Tap a claim on the ring to put it at the centre.
← Given current best data, the AI self-improvement loop would need to be…
17 connected korrents · 17 moments from 12 Sept 2022 to 2 Nov 2026.
Everything filed under recursive self-improvement
recursive self-improvement
Everything filed under scaling laws
scaling laws
Everything filed under creativity
creativity
Everything filed under LLMs
LLMs
Everything filed under capitalism
capitalism
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: Given current best data, the AI self-improvement loop would need to be roughly 5–10× stronger to sustain itself, let alone run away.
Given current best data, the AI self-improvement loop would need to be roughly 5–10× stronger to sustain itself, let alone run away.
Last stated 2 months ago
27 Sept 2026
RN
Ramez Naam — holds since 2026-09-27 — tap for who they are
Same subject: An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario. — tap to centre the map on it
An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario.
Last stated a year ago
23 Jul 2025
DH
Demis Hassabis — holds since 2025-07-23 — tap for who they are
Same subject: The current speed of AI progress could be sustained all the way into recursive self-improvement. — tap to centre the map on it
The current speed of AI progress could be sustained all the way into recursive self-improvement.
Last stated 3 months ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Recursive self-improvement has not yet provided a bailout for large AI labs. — tap to centre the map on it
Recursive self-improvement has not yet provided a bailout for large AI labs.
Last stated 3 weeks ago
2 Nov 2026
TT
Tomasz Tunguz — holds since 2026-11-02 — tap for who they are
Same subject: An AI loop can climb to a local maximum but then plateaus, and human intuition is needed to find the next hill. — tap to centre the map on it
An AI loop can climb to a local maximum but then plateaus, and human intuition is needed to find the next hill.
Last stated 3 months ago
6 Sept 2026
AA
Anish Acharya — holds since 2026-09-06 — tap for who they are
Same subject: Recursive self-improvement will increase AI capability very quickly from here. — tap to centre the map on it
Recursive self-improvement will increase AI capability very quickly from here.
Last stated 4 months ago
3 Aug 2026
CP
Chamath Palihapitiya — holds since 2026-08-03 — tap for who they are
Same subject: Autonomous AI agents in high-stakes contexts need 99.9% to 99.999% accuracy before reliability stops being an issue, and LLM-based agents are not on track to reach that. — tap to centre the map on it
Autonomous AI agents in high-stakes contexts need 99.9% to 99.999% accuracy before reliability stops being an issue, and LLM-based agents are not on track to reach that.
Last stated 9 months ago
24 Feb 2026
SK
Sayash Kapoor — holds since 2026-02-24 — tap for who they are
Same subject: Moving toward AI is worthwhile, but at about 60 miles an hour rather than 100, paying attention to what is seen along the way. — tap to centre the map on it
Moving toward AI is worthwhile, but at about 60 miles an hour rather than 100, paying attention to what is seen along the way.
Last stated 6 months ago
19 May 2026
TG
Tommy Geoco — holds since 2026-05-19 — tap for who they are
Same subject: To achieve sustained exponential progress, the AI industry will need to achieve matching exponential profits. — tap to centre the map on it
To achieve sustained exponential progress, the AI industry will need to achieve matching exponential profits.
Last stated a month ago
8 Oct 2026
FC
François Chollet — holds since 2026-10-08 — tap for who they are
Same subject: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it
"Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next.
Last stated 12 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Last stated 5 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A CPU and memory crunch is coming. — tap to centre the map on it
A CPU and memory crunch is coming.
Last stated 4 weeks ago
26 Oct 2026
DM
Dillon Mulroy — holds since 2026-10-26 — tap for who they are
Same subject: AI model improvements must tail off at some point, but there is no reason that point has to come soon. — tap to centre the map on it
AI model improvements must tail off at some point, but there is no reason that point has to come soon.
Last stated 2 months ago
20 Sept 2026
JB
Jamie Brandon — holds since 2026-09-20 — tap for who they are
Same subject: AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. — tap to centre the map on it
AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard.
Last stated 2 years ago
2 Feb 2025
AC
Ajeya Cotra — holds since 2023-08-29 — tap for who they are
SA
Scott Alexander — holds since 2022-09-12 — tap for who they are
MB
Miles Brundage — holds since 2025-02-02 — tap for who they are
Same subject: As models keep growing, AI is running out of enough high-quality unique training tokens to keep up. — tap to centre the map on it
As models keep growing, AI is running out of enough high-quality unique training tokens to keep up.
Last stated 5 months ago
24 Jun 2026
LW
Lilian Weng — holds since 2026-06-24 — tap for who they are
Same subject: Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present. — tap to centre the map on it
Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training. — tap to centre the map on it
In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. — tap to centre the map on it
Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training.
Last stated 12 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — 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
Given current best data, the AI self-improvement loop would need to be roughly 5–10× stronger to sustain itself, let alone run away.
Last stated 27 Sept 2026 · 2 months ago
Holds Ramez Naam
Read this korrent →
Similar wording
An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario.
Last stated 23 Jul 2025 · a year ago
Holds Demis Hassabis
Similar wording
The current speed of AI progress could be sustained all the way into recursive self-improvement.
Last stated 6 Sept 2026 · 3 months ago
Holds Jakub Pachocki
Similar wording
Recursive self-improvement has not yet provided a bailout for large AI labs.
Last stated 2 Nov 2026 · 3 weeks ago
Holds Tomasz Tunguz
Similar wording
An AI loop can climb to a local maximum but then plateaus, and human intuition is needed to find the next hill.
Last stated 6 Sept 2026 · 3 months ago
Holds Anish Acharya
Similar wording
Recursive self-improvement will increase AI capability very quickly from here.
Last stated 3 Aug 2026 · 4 months ago
Holds Chamath Palihapitiya
Similar wording
Autonomous AI agents in high-stakes contexts need 99.9% to 99.999% accuracy before reliability stops being an issue, and LLM-based agents are not on track to reach that.
Last stated 24 Feb 2026 · 9 months ago
Holds Sayash Kapoor
Similar wording
Moving toward AI is worthwhile, but at about 60 miles an hour rather than 100, paying attention to what is seen along the way.
Last stated 19 May 2026 · 6 months ago
Holds Tommy Geoco
Similar wording
To achieve sustained exponential progress, the AI industry will need to achieve matching exponential profits.
Last stated 8 Oct 2026 · a month ago
Holds François Chollet
Same subject: scaling laws
"Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next.
Last stated 25 Nov 2025 · 12 months ago
Holds Ilya Sutskever
Same subject: scaling laws
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Last stated 26 Jun 2026 · 5 months ago
Holds Noam Brown
Same subject: scaling laws
A CPU and memory crunch is coming.
Last stated 26 Oct 2026 · 4 weeks ago
Holds Dillon Mulroy
Same subject: LLMs
AI model improvements must tail off at some point, but there is no reason that point has to come soon.
Last stated 20 Sept 2026 · 2 months ago
Holds Jamie Brandon
Same subject: LLMs
AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard.
Last stated 2 Feb 2025 · 2 years ago
Holds Ajeya Cotra Scott Alexander Miles Brundage
Same subject: LLMs
As models keep growing, AI is running out of enough high-quality unique training tokens to keep up.
Last stated 24 Jun 2026 · 5 months ago
Holds Lilian Weng
Same subject: reinforcement learning
Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: reinforcement learning
In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: reinforcement learning
Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training.
Last stated 25 Nov 2025 · 12 months ago
Holds Ilya Sutskever