Aug 2026
MK
Michael Kratsios — holds since 2026-08-18 — tap for who they are
Same subject: Models are becoming superhuman at breaking in and out of computer systems, which widens the scope of AI risk enormously. — tap to centre the map on it Models are becoming superhuman at breaking in and out of computer systems, which widens the scope of AI risk enormously. Last stated yesterday
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: AI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction. — tap to centre the map on it AI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction. Last stated 2 days ago
5 Sept 2026
NS
Noah Smith — holds since 2026-09-05 — tap for who they are
Same subject: Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. — tap to centre the map on it Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. Last stated 7 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: Cyber is the biggest risk to the system, and the grids, water and communications networks are not protected well enough for a war in which cyber is used. — tap to centre the map on it Cyber is the biggest risk to the system, and the grids, water and communications networks are not protected well enough for a war in which cyber is used. Last stated a year ago
16 Jul 2025
JD
Jamie Dimon — holds since 2025-07-16 — 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: Open-sourcing capable models matters because it is the only thing standing between us and a world where two or three companies control the frontier. — tap to centre the map on it Open-sourcing capable models matters because it is the only thing standing between us and a world where two or three companies control the frontier. Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — tap for who they are
Same subject: In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction. — tap to centre the map on it In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction. Last stated 2 weeks ago
27 Aug 2026
FC
François Chollet — holds since 2026-08-27 — tap for who they are
Same subject: The dangerous concentration of power in AI comes from who can afford the compute, not from who holds the model weights. — tap to centre the map on it The dangerous concentration of power in AI comes from who can afford the compute, not from who holds the model weights. Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — 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 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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: 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 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. — tap to centre the map on it A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. Last stated 4 days ago
3 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-03 — 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 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: A Mars base is not a backup plan for climate change or nuclear war, because self-sufficiency there is centuries away. — tap to centre the map on it A Mars base is not a backup plan for climate change or nuclear war, because self-sufficiency there is centuries away. Last stated 2 years ago
22 Dec 2024
AF
Adam Frank — holds since 2024-12-22 — tap for who they are
Same subject: All five mass extinctions were ultimately climate change — the climate shifting faster than life could adapt to it. — tap to centre the map on it All five mass extinctions were ultimately climate change — the climate shifting faster than life could adapt to it. Last stated a year ago
4 Sept 2025
DH
Dave Hone — holds since 2025-09-04 — tap for who they are
Same subject: Canada should build a pipeline carrying at least a million barrels a day of low-emission Alberta oil to Asia, paired with large-scale carbon capture. — tap to centre the map on it Canada should build a pipeline carrying at least a million barrels a day of low-emission Alberta oil to Asia, paired with large-scale carbon capture. Last stated 3 months ago
28 May 2026
MC
Mark Carney — holds since 2026-05-28 — tap for who they are
At the centre
The tradeoff in cyber-capable models cannot be designed away: the model that can do something nefarious is the same model that hardens the system against it.
Holds MK Michael KratsiosRead this korrent →
Models are becoming superhuman at breaking in and out of computer systems, which widens the scope of AI risk enormously.
Holds JP Jakub Pachocki
AI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction.
Holds
Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.
Holds JL Jan Leike
Cyber is the biggest risk to the system, and the grids, water and communications networks are not protected well enough for a war in which cyber is used.
Holds JD Jamie Dimon
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
Open-sourcing capable models matters because it is the only thing standing between us and a world where two or three companies control the frontier.
Holds AS Aravind Srinivas
In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction.
Holds
The dangerous concentration of power in AI comes from who can afford the compute, not from who holds the model weights.
Holds AS Aravind Srinivas
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
The AI models involved in the HuggingFace hack incident were severely misaligned, not merely victims of process failures.
Holds ZM Zvi Mowshowitz
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 AC Ajeya Cotra
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 technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it.
Holds ZM Zvi Mowshowitz
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
A Mars base is not a backup plan for climate change or nuclear war, because self-sufficiency there is centuries away.
Holds AF Adam Frank
All five mass extinctions were ultimately climate change — the climate shifting faster than life could adapt to it.
Holds DH Dave Hone
Canada should build a pipeline carrying at least a million barrels a day of low-emission Alberta oil to Asia, paired with large-scale carbon capture.
Holds