Tap a claim on the ring to put it at the centre.
← A reasoning model that always reasons can be wasteful on simple…
17 connected korrents · 16 moments from 26 Aug 2022 to 24 Oct 2026.
Everything filed under LLMs
LLMs
Everything filed under design
design
Everything filed under reinforcement learning
reinforcement learning
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: A reasoning model that always reasons can be wasteful on simple prompts, so models with different effort levels are useful.
A reasoning model that always reasons can be wasteful on simple prompts, so models with different effort levels are useful.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: Choosing which model to use for a task matters, and high reasoning effort may be too much for some work. — tap to centre the map on it
Choosing which model to use for a task matters, and high reasoning effort may be too much for some work.
Last stated a year ago
25 Aug 2025
LR
Lee Robinson — holds since 2025-08-25 — tap for who they are
Same subject: In general, the more capable a model is, the less reasoning it needs to do explicitly. — tap to centre the map on it
In general, the more capable a model is, the less reasoning it needs to do explicitly.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — 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: 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: Try a model without reasoning first, and switch to a reasoning model if it does not solve the problem. — tap to centre the map on it
Try a model without reasoning first, and switch to a reasoning model if it does not solve the problem.
Last stated 2 years ago
27 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-27 — tap for who they are
Same subject: More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost. — tap to centre the map on it
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost.
Last stated a year ago
19 Aug 2025
JA
Jay Alammar — holds since 2025-08-19 — tap for who they are
Same subject: Most reasoning models are still trained on code and math, and it would be interesting to go beyond those domains. — tap to centre the map on it
Most reasoning models are still trained on code and math, and it would be interesting to go beyond those domains.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: The aha moment for reasoning models will come from computer use and robotics rather than from scientific discovery, because those are the infinitely verifiable playgrounds. — tap to centre the map on it
The aha moment for reasoning models will come from computer use and robotics rather than from scientific discovery, because those are the infinitely verifiable playgrounds.
Last stated 2 years ago
3 Feb 2025
DP
Dylan Patel — holds since 2025-02-03 — tap for who they are
Same subject: A $1,299, 100-gram pair of slip-on glasses seems far more enticing than a $3,699, 700-gram headset strapped to the face. — tap to centre the map on it
A $1,299, 100-gram pair of slip-on glasses seems far more enticing than a $3,699, 700-gram headset strapped to the face.
Last stated 2 months ago
24 Sept 2026
MS
M.G. Siegler — holds since 2026-09-24 — tap for who they are
Same subject: A baby-step version of eval-driven design is to sketch out 10 to 20 hero flows and run the feature or interaction through them to see where it falls apart. — tap to centre the map on it
A baby-step version of eval-driven design is to sketch out 10 to 20 hero flows and run the feature or interaction through them to see where it falls apart.
Last stated 2 months ago
9 Sept 2026
EB
Ed Bayes — holds since 2026-09-09 — tap for who they are
Same subject: A black background with green text is easy on the eyes for writing. — tap to centre the map on it
A black background with green text is easy on the eyes for writing.
Last stated 4 years ago
26 Aug 2022
CP
Christopher Paolini — holds since 2022-08-26 — tap for who they are
Same subject: Not showing the code and exact details of what the agent ran in the ChatGPT UI is a lack of transparency and an anti-feature. — tap to centre the map on it
Not showing the code and exact details of what the agent ran in the ChatGPT UI is a lack of transparency and an anti-feature.
Last stated 2 months ago
12 Sept 2026
SW
Simon Willison — holds since 2026-09-12 — tap for who they are
Same subject: OpenAI was wrong to ship Dots as a section inside the ChatGPT app instead of as a separate app. — tap to centre the map on it
OpenAI was wrong to ship Dots as a section inside the ChatGPT app instead of as a separate app.
Last stated a month ago
22 Oct 2026
KB
Kayvon Beykpour — holds since 2026-10-22 — tap for who they are
Same subject: Software is even more susceptible to design convergence than hardware, which often took decades to converge. — tap to centre the map on it
Software is even more susceptible to design convergence than hardware, which often took decades to converge.
Last stated a month ago
9 Oct 2026
LW
Luke Wroblewski — holds since 2026-10-09 — tap for who they are
Same subject: Being able to put your thinking into writing that does not read as written by Claude is a green flag in a design candidate. — tap to centre the map on it
Being able to put your thinking into writing that does not read as written by Claude is a green flag in a design candidate.
Last stated 2 months ago
29 Sept 2026
DM
Danny Martinez — holds since 2026-09-29 — tap for who they are
Same subject: Claude has surprisingly good design taste for SwiftUI applications. — tap to centre the map on it
Claude has surprisingly good design taste for SwiftUI applications.
Last stated 8 months ago
27 Mar 2026
SW
Simon Willison — holds since 2026-03-27 — tap for who they are
Same subject: Claude tends to have good default taste in web page design. — tap to centre the map on it
Claude tends to have good default taste in web page design.
Last stated 2 years ago
11 Mar 2025
SW
Simon Willison — holds since 2025-03-11 — 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
At the centre
A reasoning model that always reasons can be wasteful on simple prompts, so models with different effort levels are useful.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Read this korrent →
Similar wording
Choosing which model to use for a task matters, and high reasoning effort may be too much for some work.
Last stated 25 Aug 2025 · a year ago
Holds Lee Robinson
Similar wording
In general, the more capable a model is, the less reasoning it needs to do explicitly.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Similar wording
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
Similar wording
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
Similar wording
Try a model without reasoning first, and switch to a reasoning model if it does not solve the problem.
Last stated 27 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Similar wording
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost.
Last stated 19 Aug 2025 · a year ago
Holds Jay Alammar
Similar wording
Most reasoning models are still trained on code and math, and it would be interesting to go beyond those domains.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
The aha moment for reasoning models will come from computer use and robotics rather than from scientific discovery, because those are the infinitely verifiable playgrounds.
Last stated 3 Feb 2025 · 2 years ago
Holds Dylan Patel
Same subject: design
A $1,299, 100-gram pair of slip-on glasses seems far more enticing than a $3,699, 700-gram headset strapped to the face.
Last stated 24 Sept 2026 · 2 months ago
Holds M.G. Siegler
Same subject: design
A baby-step version of eval-driven design is to sketch out 10 to 20 hero flows and run the feature or interaction through them to see where it falls apart.
Last stated 9 Sept 2026 · 2 months ago
Holds Ed Bayes
Same subject: design
A black background with green text is easy on the eyes for writing.
Last stated 26 Aug 2022 · 4 years ago
Holds Christopher Paolini
Same subject: OpenAI
Not showing the code and exact details of what the agent ran in the ChatGPT UI is a lack of transparency and an anti-feature.
Last stated 12 Sept 2026 · 2 months ago
Holds Simon Willison
Same subject: OpenAI
OpenAI was wrong to ship Dots as a section inside the ChatGPT app instead of as a separate app.
Last stated 22 Oct 2026 · a month ago
Holds Kayvon Beykpour
Same subject: OpenAI
Software is even more susceptible to design convergence than hardware, which often took decades to converge.
Last stated 9 Oct 2026 · a month ago
Holds Luke Wroblewski
Same subject: Anthropic
Being able to put your thinking into writing that does not read as written by Claude is a green flag in a design candidate.
Last stated 29 Sept 2026 · 2 months ago
Holds Danny Martinez
Same subject: Anthropic
Claude has surprisingly good design taste for SwiftUI applications.
Last stated 27 Mar 2026 · 8 months ago
Holds Simon Willison
Same subject: Anthropic
Claude tends to have good default taste in web page design.
Last stated 11 Mar 2025 · 2 years ago
Holds Simon Willison