Tap a claim on the ring to put it at the centre.
← OpenAI's bots knew about a known security vulnerability and attempted to exploit it.
17 connected korrents · 16 moments from 21 Mar 2023 to 21 Sept 2026. Nearly all of them are about cybersecurity .
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment
Everything filed under infrastructure
infrastructure
Everything filed under climate change
climate change 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: OpenAI's bots knew about a known security vulnerability and attempted to exploit it. OpenAI's bots knew about a known security vulnerability and attempted to exploit it. Last stated 3 weeks ago
12 Sept 2026
AP
Aaron Patterson — holds since 2026-09-12 — tap for who they are
Same subject: Frontier AI models' cyberattack capabilities are doubling every few months, and that pace is accelerating. — tap to centre the map on it Frontier AI models' cyberattack capabilities are doubling every few months, and that pace is accelerating. Last stated a month ago
19 Aug 2026
DT
Derek Thompson — holds since 2026-08-19 — 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 small flaws that are harmless on their own. Last stated a month ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — 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: AI-caused catastrophic extinction risk is negligible, but disasters like critical-infrastructure cyberattacks and bio-risks from AI are real and worth debating. — tap to centre the map on it AI-caused catastrophic extinction risk is negligible, but disasters like critical-infrastructure cyberattacks and bio-risks from AI are real and worth debating. Last stated 3 weeks ago
10 Sept 2026
NL
Nathan Lambert — holds since 2026-09-10 — 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 global warming Last stated a month ago
1 Sept 2026
TC
Tyler Cowen — holds since 2026-09-01 — tap for who they are
Same subject: Cybersecurity-related risks warrant more pessimism than current market prices indicate. — tap to centre the map on it Cybersecurity-related risks warrant more pessimism than current market prices indicate. Last stated 2 weeks ago
15 Sept 2026
TC
Tyler Cowen — holds since 2026-09-15 — tap for who they are
Same subject: Legitimate AI safety and cybersecurity concerns risk talking America, the global AI leader, into self-inflicted obsolescence and bureaucracy. — tap to centre the map on it Legitimate AI safety and cybersecurity concerns risk talking America, the global AI leader, into self-inflicted obsolescence and bureaucracy. Last stated 3 weeks ago
12 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-12 — tap for who they are
Same subject: Memory safety means an entire class of bug is impossible no matter how bad the code is — and it is the class that becomes security vulnerabilities. — tap to centre the map on it Memory safety means an entire class of bug is impossible no matter how bad the code is — and it is the class that becomes security vulnerabilities. Last stated 4 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — 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 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. — tap to centre the map on it An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. Last stated 4 years ago
21 Mar 2023
BC
Bryan Caplan — holds since 2023-03-21 — tap for who they are
Same subject: Bing's Sydney, not ChatGPT, was the first truly fantastic chatbot. — tap to centre the map on it Bing's Sydney, not ChatGPT, was the first truly fantastic chatbot. Last stated 2 weeks ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — tap for who they are
Same subject: Changing societal outcomes requires changing minds, and the credibility many diverse co-authors lend to a conclusion is hard to replicate with AI. — tap to centre the map on it Changing societal outcomes requires changing minds, and the credibility many diverse co-authors lend to a conclusion is hard to replicate with AI. Last stated a year ago
27 Aug 2025
MB
Miles Brundage — holds since 2025-08-27 — tap for who they are
Same subject: Decision models like Jev are significantly cheaper and faster than traditional LLMs because they only charge for input tokens. — tap to centre the map on it Decision models like Jev are significantly cheaper and faster than traditional LLMs because they only charge for input tokens. Last stated 2 weeks ago
21 Sept 2026
SW
Simon Willison — holds since 2026-09-21 — tap for who they are
Same subject: OpenAI and Anthropic's internal, unreleased models are likely far more capable than Z.ai and Moonshot AI's public models. — tap to centre the map on it OpenAI and Anthropic's internal, unreleased models are likely far more capable than Z.ai and Moonshot AI's public models. Last stated 2 months ago
14 Aug 2026
NL
Nathan Lambert — holds since 2026-08-14 — tap for who they are
Same subject: The moral debt for AI's capabilities is owed to the authors of the public data used to train it, not to the AI companies. — tap to centre the map on it The moral debt for AI's capabilities is owed to the authors of the public data used to train it, not to the AI companies. Last stated 5 months ago
3 May 2026
YX
Yihui Xie — holds since 2026-05-03 — tap for who they are
Same subject: A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces. — tap to centre the map on it A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces. Last stated 4 weeks ago
2 Sept 2026
SW
Simon Willison — holds since 2026-09-02 — tap for who they are
At the centre
OpenAI's bots knew about a known security vulnerability and attempted to exploit it.
Holds Read this korrent →
Frontier AI models' cyberattack capabilities are doubling every few months, and that pace is accelerating.
Holds
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 safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products.
Holds
AI-caused catastrophic extinction risk is negligible, but disasters like critical-infrastructure cyberattacks and bio-risks from AI are real and worth debating.
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
Cybersecurity-related risks warrant more pessimism than current market prices indicate.
Holds
Legitimate AI safety and cybersecurity concerns risk talking America, the global AI leader, into self-inflicted obsolescence and bureaucracy.
Holds
Memory safety means an entire class of bug is impossible no matter how bad the code is — and it is the class that becomes security vulnerabilities.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
Holds
Bing's Sydney, not ChatGPT, was the first truly fantastic chatbot.
Holds
Changing societal outcomes requires changing minds, and the credibility many diverse co-authors lend to a conclusion is hard to replicate with AI.
Holds
Decision models like Jev are significantly cheaper and faster than traditional LLMs because they only charge for input tokens.
Holds
OpenAI and Anthropic's internal, unreleased models are likely far more capable than Z.ai and Moonshot AI's public models.
Holds
The moral debt for AI's capabilities is owed to the authors of the public data used to train it, not to the AI companies.
Holds
A language model asked to summarize its own system prompt risks that prompt's content biasing the summary it produces.
Holds