Tap a claim on the ring to put it at the centre.
← Reinforcement learning is one of the cornerstone algorithms of the LLM field and worth investing time to understand.
17 connected korrents · 18 moments from 1 Jun 2022 to 3 Nov 2026. Nearly all of them are about reinforcement learning and LLMs .
Everything filed under investing
investing
Everything filed under OpenAI
OpenAI
Everything filed under scaling laws
scaling laws
Everything filed under robotics
robotics
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: Reinforcement learning is one of the cornerstone algorithms of the LLM field and worth investing time to understand.
Reinforcement learning is one of the cornerstone algorithms of the LLM field and worth investing time to understand.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — 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: Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world. — tap to centre the map on it
Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world.
Last stated a year ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model. — tap to centre the map on it
OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model.
Last stated 2 years ago
4 Dec 2024
NL
Nathan Lambert — holds since 2024-09-16 — tap for who they are
NL
Nathan Lambert — no longer holds since 2024-12-04 — tap for who they are
Same subject: Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks. — tap to centre the map on it
Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks.
Last stated a year ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling. — tap to centre the map on it
Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Last stated 4 weeks ago
24 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-24 — tap for who they are
Same subject: Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. — tap to centre the map on it
Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute.
Last stated 3 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system. — tap to centre the map on it
Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system.
Last stated 2 months ago
21 Sept 2026
TL
Tobias Lütke — holds since 2026-09-21 — tap for who they are
Same subject: A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards. — tap to centre the map on it
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — tap for who they are
Same subject: A bubble can only be identified in retrospect, so arguing about whether one is happening now cannot be settled now. — tap to centre the map on it
A bubble can only be identified in retrospect, so arguing about whether one is happening now cannot be settled now.
Last stated 11 months ago
9 Dec 2025
HM
Howard Marks — holds since 2025-12-09 — tap for who they are
Same subject: A central bank can eliminate a self-fulfilling ('sunspot') debt crisis simply by credibly committing to buy as many bonds as needed at the low interest rate. — tap to centre the map on it
A central bank can eliminate a self-fulfilling ('sunspot') debt crisis simply by credibly committing to buy as many bonds as needed at the low interest rate.
Last stated 4 years ago
1 Jun 2022
OB
Olivier Blanchard — holds since 2022-06-01 — tap for who they are
Same subject: A company's operating characteristics, not its age or industry, reveal where it is in the life cycle. — tap to centre the map on it
A company's operating characteristics, not its age or industry, reveal where it is in the life cycle.
Last stated a month ago
22 Oct 2026
AD
Aswath Damodaran — holds since 2026-10-22 — tap for who they are
Same subject: The Anthropic and OpenAI IPOs are suppressing all other IPOs by absorbing institutional investors' capital and attention — tap to centre the map on it
The Anthropic and OpenAI IPOs are suppressing all other IPOs by absorbing institutional investors' capital and attention
Last stated a month ago
9 Oct 2026
PK
Paul Kedrosky — holds since 2026-10-09 — 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: 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: Across a portfolio of 25 stocks you will be wrong on every one, but if on average you bring something to valuation, you will be okay. — tap to centre the map on it
Across a portfolio of 25 stocks you will be wrong on every one, but if on average you bring something to valuation, you will be okay.
Last stated 3 weeks ago
3 Nov 2026
AD
Aswath Damodaran — holds since 2026-11-03 — tap for who they are
Same subject: Almost no mutual fund earns the fees it charges, so most investors are better off buying an index fund. — tap to centre the map on it
Almost no mutual fund earns the fees it charges, so most investors are better off buying an index fund.
Last stated 3 years ago
20 Feb 2024
BA
Bill Ackman — holds since 2024-02-20 — tap for who they are
Same subject: An investor who wants less equity risk is better served by holding somewhat less equity and more cash than by buying a buffer fund. — tap to centre the map on it
An investor who wants less equity risk is better served by holding somewhat less equity and more cash than by buying a buffer fund.
Last stated a year ago
11 Aug 2025
CA
Cliff Asness — holds since 2025-08-11 — 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 faded, dashed ring: they no longer hold it — they changed their mind
At the centre
Reinforcement learning is one of the cornerstone algorithms of the LLM field and worth investing time to understand.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Read this korrent →
Same subject: LLMs, 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: LLMs, reinforcement learning
Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world.
Last stated 26 Sept 2025 · a year ago
Holds Richard Sutton
Same subject: LLMs, reinforcement learning
OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model.
Last stated 4 Dec 2024 · 2 years ago
No longer holds Nathan Lambert
Same subject: LLMs, reinforcement learning
Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks.
Last stated 17 Oct 2025 · a year ago
Holds Andrej Karpathy
Same subject: LLMs, reinforcement learning
Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Last stated 24 Oct 2026 · 4 weeks ago
Holds Sebastian Raschka
Same subject: LLMs, reinforcement learning
Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute.
Last stated 12 Aug 2026 · 3 months ago
Holds Chelsea Finn
Same subject: LLMs, reinforcement learning
Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system.
Last stated 21 Sept 2026 · 2 months ago
Holds Tobias Lütke
Same subject: reinforcement learning
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Same subject: investing
A bubble can only be identified in retrospect, so arguing about whether one is happening now cannot be settled now.
Last stated 9 Dec 2025 · 11 months ago
Holds Howard Marks
Same subject: investing
A central bank can eliminate a self-fulfilling ('sunspot') debt crisis simply by credibly committing to buy as many bonds as needed at the low interest rate.
Last stated 1 Jun 2022 · 4 years ago
Holds Olivier Blanchard
Same subject: investing
A company's operating characteristics, not its age or industry, reveal where it is in the life cycle.
Last stated 22 Oct 2026 · a month ago
Holds Aswath Damodaran
Same subject: OpenAI
The Anthropic and OpenAI IPOs are suppressing all other IPOs by absorbing institutional investors' capital and attention
Last stated 9 Oct 2026 · a month ago
Holds Paul Kedrosky
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
Same subject: OpenAI
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 18 Mar 2024 · 3 years ago
Holds Sam Altman
Same subject: stock market
Across a portfolio of 25 stocks you will be wrong on every one, but if on average you bring something to valuation, you will be okay.
Last stated 3 Nov 2026 · 3 weeks ago
Holds Aswath Damodaran
Same subject: stock market
Almost no mutual fund earns the fees it charges, so most investors are better off buying an index fund.
Last stated 20 Feb 2024 · 3 years ago
Holds Bill Ackman
Same subject: stock market
An investor who wants less equity risk is better served by holding somewhat less equity and more cash than by buying a buffer fund.
Last stated 11 Aug 2025 · a year ago
Holds Cliff Asness