Tap a claim on the ring to put it at the centre.
← Today's AI systems are significantly under-elicited for their ability to automate AI R&D.
17 connected korrents · 17 moments from 27 Nov 2025 to 31 Oct 2026.
Everything filed under LLMs
LLMs
Everything filed under recursive self-improvement
recursive self-improvement
Everything filed under AI agents
AI agents
Everything filed under AGI
AGI
Everything filed under OpenAI
OpenAI
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: Today's AI systems are significantly under-elicited for their ability to automate AI R&D.
Today's AI systems are significantly under-elicited for their ability to automate AI R&D.
Last stated 3 months ago
10 Aug 2026
JC
Jack Clark — holds since 2026-08-10 — tap for who they are
Same subject: AI agents trained on an expert's published work can only automate a small fraction of that expert's actual job. — tap to centre the map on it
AI agents trained on an expert's published work can only automate a small fraction of that expert's actual job.
Last stated 12 months ago
27 Nov 2025
BG
Brendan Gregg — holds since 2025-11-27 — tap for who they are
Same subject: The current capabilities of existing AI models are barely being used and are often not even well understood. — tap to centre the map on it
The current capabilities of existing AI models are barely being used and are often not even well understood.
Last stated 2 months ago
18 Sept 2026
EM
Ethan Mollick — holds since 2026-09-18 — tap for who they are
Same subject: Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet. — tap to centre the map on it
Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet.
Last stated 9 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Having the very best AI model and harness does not result in better or faster execution and can slow teams down — tap to centre the map on it
Having the very best AI model and harness does not result in better or faster execution and can slow teams down
Last stated 2 months ago
19 Sept 2026
GO
Gergely Orosz — holds since 2026-09-19 — tap for who they are
Same subject: Today's AI systems are highly capable at engineering but lack the intuitive creativity needed to be good researchers, tending toward rote, formulaic thinking. — tap to centre the map on it
Today's AI systems are highly capable at engineering but lack the intuitive creativity needed to be good researchers, tending toward rote, formulaic thinking.
Last stated 4 months ago
3 Aug 2026
JC
Jack Clark — holds since 2026-08-03 — tap for who they are
Same subject: There is essentially no cognitive task humans do where AI improvement is failing to transfer at all. — tap to centre the map on it
There is essentially no cognitive task humans do where AI improvement is failing to transfer at all.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: People trying to use AI to automate knowledge work or simplify their job are very early adopters, and their tolerance for sub-par experiences is quite high. — tap to centre the map on it
People trying to use AI to automate knowledge work or simplify their job are very early adopters, and their tolerance for sub-par experiences is quite high.
Last stated 7 months ago
14 Apr 2026
BL
Brian Lovin — holds since 2026-04-14 — tap for who they are
Same subject: Inconsistent output from an AI product is not necessarily bad; it is how AI behaves. — tap to centre the map on it
Inconsistent output from an AI product is not necessarily bad; it is how AI behaves.
Last stated 3 weeks ago
31 Oct 2026
MN
Marily Nika — holds since 2026-10-31 — tap for who they are
Same subject: AI systems are getting good at performing increasingly automated science, as they already have at automated AI R&D. — tap to centre the map on it
AI systems are getting good at performing increasingly automated science, as they already have at automated AI R&D.
Last stated 2 months ago
5 Oct 2026
JC
Jack Clark — holds since 2026-10-05 — tap for who they are
Same subject: As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves. — tap to centre the map on it
As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves.
Last stated 3 months ago
17 Aug 2026
JC
Jack Clark — holds since 2026-08-17 — tap for who they are
Same subject: Human parity on discovery benchmarks like DiG-bench will be reached by mid-2027, marking the point where recursive self-improvement in AI seriously kicks off. — tap to centre the map on it
Human parity on discovery benchmarks like DiG-bench will be reached by mid-2027, marking the point where recursive self-improvement in AI seriously kicks off.
Last stated 3 months ago
17 Aug 2026
JC
Jack Clark — holds since 2026-08-17 — tap for who they are
Same subject: A ban on self-recursive improvement in AI models would create a big incentive for some other parts of the world to invest a lot more in compute. — tap to centre the map on it
A ban on self-recursive improvement in AI models would create a big incentive for some other parts of the world to invest a lot more in compute.
Last stated 2 months ago
22 Sept 2026
TC
Tyler Cowen — holds since 2026-09-22 — tap for who they are
Same subject: A sealed machine that redesigns itself will eventually redesign everything that touches its seal. — tap to centre the map on it
A sealed machine that redesigns itself will eventually redesign everything that touches its seal.
