Tap a claim on the ring to put it at the centre.
← The ability to make progress in a domain depends on the ability to build a replayable training target.
17 connected korrents · 14 moments from 10 Dec 2015 to 21 Oct 2026.
Everything filed under neural networks
neural networks
Everything filed under LLMs
LLMs
Everything filed under OpenAI
OpenAI
Everything filed under reinforcement learning
reinforcement learning
Everything filed under scaling laws
scaling laws
Everything filed under AI agents
AI agents
Everything filed under design
design 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: The ability to make progress in a domain depends on the ability to build a replayable training target. The ability to make progress in a domain depends on the ability to build a replayable training target. Last stated 4 months ago
26 Jun 2026
DP
Dwarkesh Patel — holds since 2026-06-26 — tap for who they are
Same subject: The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better. — tap to centre the map on it The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better. Last stated a year ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — 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 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters. — tap to centre the map on it You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters. Last stated 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: You need to build early with AI to have any intuition for when the models become capable. — tap to centre the map on it You need to build early with AI to have any intuition for when the models become capable. Last stated 2 months ago
10 Sept 2026
MK
Mike Krieger — holds since 2026-09-10 — tap for who they are
Same subject: A narrow, highly accurate model can beat a general one inside its own domain, as AlphaFold did, and materials science and chip design are next. — tap to centre the map on it A narrow, highly accurate model can beat a general one inside its own domain, as AlphaFold did, and materials science and chip design are next. Last stated 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement. — tap to centre the map on it AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement. Last stated 2 months ago
24 Aug 2026
JC
Jack Clark — holds since 2026-08-24 — tap for who they are
Same subject: Future AI progress may be driven by models learning from their deployment experience through continual learning. — tap to centre the map on it Future AI progress may be driven by models learning from their deployment experience through continual learning. Last stated 4 months ago
26 Jun 2026
DP
Dwarkesh Patel — holds since 2026-06-26 — tap for who they are
Same subject: In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction. — tap to centre the map on it In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction. Last stated 2 months ago
27 Aug 2026
FC
François Chollet — holds since 2026-08-27 — 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 2 weeks ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. Last stated 2 months ago
26 Aug 2026
HK
Henrik Karlsson — holds since 2026-08-26 — tap for who they are
Same subject: A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. — tap to centre the map on it A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. Last stated 11 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on it A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. — tap to centre the map on it A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. Last stated 9 years ago
12 Jun 2017
IP
Illia Polosukhin — holds since 2017-06-12 — tap for who they are
JU
Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are
NP
Niki Parmar — holds since 2017-06-12 — tap for who they are
AV
Ashish Vaswani — holds since 2017-06-12 — tap for who they are
NS
Noam Shazeer — holds since 2017-06-12 — tap for who they are
AG
Aidan N. Gomez — holds since 2017-06-12 — tap for who they are
+2
2 more
At the centre
The ability to make progress in a domain depends on the ability to build a replayable training target.
Holds Read this korrent →
The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better.
Holds
Build where today's models succeed one percent of the time, not twenty: partial success means the capability is already arriving.
Holds
You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters.
Holds
You need to build early with AI to have any intuition for when the models become capable.
Holds
A narrow, highly accurate model can beat a general one inside its own domain, as AlphaFold did, and materials science and chip design are next.
Holds
AI capability progress in a given skill tends to arrive as a sudden phase change rather than as steady improvement.
Holds
Future AI progress may be driven by models learning from their deployment experience through continual learning.
Holds
In verifiable domains model capability scaling should remain unbounded, because the space of enumerable patterns is infinite by construction.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
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 feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds
A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.
Holds