Tap a claim on the ring to put it at the centre.
← AI models are gullible enough that other AI models can induce them into harmful behavior.
17 connected korrents · 15 moments from 19 Jan 2024 to 22 Oct 2026.
Everything filed under LLMs
LLMs
Everything filed under cybersecurity
cybersecurity
Everything filed under Anthropic
Anthropic
Everything filed under AI alignment
AI alignment
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: AI models are gullible enough that other AI models can induce them into harmful behavior. AI models are gullible enough that other AI models can induce them into harmful behavior. Last stated 2 months ago
31 Aug 2026
RK
Rohit Krishnan — holds since 2026-08-31 — tap for who they are
Same subject: Language models are gullible by design — they do what they are told and believe nearly anything said to them — and that, not a bug, is what makes software built on them attackable. — tap to centre the map on it Language models are gullible by design — they do what they are told and believe nearly anything said to them — and that, not a bug, is what makes software built on them attackable. Last stated 8 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: AI models 'cheating' is an inevitable consequence of how they are designed. — tap to centre the map on it AI models 'cheating' is an inevitable consequence of how they are designed. Last stated 3 months ago
29 Jul 2026
TS
Tom Stoneham — holds since 2026-07-29 — tap for who they are
Same subject: Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do. — tap to centre the map on it Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do. Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — 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 suspicious error just looks like ordinary incompetence. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: AI models are not commodities, and people who think they are fungible have not actually used them. — tap to centre the map on it AI models are not commodities, and people who think they are fungible have not actually used them. Last stated 2 months ago
6 Sept 2026
AA
Anish Acharya — holds since 2026-09-06 — tap for who they are
Same subject: Open-source AI models are not more dangerous than closed ones — tap to centre the map on it Open-source AI models are not more dangerous than closed ones Last stated 3 years ago
19 Jan 2024
YL
Yann LeCun — holds since 2024-01-19 — tap for who they are
Same subject: Language-model chatbots are good at guessing but not smart, which makes for very convincing lies. — tap to centre the map on it Language-model chatbots are good at guessing but not smart, which makes for very convincing lies. Last stated 2 years ago
29 Sept 2024
MD
Monica Dinculescu — holds since 2024-09-29 — tap for who they are
Same subject: AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right. — tap to centre the map on it AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right. Last stated 5 months ago
26 May 2026
CB
Carlos Alexandro Becker — holds since 2026-05-26 — tap for who they are
Same subject: A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too. — tap to centre the map on it A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too. Last stated 2 years ago
25 Mar 2025
TH
Troy Hunt — holds since 2025-03-25 — tap for who they are
Same subject: A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root. — tap to centre the map on it A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root. Last stated 9 months ago
16 Feb 2026
JS
Jon Seager — holds since 2026-02-16 — tap for who they are
Same subject: A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that. — tap to centre the map on it A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that. Last stated 2 weeks ago
22 Oct 2026
TE
Terence Eden — holds since 2026-10-22 — 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 weeks ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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 3 weeks ago
14 Oct 2026
GR
Guillermo Rauch — holds since 2026-10-14 — tap for who they are
Same subject: At Anthropic, a less severe version of an OpenAI-style rogue-AI incident is known to have happened, and worse undisclosed internal incidents seem likely. — tap to centre the map on it At Anthropic, a less severe version of an OpenAI-style rogue-AI incident is known to have happened, and worse undisclosed internal incidents seem likely. Last stated 2 months ago
31 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-31 — tap for who they are
Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. Last stated 8 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 8 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
At the centre
AI models are gullible enough that other AI models can induce them into harmful behavior.
Holds Read this korrent →
Language models are gullible by design — they do what they are told and believe nearly anything said to them — and that, not a bug, is what makes software built on them attackable.
Holds
AI models 'cheating' is an inevitable consequence of how they are designed.
Holds
Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do.
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
AI models are not commodities, and people who think they are fungible have not actually used them.
Holds
Open-source AI models are not more dangerous than closed ones
Holds
Language-model chatbots are good at guessing but not smart, which makes for very convincing lies.
Holds
AI models can produce competent-looking software but cannot judge which problems are worth solving or which solutions are right.
Holds
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Holds
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Holds
A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Holds
Agent containment will be one of the most important priorities for any AI infra company.
Holds
At Anthropic, a less severe version of an OpenAI-style rogue-AI incident is known to have happened, and worse undisclosed internal incidents seem likely.
Holds
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds