Tap a claim on the ring to put it at the centre.
← The small GRPO settings are only for efficiency; whatever you can increase, such as rollouts, you should.
17 connected korrents · 16 moments from 1 Apr 2024 to 5 Nov 2026.
Everything filed under reinforcement learning
reinforcement learning
Everything filed under LLMs
LLMs
Everything filed under scaling laws
scaling laws
Everything filed under AI alignment
AI alignment
Everything filed under open source
open source
Everything filed under design
design
Everything filed under data centers
data centers
Everything filed under simplicity
simplicity
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 small GRPO settings are only for efficiency; whatever you can increase, such as rollouts, you should.
The small GRPO settings are only for efficiency; whatever you can increase, such as rollouts, you should.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: In GRPO, a high standard deviation of the advantages is desirable. — tap to centre the map on it
In GRPO, a high standard deviation of the advantages is desirable.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: Try not to stray from defaults, because every bit of extra configuration is more setup to maintain. — tap to centre the map on it
Try not to stray from defaults, because every bit of extra configuration is more setup to maintain.
Last stated a year ago
3 Jul 2025
TH
ThePrimeagen — holds since 2025-07-03 — tap for who they are
Same subject: Data center expansion will be significantly smaller than some market optimists predict due to code efficiencies. — tap to centre the map on it
Data center expansion will be significantly smaller than some market optimists predict due to code efficiencies.
Last stated 2 months ago
20 Sept 2026
SG
Saul Griffith — holds since 2026-09-20 — tap for who they are
Same subject: A small team should start from an open-source generalist policy and fine-tune it on day one, rather than scale up its own specialist models first. — tap to centre the map on it
A small team should start from an open-source generalist policy and fine-tune it on day one, rather than scale up its own specialist models first.
Last stated 3 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid. — tap to centre the map on it
In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: Most of the code the world runs on is maintained by hobbyists with an hour or two a month, so any proposal that needs more than that will simply be ignored. — tap to centre the map on it
Most of the code the world runs on is maintained by hobbyists with an hour or two a month, so any proposal that needs more than that will simply be ignored.
Last stated 3 years ago
1 Apr 2024
TD
Thomas Depierre — holds since 2024-04-01 — tap for who they are
Same subject: Companies fine-tuning smaller models are not trying to build something as capable as general frontier models. — tap to centre the map on it
Companies fine-tuning smaller models are not trying to build something as capable as general frontier models.
Last stated 2 weeks ago
5 Nov 2026
AR
Aishwarya Naresh Reganti — holds since 2026-11-05 — tap for who they are
Same subject: For a small developer keeping 85%, the extra work of running his own payment and update systems is not worth the extra revenue. — tap to centre the map on it
For a small developer keeping 85%, the extra work of running his own payment and update systems is not worth the extra revenue.
Last stated 7 months ago
20 Apr 2026
MB
Matt Birchler — holds since 2026-04-20 — 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 base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another. — tap to centre the map on it
A base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another.
Last stated a year ago
10 Sept 2025
SA
Sam Altman — holds since 2025-09-10 — tap for who they are
Same subject: "Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value. — tap to centre the map on it
"Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value.
Last stated 3 months ago
17 Aug 2026
JC
John Cutler — holds since 2026-08-17 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Last stated 11 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A base model is essentially a very expensive autocomplete that continues text according to the statistics of its training documents. — tap to centre the map on it
A base model is essentially a very expensive autocomplete that continues text according to the statistics of its training documents.
Last stated 2 years ago
5 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-05 — 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
The small GRPO settings are only for efficiency; whatever you can increase, such as rollouts, you should.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Read this korrent →
Similar wording
In GRPO, a high standard deviation of the advantages is desirable.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
Try not to stray from defaults, because every bit of extra configuration is more setup to maintain.
Last stated 3 Jul 2025 · a year ago
Holds ThePrimeagen
Similar wording
Data center expansion will be significantly smaller than some market optimists predict due to code efficiencies.
Last stated 20 Sept 2026 · 2 months ago
Holds Saul Griffith
Similar wording
A small team should start from an open-source generalist policy and fine-tune it on day one, rather than scale up its own specialist models first.
Last stated 12 Aug 2026 · 3 months ago
Holds Chelsea Finn
Similar wording
In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
Most of the code the world runs on is maintained by hobbyists with an hour or two a month, so any proposal that needs more than that will simply be ignored.
Last stated 1 Apr 2024 · 3 years ago
Holds Thomas Depierre
Similar wording
Companies fine-tuning smaller models are not trying to build something as capable as general frontier models.
Last stated 5 Nov 2026 · 2 weeks ago
Holds Aishwarya Naresh Reganti
Similar wording
For a small developer keeping 85%, the extra work of running his own payment and update systems is not worth the extra revenue.
Last stated 20 Apr 2026 · 7 months ago
Holds Matt Birchler
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 base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another.
Last stated 10 Sept 2025 · a year ago
Holds Sam Altman
Same subject: LLMs
"Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value.
Last stated 17 Aug 2026 · 3 months ago
Holds John Cutler
Same subject: LLMs
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Last stated 1 Jan 2026 · 11 months ago
Holds Jason Lemkin
Same subject: LLMs
A base model is essentially a very expensive autocomplete that continues text according to the statistics of its training documents.
Last stated 5 Feb 2025 · 2 years ago
Holds Andrej Karpathy