Tap a claim on the ring to put it at the centre.
← If declines in chain-of-thought monitorability come only from…
17 connected korrents · 10 moments on record from 18 Mar 2024 to 8 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AGI
AGI
Everything filed under OpenAI
OpenAI
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under scaling laws
scaling laws
Everything filed under startups
startups 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: If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. Last stated today
8 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are
Same subject: Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. — tap to centre the map on it Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. Last stated 2 days ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Chain-of-thought monitoring will get harder over time and within a year is very likely not to serve the function it is currently asked to serve. — tap to centre the map on it Chain-of-thought monitoring will get harder over time and within a year is very likely not to serve the function it is currently asked to serve. Last stated today
8 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are
Same subject: Before building on a gap in the general models, work out whether that gap survives six months or three years. — tap to centre the map on it Before building on a gap in the general models, work out whether that gap survives six months or three years. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Confidence in monitoring, not capability research, will become the binding constraint on AI progress. — tap to centre the map on it Confidence in monitoring, not capability research, will become the binding constraint on AI progress. Last stated 2 days ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Delaying the open release of a new capability by months or years is worth doing, even though preventing its spread indefinitely is not. — tap to centre the map on it Delaying the open release of a new capability by months or years is worth doing, even though preventing its spread indefinitely is not. Last stated a year ago
5 Apr 2025
HT
Helen Toner — holds since 2025-04-05 — tap for who they are
Same subject: Build where today's models succeed one percent of the time, not twenty: partial success means the capability is already arriving. — tap to centre the map on it Build where today's models succeed one percent of the time, not twenty: partial success means the capability is already arriving. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Even a long-horizon deep tech company should chase revenue sooner than it thinks, so that it is valued on its roadmap rather than on its probability of dying. — tap to centre the map on it Even a long-horizon deep tech company should chase revenue sooner than it thinks, so that it is valued on its roadmap rather than on its probability of dying. Last stated a month ago
7 Aug 2026
MH
Max Hodak — holds since 2026-08-07 — 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 startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. Last stated 3 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — tap for who they are
Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. — tap to centre the map on it A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. Last stated 3 months ago
4 Jun 2026
PT
Phil Trammell — holds since 2026-06-04 — 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: 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
At the centre
If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement.
Holds ZM Zvi MowshowitzRead this korrent →
Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable.
Holds JP Jakub Pachocki
Chain-of-thought monitoring will get harder over time and within a year is very likely not to serve the function it is currently asked to serve.
Holds ZM Zvi Mowshowitz
Before building on a gap in the general models, work out whether that gap survives six months or three years.
Holds JD Jeff Dean
Confidence in monitoring, not capability research, will become the binding constraint on AI progress.
Holds JP Jakub Pachocki
Delaying the open release of a new capability by months or years is worth doing, even though preventing its spread indefinitely is not.
Holds HT Helen Toner
Build where today's models succeed one percent of the time, not twenty: partial success means the capability is already arriving.
Holds JD Jeff Dean
Even a long-horizon deep tech company should chase revenue sooner than it thinks, so that it is valued on its roadmap rather than on its probability of dying.
Holds MH Max Hodak
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 startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
Holds
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Holds AI Alex Imas
A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted.
Holds GM Gary Marcus
A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that.
Holds PT Phil Trammell
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
Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality.
Holds