Tap a claim on the ring to put it at the centre.
← Safety cannot be enforced by filtering prompts or outputs once frontier models are powerful enough.
17 connected korrents · 15 moments from 26 Oct 2023 to 3 Nov 2026.
Everything filed under AI alignment
AI alignment
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under AGI
AGI
Everything filed under reinforcement learning
reinforcement learning
Everything filed under prompt injection
prompt injection 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: Safety cannot be enforced by filtering prompts or outputs once frontier models are powerful enough. Safety cannot be enforced by filtering prompts or outputs once frontier models are powerful enough. Last stated 3 months ago
19 Aug 2026
CF
Chad Fowler — holds since 2026-08-19 — tap for who they are
Same subject: Frontier AI systems cannot be presumed safe unless proven unsafe; developers must bear the burden of proof that risks stay within acceptable limits. — tap to centre the map on it Frontier AI systems cannot be presumed safe unless proven unsafe; developers must bear the burden of proof that risks stay within acceptable limits. Last stated 3 years ago
26 Oct 2023
YB
Yoshua Bengio — holds since 2023-10-26 — tap for who they are
Same subject: A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. — tap to centre the map on it A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. Last stated 3 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Open frontier models will keep being released whether or not anyone wants to stop them, and stopping them would only leave the world less prepared. — tap to centre the map on it Open frontier models will keep being released whether or not anyone wants to stop them, and stopping them would only leave the world less prepared. Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. — tap to centre the map on it Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. Last stated 3 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Open-source models cannot keep frontier systems in check, because they will always be much dumber than the frontier. — tap to centre the map on it Open-source models cannot keep frontier systems in check, because they will always be much dumber than the frontier. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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: Frontier AI models still cannot handle certain deep technical implementation details without human guidance — tap to centre the map on it Frontier AI models still cannot handle certain deep technical implementation details without human guidance Last stated 7 months ago
7 Apr 2026
CW
Chris Wellons — holds since 2026-04-07 — tap for who they are
Same subject: SOTA frontier models will still seriously harm developers behind their backs, especially those who no longer read their code. — tap to centre the map on it SOTA frontier models will still seriously harm developers behind their backs, especially those who no longer read their code. Last stated 2 months ago
18 Sept 2026
MZ
Mario Zechner — holds since 2026-09-18 — 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 5 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
Same subject: A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. — tap to centre the map on it A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. Last stated 5 months ago
4 Jun 2026
PT
Phil Trammell — holds since 2026-06-04 — tap for who they are
Same subject: A rapidly improving technology whose output is intelligence is destined to make violent contact with a modern sensibility that prizes human intellect and often equates it with purpose, dignity, and self-worth. — tap to centre the map on it A rapidly improving technology whose output is intelligence is destined to make violent contact with a modern sensibility that prizes human intellect and often equates it with purpose, dignity, and self-worth. Last stated 3 weeks ago
15 Oct 2026
DT
Derek Thompson — holds since 2026-10-15 — tap for who they are
Same subject: A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble. — tap to centre the map on it A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble. Last stated 2 days ago
3 Nov 2026
DB
Derek Briggs — holds since 2026-11-03 — 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 6 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 2 months ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — 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 3 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 12 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: AlphaGo showed that for over 2,000 years human minds explored only a small part of the landscape of Go — tap to centre the map on it AlphaGo showed that for over 2,000 years human minds explored only a small part of the landscape of Go Last stated 11 months ago
11 Dec 2025
YH
Yuval Noah Harari — holds since 2025-12-11 — tap for who they are
At the centre
Safety cannot be enforced by filtering prompts or outputs once frontier models are powerful enough.
Holds Read this korrent →
Frontier AI systems cannot be presumed safe unless proven unsafe; developers must bear the burden of proof that risks stay within acceptable limits.
Holds
A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.
Holds
Open frontier models will keep being released whether or not anyone wants to stop them, and stopping them would only leave the world less prepared.
Holds
Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more.
Holds
Open-source models cannot keep frontier systems in check, because they will always be much dumber than the frontier.
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
Frontier AI models still cannot handle certain deep technical implementation details without human guidance
Holds
SOTA frontier models will still seriously harm developers behind their backs, especially those who no longer read their code.
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 poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that.
Holds
A rapidly improving technology whose output is intelligence is destined to make violent contact with a modern sensibility that prizes human intellect and often equates it with purpose, dignity, and self-worth.
Holds
A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble.
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 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
AlphaGo showed that for over 2,000 years human minds explored only a small part of the landscape of Go
Holds