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 · 15 moments from 18 Mar 2024 to 21 Oct 2026.
Everything filed under cybersecurity
cybersecurity
Everything filed under AI alignment
AI alignment
Everything filed under OpenAI
OpenAI
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: 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 2 months ago
18 Aug 2026
MK
Michael Kratsios — holds since 2026-08-18 — tap for who they are
Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe because they are not smart enough, not because they are too smart. Last stated a month ago
13 Sept 2026
FC
François Chollet — holds since 2026-09-13 — 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 2 months ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. — tap to centre the map on it A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. Last stated a month ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — 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 months ago
5 Sept 2026
NS
Noah Smith — holds since 2026-09-05 — tap for who they are
Same subject: A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. — tap to centre the map on it A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. Last stated a month ago
11 Sept 2026
YB
Yoshua Bengio — holds since 2026-09-11 — 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 9 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products. — tap to centre the map on it AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products. Last stated 3 months ago
10 Jul 2026
SK
Steve Klabnik — holds since 2026-07-10 — tap for who they are
Same subject: In the near term, more capable models should mean safer models. — tap to centre the map on it In the near term, more capable models should mean safer models. Last stated a month ago
13 Sept 2026
FC
François Chollet — holds since 2026-09-13 — tap for who they are
Same subject: Agent containment will be one of the most important priorities for any AI infra company. — tap to centre the map on it Agent containment will be one of the most important priorities for any AI infra company. Last stated a week ago
14 Oct 2026
GR
Guillermo Rauch — holds since 2026-10-14 — 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 OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug. — tap to centre the map on it The OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug. Last stated 2 months ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. Last stated 2 days ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A business making hundreds of millions from an open source project owes it money or contribution, and can be refused its trademarks if it gives neither. — tap to centre the map on it A business making hundreds of millions from an open source project owes it money or contribution, and can be refused its trademarks if it gives neither. Last stated 2 years ago
26 Sept 2024
MM
Matt Mullenweg — holds since 2024-09-26 — tap for who they are
Same subject: A codec does not really exist until everyone can decode it. — tap to centre the map on it A codec does not really exist until everyone can decode it. Last stated 5 months ago
31 May 2026
JK
Jean-Baptiste Kempf — holds since 2026-05-31 — tap for who they are
Same subject: A company that will not accept a project’s terms is free to go and use a more permissive project instead. — tap to centre the map on it A company that will not accept a project’s terms is free to go and use a more permissive project instead. Last stated 2 years ago
26 Sept 2024
MM
Matt Mullenweg — holds since 2024-09-26 — 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 Read this korrent →
Current models are unsafe because they are not smart enough, not because they are too smart.
Holds
Models are becoming superhuman at breaking in and out of computer systems, which widens the scope of AI risk enormously.
Holds
A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety.
Holds
AI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction.
Holds
A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one.
Holds
Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.
Holds
AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products.
Holds
In the near term, more capable models should mean safer models.
Holds
Agent containment will be one of the most important priorities for any AI infra company.
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 OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
Holds
A business making hundreds of millions from an open source project owes it money or contribution, and can be refused its trademarks if it gives neither.
Holds
A codec does not really exist until everyone can decode it.
Holds
A company that will not accept a project’s terms is free to go and use a more permissive project instead.
Holds