Tap a claim on the ring to put it at the centre.
← Deep learning can learn almost any modality of data and translate between modalities.
17 connected korrents · 16 moments from 10 Dec 2015 to 21 Oct 2026.
Everything filed under neural networks
neural networks
Everything filed under LLMs
LLMs
Everything filed under curiosity
curiosity
Everything filed under optimism
optimism
Everything filed under chat interfaces
chat interfaces
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: Deep learning can learn almost any modality of data and translate between modalities.
Deep learning can learn almost any modality of data and translate between modalities.
Last stated 2 years ago
27 Jan 2025
JH
Jensen Huang — holds since 2025-01-27 — tap for who they are
Same subject: Until AI learns from something richer than text, its limited data will leave it struggling with the richness of language. — tap to centre the map on it
Until AI learns from something richer than text, its limited data will leave it struggling with the richness of language.
Last stated 6 years ago
18 Dec 2020
MS
Marcus du Sautoy — holds since 2020-12-18 — tap for who they are
Same subject: We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning. — tap to centre the map on it
We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning.
Last stated a year ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Current AI models cannot produce insights beyond human understanding, however impressive they seem — tap to centre the map on it
Current AI models cannot produce insights beyond human understanding, however impressive they seem
Last stated a year ago
23 Jun 2025
EM
Ethan Mollick — holds since 2025-06-23 — tap for who they are
Same subject: People often seem to focus on what AI can execute and not on what it can teach them. — tap to centre the map on it
People often seem to focus on what AI can execute and not on what it can teach them.
Last stated 2 months ago
10 Sept 2026
KS
Karri Saarinen — holds since 2026-09-10 — tap for who they are
Same subject: Almost everybody can benefit from AI in some way. — tap to centre the map on it
Almost everybody can benefit from AI in some way.
Last stated a month ago
21 Oct 2026
DS
Dharmesh Shah — holds since 2026-10-21 — tap for who they are
Same subject: Current AI models do not actually understand things and still hallucinate. — tap to centre the map on it
Current AI models do not actually understand things and still hallucinate.
Last stated a year ago
13 Oct 2025
SG
Saul Griffith — holds since 2025-10-13 — tap for who they are
Same subject: The hope for AI interfaces is that people will not have to pick a modality up front, and can move fluidly between chat, point-and-click and voice. — tap to centre the map on it
The hope for AI interfaces is that people will not have to pick a modality up front, and can move fluidly between chat, point-and-click and voice.
Last stated a year ago
10 Nov 2025
CR
Carl Rivera — holds since 2025-11-10 — tap for who they are
Same subject: The language best suited to AI is simply the one the models have seen most of in training, which is why they do so well on JavaScript, TypeScript and Python. — tap to centre the map on it
The language best suited to AI is simply the one the models have seen most of in training, which is why they do so well on JavaScript, TypeScript and Python.
Last stated 6 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — tap for who they are
Same subject: A curve, which is what a deep learning model is, is a very bad substrate for discrete computation. — tap to centre the map on it
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 2 years ago
6 Nov 2024
FC
François Chollet — holds since 2024-11-06 — 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 project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Last stated 3 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — 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 winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work. — tap to centre the map on it
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
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: Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases. — tap to centre the map on it
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Last stated 5 years ago
11 Jun 2021
GW
Gwern — holds since 2021-06-11 — 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
Same subject: Linear probes are very strong classifiers, and attention-head probes are even stronger. — tap to centre the map on it
Linear probes are very strong classifiers, and attention-head probes are even stronger.
Last stated 11 months ago
20 Dec 2025
NN
Neel Nanda — holds since 2025-12-20 — tap for who they are
Same subject: Self-attention can yield more interpretable models. — tap to centre the map on it
Self-attention can yield more interpretable models.
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
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
Deep learning can learn almost any modality of data and translate between modalities.
Last stated 27 Jan 2025 · 2 years ago
Holds Jensen Huang
Read this korrent →
Similar wording
Until AI learns from something richer than text, its limited data will leave it struggling with the richness of language.
Last stated 18 Dec 2020 · 6 years ago
Holds Marcus du Sautoy
Similar wording
We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning.
Last stated 26 Sept 2025 · a year ago
Holds Richard Sutton
Similar wording
Current AI models cannot produce insights beyond human understanding, however impressive they seem
Last stated 23 Jun 2025 · a year ago
Holds Ethan Mollick
Similar wording
People often seem to focus on what AI can execute and not on what it can teach them.
Last stated 10 Sept 2026 · 2 months ago
Holds Karri Saarinen
Similar wording
Almost everybody can benefit from AI in some way.
Last stated 21 Oct 2026 · a month ago
Holds Dharmesh Shah
Similar wording
Current AI models do not actually understand things and still hallucinate.
Last stated 13 Oct 2025 · a year ago
Holds Saul Griffith
Similar wording
The hope for AI interfaces is that people will not have to pick a modality up front, and can move fluidly between chat, point-and-click and voice.
Last stated 10 Nov 2025 · a year ago
Holds Carl Rivera
Similar wording
The language best suited to AI is simply the one the models have seen most of in training, which is why they do so well on JavaScript, TypeScript and Python.
Last stated 13 May 2026 · 6 months ago
Holds Anders Hejlsberg
Same subject: neural networks
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 6 Nov 2024 · 2 years ago
Holds François Chollet
Same subject: neural networks
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 10 Dec 2015 · 11 years ago
Holds Jian Sun Kaiming He
Same subject: neural networks
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Last stated 23 Aug 2026 · 3 months ago
Holds Kun Chen
Same subject: pruning
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 Mar 2018 · 9 years ago
Holds Michael Carbin Jonathan Frankle
Same subject: pruning
A winning ticket wins on its initial weights: the connections it keeps started at values that happen to make training work.
Last stated 9 Mar 2018 · 9 years ago
Holds Michael Carbin Jonathan Frankle
Same subject: pruning
Intelligence is the execution of small, simplicity-weighted programs found by search over smooth loss landscapes in overparameterized networks, approaching Bayes-optimal reasoning as scale increases.
Last stated 11 Jun 2021 · 5 years ago
Holds Gwern
Same subject: transformers
A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution.
Last stated 12 Jun 2017 · 9 years ago
Holds Illia Polosukhin Jakob Uszkoreit Niki Parmar Ashish Vaswani Noam Shazeer Aidan N. Gomez Llion Jones Łukasz Kaiser
Same subject: transformers
Linear probes are very strong classifiers, and attention-head probes are even stronger.
Last stated 20 Dec 2025 · 11 months ago
Holds Neel Nanda
Same subject: transformers
Self-attention can yield more interpretable models.
Last stated 12 Jun 2017 · 9 years ago
Holds Illia Polosukhin Jakob Uszkoreit Niki Parmar Ashish Vaswani Noam Shazeer Aidan N. Gomez Llion Jones Łukasz Kaiser