Tap a claim on the ring to put it at the centre.
← RLVR is so expensive that it is usually not run for multiple epochs.
17 connected korrents · 15 moments from 1 Oct 2023 to 26 Oct 2026.
Everything filed under reinforcement learning
reinforcement learning
Everything filed under AI alignment
AI alignment
Everything filed under robotics
robotics
Everything filed under scaling laws
scaling laws
Everything filed under software performance
software performance
Everything filed under LLMs
LLMs
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: RLVR is so expensive that it is usually not run for multiple epochs.
RLVR is so expensive that it is usually not run for multiple epochs.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: RLVR is much simpler than RLHF because it needs no reward model, which is why it is attractive in practice. — tap to centre the map on it
RLVR is much simpler than RLHF because it needs no reward model, which is why it is attractive in practice.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — tap for who they are
Same subject: Use RLVR to train large state-of-the-art models, but for a smaller model distilling from a bigger one can give better results than RLVR from scratch. — tap to centre the map on it
Use RLVR to train large state-of-the-art models, but for a smaller model distilling from a bigger one can give better results than RLVR from scratch.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: RLHF is not reinforcement learning in the magical sense, because it cannot be run indefinitely. — tap to centre the map on it
RLHF is not reinforcement learning in the magical sense, because it cannot be run indefinitely.
Last stated 2 years ago
5 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-05 — tap for who they are
Same subject: Unreal Engine's deepest limitation is that game simulation still runs on a single core, because single-threaded programming is orders of magnitude easier than multi-threaded. — tap to centre the map on it
Unreal Engine's deepest limitation is that game simulation still runs on a single core, because single-threaded programming is orders of magnitude easier than multi-threaded.
Last stated 2 years ago
30 Apr 2025
TS
Tim Sweeney — holds since 2025-04-30 — tap for who they are
Same subject: Today's RL environments are better than 2024's because we learned what to build and put AI labour on building it, not because labs hired more human experts. — tap to centre the map on it
Today's RL environments are better than 2024's because we learned what to build and put AI labour on building it, not because labs hired more human experts.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Distilling from a model's reasoning traces gets there quicker and cheaper than reinforcement learning, which is why labs that invest in RL complain about it. — tap to centre the map on it
Distilling from a model's reasoning traces gets there quicker and cheaper than reinforcement learning, which is why labs that invest in RL complain about it.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: Instability in small-scale RL training does not necessarily mean the algorithm is wrong; the scale may be too small to see its benefits. — tap to centre the map on it
Instability in small-scale RL training does not necessarily mean the algorithm is wrong; the scale may be too small to see its benefits.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: A published training-run cost always understates the truth, because any notable model takes two to four times that run's compute in experiments alone. — tap to centre the map on it
A published training-run cost always understates the truth, because any notable model takes two to four times that run's compute in experiments alone.
Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — 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: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated a month ago
9 Oct 2026
CR
Carl Rivera — holds since 2026-10-09 — tap for who they are
Same subject: A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies. — tap to centre the map on it
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated a year ago
8 Jul 2025
RG
Ryan Greenblatt — holds since 2025-07-08 — tap for who they are
Same subject: A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm. — tap to centre the map on it
A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm.
Last stated 4 weeks ago
26 Oct 2026
NL
Nathan Lambert — holds since 2026-10-26 — tap for who they are
Same subject: A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas. — tap to centre the map on it
A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas.
Last stated 3 years ago
1 Oct 2023
TC
Tyler Cowen — holds since 2023-10-01 — tap for who they are
Same subject: A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it. — tap to centre the map on it
A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it.
Last stated 2 years ago
6 Apr 2025
MH
Molson Hart — holds since 2025-04-06 — tap for who they are
Same subject: A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. — tap to centre the map on it
A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases.
Last stated 4 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — 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
RLVR is so expensive that it is usually not run for multiple epochs.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Read this korrent →
Similar wording
RLVR is much simpler than RLHF because it needs no reward model, which is why it is attractive in practice.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Similar wording
Use RLVR to train large state-of-the-art models, but for a smaller model distilling from a bigger one can give better results than RLVR from scratch.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
RLHF is not reinforcement learning in the magical sense, because it cannot be run indefinitely.
Last stated 5 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Similar wording
Unreal Engine's deepest limitation is that game simulation still runs on a single core, because single-threaded programming is orders of magnitude easier than multi-threaded.
Last stated 30 Apr 2025 · 2 years ago
Holds Tim Sweeney
Similar wording
Today's RL environments are better than 2024's because we learned what to build and put AI labour on building it, not because labs hired more human experts.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
Distilling from a model's reasoning traces gets there quicker and cheaper than reinforcement learning, which is why labs that invest in RL complain about it.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
Instability in small-scale RL training does not necessarily mean the algorithm is wrong; the scale may be too small to see its benefits.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
A published training-run cost always understates the truth, because any notable model takes two to four times that run's compute in experiments alone.
Last stated 3 Feb 2025 · 2 years ago
Holds Nathan Lambert
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: AI alignment
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated 9 Oct 2026 · a month ago
Holds Carl Rivera
Same subject: AI alignment
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated 8 Jul 2025 · a year ago
Holds Ryan Greenblatt
Same subject: AI alignment
A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm.
Last stated 26 Oct 2026 · 4 weeks ago
Holds Nathan Lambert
Same subject: robotics
A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas.
Last stated 1 Oct 2023 · 3 years ago
Holds Tyler Cowen
Same subject: robotics
A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it.
Last stated 6 Apr 2025 · 2 years ago
Holds Molson Hart
Same subject: robotics
A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases.
Last stated 3 Aug 2026 · 4 months ago
Holds Dmitri Dolgov