Last stated a month ago
21 Oct 2026
BM
Bruno Maçães — holds since 2026-10-21 — tap for who they are
Same subject: AI adoption and acceleration should be monitored across the whole AI stack, because that is when futurists expect things to go much faster: once AI fully automates making more AI. — tap to centre the map on it
AI adoption and acceleration should be monitored across the whole AI stack, because that is when futurists expect things to go much faster: once AI fully automates making more AI.
Last stated 9 months ago
17 Feb 2026
AC
Ajeya Cotra — holds since 2026-02-17 — tap for who they are
Same subject: Internal models at Anthropic and OpenAI are improving even faster than AI overall, with early recursive self-improvement beginning over the summer. — tap to centre the map on it
Internal models at Anthropic and OpenAI are improving even faster than AI overall, with early recursive self-improvement beginning over the summer.
Last stated 2 months ago
14 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-14 — tap for who they are
Same subject: Recursive self-improvement has already started, because AI research itself is now being automated. — tap to centre the map on it
Recursive self-improvement has already started, because AI research itself is now being automated.
Last stated 2 months ago
13 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-13 — tap for who they are
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Last stated a month ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
Today's AI systems are significantly under-elicited for their ability to automate AI R&D.
Last stated 10 Aug 2026 · 3 months ago
Holds Jack Clark
Read this korrent →
Similar wording
AI agents trained on an expert's published work can only automate a small fraction of that expert's actual job.
Last stated 27 Nov 2025 · 12 months ago
Holds Brendan Gregg
Similar wording
The current capabilities of existing AI models are barely being used and are often not even well understood.
Last stated 18 Sept 2026 · 2 months ago
Holds Ethan Mollick
Similar wording
Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet.
Last stated 12 Feb 2026 · 9 months ago
Holds Peter Steinberger
Similar wording
Having the very best AI model and harness does not result in better or faster execution and can slow teams down
Last stated 19 Sept 2026 · 2 months ago
Holds Gergely Orosz
Similar wording
Today's AI systems are highly capable at engineering but lack the intuitive creativity needed to be good researchers, tending toward rote, formulaic thinking.
Last stated 3 Aug 2026 · 4 months ago
Holds Jack Clark
Similar wording
There is essentially no cognitive task humans do where AI improvement is failing to transfer at all.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
People trying to use AI to automate knowledge work or simplify their job are very early adopters, and their tolerance for sub-par experiences is quite high.
Last stated 14 Apr 2026 · 7 months ago
Holds Brian Lovin
Similar wording
Inconsistent output from an AI product is not necessarily bad; it is how AI behaves.
Last stated 31 Oct 2026 · 3 weeks ago
Holds Marily Nika
Same subject: AI and science
AI systems are getting good at performing increasingly automated science, as they already have at automated AI R&D.
Last stated 5 Oct 2026 · 2 months ago
Holds Jack Clark
Same subject: AI and science
As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves.
Last stated 17 Aug 2026 · 3 months ago
Holds Jack Clark
Same subject: AI and science
Human parity on discovery benchmarks like DiG-bench will be reached by mid-2027, marking the point where recursive self-improvement in AI seriously kicks off.
Last stated 17 Aug 2026 · 3 months ago
Holds Jack Clark
Same subject: recursive self-improvement
A ban on self-recursive improvement in AI models would create a big incentive for some other parts of the world to invest a lot more in compute.
Last stated 22 Sept 2026 · 2 months ago
Holds Tyler Cowen
Same subject: recursive self-improvement
A sealed machine that redesigns itself will eventually redesign everything that touches its seal.
Last stated 21 Oct 2026 · a month ago
Holds Bruno Maçães
Same subject: recursive self-improvement
AI adoption and acceleration should be monitored across the whole AI stack, because that is when futurists expect things to go much faster: once AI fully automates making more AI.
Last stated 17 Feb 2026 · 9 months ago
Holds Ajeya Cotra
Same subject: OpenAI
Internal models at Anthropic and OpenAI are improving even faster than AI overall, with early recursive self-improvement beginning over the summer.
Last stated 14 Sept 2026 · 2 months ago
Holds Zvi Mowshowitz
Same subject: OpenAI
Recursive self-improvement has already started, because AI research itself is now being automated.
Last stated 13 Sept 2026 · 2 months ago
Holds Zvi Mowshowitz Jan Leike
Same subject: OpenAI
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Last stated 21 Oct 2026 · a month ago
Holds Peter Steinberger