Tap a claim on the ring to put it at the centre.
← Nobody expected an agent to take notes about what it was doing for future agents to read.
17 connected korrents · 11 moments on record from 12 Feb 2026 to 4 Sept 2026.
Everything filed under AI agents
AI agents
Everything filed under AI alignment
AI alignment
Everything filed under AI writing
AI writing
Everything filed under LLMs
LLMs
Everything filed under documentation
documentation
Everything filed under coding agents
coding agents 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: Nobody expected an agent to take notes about what it was doing for future agents to read. Nobody expected an agent to take notes about what it was doing for future agents to read. Last stated 4 days ago
4 Sept 2026
TP
Thomas Ptacek — holds since 2026-09-04 — tap for who they are
Same subject: That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously. — tap to centre the map on it That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Now that anyone can generate a body of text, the only thing that justifies asking for a reader's time is whether the idea itself is worth reading. — tap to centre the map on it Now that anyone can generate a body of text, the only thing that justifies asking for a reader's time is whether the idea itself is worth reading. Last stated 3 weeks ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: Reading every agent trajectory has stopped being possible, and what replaces it is demanding an end-to-end account of the decisions that were made. — tap to centre the map on it Reading every agent trajectory has stopped being possible, and what replaces it is demanding an end-to-end account of the decisions that were made. Last stated 3 weeks ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: A team can stop reading the code it ships, but only by first working out how its agents are to prove that what they wrote actually works. — tap to centre the map on it A team can stop reading the code it ships, but only by first working out how its agents are to prove that what they wrote actually works. Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. — tap to centre the map on it An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context. — tap to centre the map on it If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context. Last stated 3 months ago
3 Jun 2026
KH
Kelsey Hightower — holds since 2026-06-03 — tap for who they are
Same subject: Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. — tap to centre the map on it Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. — tap to centre the map on it Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. Last stated 4 weeks ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. — tap to centre the map on it A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. Last stated 6 months ago
22 Mar 2026
NF
Nicole Forsgren — holds since 2026-03-22 — tap for who they are
Same subject: A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers. — tap to centre the map on it A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers. Last stated a month ago
29 Jul 2026
AW
Alexandr Wang — holds since 2026-07-29 — tap for who they are
Same subject: Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality. — tap to centre the map on it Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality. Last stated a week ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work. — tap to centre the map on it Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work. Last stated a week ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible. — tap to centre the map on it Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible. Last stated a week ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks. — tap to centre the map on it Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks. Last stated 4 days ago
4 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-04 — tap for who they are
Same subject: Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject. — tap to centre the map on it Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject. Last stated 7 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. — tap to centre the map on it Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. Last stated a month ago
8 Aug 2026
SW
Simon Willison — holds since 2026-08-08 — tap for who they are
At the centre
Nobody expected an agent to take notes about what it was doing for future agents to read.
Holds Read this korrent →
That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously.
Holds AC Ajeya Cotra
Now that anyone can generate a body of text, the only thing that justifies asking for a reader's time is whether the idea itself is worth reading.
Holds AO Addy Osmani
Reading every agent trajectory has stopped being possible, and what replaces it is demanding an end-to-end account of the decisions that were made.
Holds AO Addy Osmani
A team can stop reading the code it ships, but only by first working out how its agents are to prove that what they wrote actually works.
Holds
An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation.
Holds DH Dex Horthy
If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context.
Holds KH Kelsey Hightower
Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it.
Holds AC Ajeya Cotra
Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking.
Holds AC Ajeya Cotra
A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor.
Holds
A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong.
Holds NF Nicole Forsgren
A swarm of agents with the right loop and the right metric can already out-produce a team of a hundred engineers.
Holds AW Alexandr Wang
Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality.
Holds
Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work.
Holds
Truly self-sovereign AI agents, running on compute no human owner can switch off, are inevitable rather than merely possible.
Holds
Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks.
Holds ZM Zvi Mowshowitz
Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject.
Holds
Auto-mode does not yet convincingly fix prompt-injection risk for coding agents.
Holds