Tap a claim on the ring to put it at the centre.
← An agent told to disagree with everything is worthless: it has to form…
17 connected korrents · 15 moments on record from 22 Apr 2024 to 1 Sept 2026.
Everything filed under AI agents
AI agents
Everything filed under Microsoft
Microsoft
Everything filed under prompt injection
prompt injection
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under JavaScript
JavaScript
Everything filed under taste
taste
Everything filed under LLMs
LLMs 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: An agent told to disagree with everything is worthless: it has to form its own view and speak only when that view differs enough to be worth the interruption. An agent told to disagree with everything is worthless: it has to form its own view and speak only when that view differs enough to be worth the interruption. Last stated 4 weeks ago
9 Aug 2026
SP
Sunil Pai — holds since 2026-08-09 — tap for who they are
Same subject: Organisational dissent suits an AI precisely because it pays none of the costs -- no promotion to want, no ego, no performance review -- that silence the humans who do it. — tap to centre the map on it Organisational dissent suits an AI precisely because it pays none of the costs -- no promotion to want, no ego, no performance review -- that silence the humans who do it. Last stated 4 weeks ago
9 Aug 2026
SP
Sunil Pai — holds since 2026-08-09 — tap for who they are
Same subject: When somebody accuses you of being arrogant about an idea, almost all they ever mean is that they disagree with you. — tap to centre the map on it When somebody accuses you of being arrogant about an idea, almost all they ever mean is that they disagree with you. Last stated 2 years ago
22 Apr 2024
SC
Sean Carroll — holds since 2024-04-22 — 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: Nobody is convinced in real time on Twitter: a good argument is a seed lobbed over the barricades that grows months later, so plant it and wait. — tap to centre the map on it Nobody is convinced in real time on Twitter: a good argument is a seed lobbed over the barricades that grows months later, so plant it and wait. Last stated 2 years ago
18 Sept 2024
DH
David Heinemeier Hansson — holds since 2024-09-18 — 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: When agents do the building, the scarce skill is taste: choosing which problem is worth the time at all. — tap to centre the map on it When agents do the building, the scarce skill is taste: choosing which problem is worth the time at all. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. — tap to centre the map on it An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — tap for who they are
Same subject: Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side. — tap to centre the map on it Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side. Last stated 5 months ago
28 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-28 — tap for who they are
Same subject: A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. — tap to centre the map on it A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. — tap to centre the map on it A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. — tap to centre the map on it If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. Last stated a week ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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
Same subject: Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. — tap to centre the map on it Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. Last stated a month ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions. — tap to centre the map on it Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions. Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — tap for who they are
Same subject: A big switch to desktop Linux is coming, at least among developers, because there is enough dissatisfaction with both Apple and Microsoft. — tap to centre the map on it A big switch to desktop Linux is coming, at least among developers, because there is enough dissatisfaction with both Apple and Microsoft. Last stated a year ago
26 Jun 2025
DH
David Heinemeier Hansson — holds since 2025-06-26 — tap for who they are
Same subject: A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models. — tap to centre the map on it A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models. Last stated 6 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A hired chief executive can become the author of a company's culture by giving it a re-founding event, as Satya Nadella and Jamie Dimon did. — tap to centre the map on it A hired chief executive can become the author of a company's culture by giving it a re-founding event, as Satya Nadella and Jamie Dimon did. Last stated 12 months ago
18 Sept 2025
TL
Tobias Lütke — holds since 2025-09-18 — tap for who they are
At the centre
An agent told to disagree with everything is worthless: it has to form its own view and speak only when that view differs enough to be worth the interruption.
Holds Read this korrent →
Organisational dissent suits an AI precisely because it pays none of the costs -- no promotion to want, no ego, no performance review -- that silence the humans who do it.
Holds
When somebody accuses you of being arrogant about an idea, almost all they ever mean is that they disagree with you.
Holds SC Sean Carroll
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
Nobody is convinced in real time on Twitter: a good argument is a seed lobbed over the barricades that grows months later, so plant it and wait.
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
When agents do the building, the scarce skill is taste: choosing which problem is worth the time at all.
Holds JD Jeff Dean
An agent can understand a maximally simplified explanation and still be unable to come up with it — that gap is what is left of the expert's job.
Holds
Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side.
Holds
A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses.
Holds AC Ajeya Cotra
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Holds AC Ajeya Cotra
If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months.
Holds AC Ajeya Cotra
Auto-mode does not yet convincingly fix prompt-injection risk for coding agents.
Holds
Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack.
Holds
Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions.
Holds
A big switch to desktop Linux is coming, at least among developers, because there is enough dissatisfaction with both Apple and Microsoft.
Holds
A company that handed its engineers Copilot and thinks it is now moving faster will be destroyed by the people using frontier models.
Holds SY Steve Yegge
A hired chief executive can become the author of a company's culture by giving it a re-founding event, as Satya Nadella and Jamie Dimon did.
Holds