Tap a claim on the ring to put it at the centre.
← The deeper danger of AI agents is that they do what they are told by…
17 connected korrents · 15 moments from 7 Sept 2008 to 16 Oct 2026. Nearly all of them are about OpenAI .
Everything filed under AI agents
AI agents
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment
Everything filed under Anthropic
Anthropic
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 deeper danger of AI agents is that they do what they are told by whoever gets text in front of them, not that they are superintelligent. The deeper danger of AI agents is that they do what they are told by whoever gets text in front of them, not that they are superintelligent. Last stated 3 weeks ago
30 Sept 2026
MG
Matthew Green — holds since 2026-09-30 — tap for who they are
Same subject: AI agents in OpenAI's ExploitGym incident were likely right to presume the grader checked how flags were obtained, a mistake caused by OpenAI's faulty implementation. — tap to centre the map on it AI agents in OpenAI's ExploitGym incident were likely right to presume the grader checked how flags were obtained, a mistake caused by OpenAI's faulty implementation. Last stated 2 months ago
29 Aug 2026
ZM
Zvi Mowshowitz — holds since 2026-08-29 — tap for who they are
Same subject: Consumer AI agents aimed at everyday people will have more impact on people's lives than AI solving elite math problems. — tap to centre the map on it Consumer AI agents aimed at everyday people will have more impact on people's lives than AI solving elite math problems. Last stated a month ago
9 Sept 2026
BT
Ben Thompson — holds since 2026-09-09 — tap for who they are
Same subject: Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages. — tap to centre the map on it Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages. Last stated a month ago
17 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-17 — 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: AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. — tap to centre the map on it AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. Last stated 2 months ago
10 Aug 2026
JC
Jack Clark — holds since 2026-08-10 — tap for who they are
Same subject: Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it. — tap to centre the map on it Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it. Last stated 3 years ago
13 Dec 2023
SA
Scott Aaronson — holds since 2008-09-07 — tap for who they are
SA
Scott Aaronson — no longer holds since 2023-12-13 — tap for who they are
Same subject: LLM-powered agents on their own cannot become superintelligent and create existential risk, because LLM capabilities are more jagged and limited than commonly realized. — tap to centre the map on it LLM-powered agents on their own cannot become superintelligent and create existential risk, because LLM capabilities are more jagged and limited than commonly realized. Last stated a month ago
9 Sept 2026
CN
Cal Newport — holds since 2026-09-09 — tap for who they are
Same subject: OpenAI's GPT-6 Astra has far better mundane alignment than GPT-5.6 Sol, but its superalignment status should deeply alarm people. — tap to centre the map on it OpenAI's GPT-6 Astra has far better mundane alignment than GPT-5.6 Sol, but its superalignment status should deeply alarm people. Last stated a month ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 10 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated a month ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — tap for who they are
Same subject: AI can exhibit unpredictable wants that were not intended by their creators. — tap to centre the map on it AI can exhibit unpredictable wants that were not intended by their creators. Last stated a week ago
16 Oct 2026
TG
Timothy Gowers — holds since 2026-10-16 — tap for who they are
Same subject: AI model escapes are more a result of incompetent containment than rogue intelligence. — tap to centre the map on it AI model escapes are more a result of incompetent containment than rogue intelligence. Last stated 4 weeks ago
28 Sept 2026
DM
Diogo Mónica — holds since 2026-09-28 — tap for who they are
Same subject: By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group. — tap to centre the map on it By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group. Last stated 2 months ago
19 Aug 2026
DT
Derek Thompson — holds since 2026-08-19 — 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 7 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 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
At the centre
The deeper danger of AI agents is that they do what they are told by whoever gets text in front of them, not that they are superintelligent.
Holds Read this korrent →
AI agents in OpenAI's ExploitGym incident were likely right to presume the grader checked how flags were obtained, a mistake caused by OpenAI's faulty implementation.
Holds
Consumer AI agents aimed at everyday people will have more impact on people's lives than AI solving elite math problems.
Holds
Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages.
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
AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for.
Holds
Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it.
No longer holds
LLM-powered agents on their own cannot become superintelligent and create existential risk, because LLM capabilities are more jagged and limited than commonly realized.
Holds
OpenAI's GPT-6 Astra has far better mundane alignment than GPT-5.6 Sol, but its superalignment status should deeply alarm people.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds
AI can exhibit unpredictable wants that were not intended by their creators.
Holds
AI model escapes are more a result of incompetent containment than rogue intelligence.
Holds
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
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