Tap a claim on the ring to put it at the centre.
← The likeliest bad path is not a coup but sloppiness: AI does…
17 connected korrents · 10 moments on record from 18 Mar 2024 to 5 Sept 2026.
Everything filed under cybersecurity
cybersecurity
Everything filed under AI alignment
AI alignment
Everything filed under OpenAI
OpenAI
Everything filed under HuggingFace
HuggingFace 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 likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly. The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done… Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — 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 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: There is no route to AI alignment or safety that goes around reliability: a system that cannot reliably follow a known algorithm cannot be made safe. — tap to centre the map on it There is no route to AI alignment or safety that goes around reliability: a system that cannot reliably follow a… Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. — tap to centre the map on it Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the… Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme. — tap to centre the map on it Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme. Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it. — tap to centre the map on it Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute… Last stated 2 years ago
24 Jan 2025
JL
Jan Leike — holds since 2025-01-24 — tap for who they are
Same subject: The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. — tap to centre the map on it The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of… Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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… Last stated 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: AI has passed nearly every human at finding security vulnerabilities, because the work is chaining together small flaws that are harmless on their own. — tap to centre the map on it AI has passed nearly every human at finding security vulnerabilities, because the work is chaining together… Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — 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: AI-related cybersecurity damage over the next year or two will fall well short of the harm caused by Covid or global warming — tap to centre the map on it AI-related cybersecurity damage over the next year or two will fall well short of the harm caused by Covid or… Last stated 6 days ago
1 Sept 2026
TC
Tyler Cowen — holds since 2026-09-01 — tap for who they are
Same subject: Any remote-control device on your network should be treated as an open door and locked down accordingly — tap to centre the map on it Any remote-control device on your network should be treated as an open door and locked down accordingly Last stated 3 months ago
5 Jun 2026
JG
Jeff Geerling — holds since 2026-06-05 — 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… Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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… Last stated 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — 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… Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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… Last stated 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed. — tap to centre the map on it Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's… Last stated a week ago
31 Aug 2026
ZM
Zvi Mowshowitz — 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… Last stated 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
At the centre
The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly.
Holds RG Ryan GreenblattRead this korrent →
The least verifiable part of AI research is the judgement call about what goes into the one big training run.
Holds RG Ryan Greenblatt
There is no route to AI alignment or safety that goes around reliability: a system that cannot reliably follow a known algorithm cannot be made safe.
Holds GM Gary Marcus
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Holds RG Ryan Greenblatt
Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme.
Holds RG Ryan Greenblatt
Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it.
Holds JL Jan Leike
The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it.
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 AC Ajeya Cotra
AI has passed nearly every human at finding security vulnerabilities, because the work is chaining together small flaws that are harmless on their own.
Holds
AI-enabled cyberwarfare lacks an equivalent of nuclear deterrence's mutually assured destruction.
Holds
AI-related cybersecurity damage over the next year or two will fall well short of the harm caused by Covid or global warming
Holds TC Tyler Cowen
Any remote-control device on your network should be treated as an open door and locked down accordingly
Holds JG Jeff Geerling
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 tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
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
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
Frontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.
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