Tap a claim on the ring to put it at the centre.
← Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there.
17 connected korrents · 14 moments from 18 Mar 2024 to 9 Sept 2026.
Everything filed under LLMs
LLMs
Everything filed under Anthropic
Anthropic
Everything filed under OpenAI
OpenAI
Everything filed under scaling laws
scaling laws
Everything filed under AI and jobs
AI and jobs 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: Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there. Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there. Last stated 6 months ago
14 Apr 2026
BL
Brian Lovin — holds since 2026-04-14 — tap for who they are
Same subject: A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. — tap to centre the map on it A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. Last stated 2 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance. — tap to centre the map on it You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance. Last stated 2 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: The medium of designing with models is nondeterministic enough that without real prompts flowing through it, an idea can look great in a design review and be completely different when users use it. — tap to centre the map on it The medium of designing with models is nondeterministic enough that without real prompts flowing through it, an idea can look great in a design review and be completely different when users use it. Last stated 4 weeks ago
9 Sept 2026
EB
Ed Bayes — holds since 2026-09-09 — tap for who they are
Same subject: A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt. — tap to centre the map on it A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt. Last stated 3 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — tap for who they are
Same subject: The ideas that end up mattering sound stupid at first, because that is where the value is locked up; copying the best with a tweak never works. — tap to centre the map on it The ideas that end up mattering sound stupid at first, because that is where the value is locked up; copying the best with a tweak never works. Last stated 2 months ago
26 Jul 2026
DH
David Heinemeier Hansson — holds since 2026-07-26 — tap for who they are
Same subject: The skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong. — tap to centre the map on it The skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong. Last stated 2 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: A detailed, specific AI prompt produces a better answer than a vague, simple one. — tap to centre the map on it A detailed, specific AI prompt produces a better answer than a vague, simple one. Last stated 10 months ago
3 Dec 2025
JE
Jason Evanish — holds since 2025-12-03 — tap for who they are
Same subject: Prompt engineering is not a durable skill, because a good product is one that works for the user who never learned to phrase a question. — tap to centre the map on it Prompt engineering is not a durable skill, because a good product is one that works for the user who never learned to phrase a question. Last stated 2 years ago
19 Jun 2024
AS
Aravind Srinivas — holds since 2024-06-19 — 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: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: Agents are going to be incorporated into mainstream interfaces — tap to centre the map on it Agents are going to be incorporated into mainstream interfaces Last stated 6 months ago
25 Mar 2026
DH
David Heinemeier Hansson — holds since 2026-03-25 — 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 10 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 3 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. — tap to centre the map on it A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. Last stated 7 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated a month ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
At the centre
Stupid prompts can work, because they flip the right bits so that the model will extrapolate from there.
Holds Read this korrent →
A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.
Holds
You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance.
Holds
The medium of designing with models is nondeterministic enough that without real prompts flowing through it, an idea can look great in a design review and be completely different when users use it.
Holds
A simple request gives zero difference between a very powerful model and an older one, and the only way to utilize super intelligent models is a giant piece of prompt.
Holds
The ideas that end up mattering sound stupid at first, because that is where the value is locked up; copying the best with a tweak never works.
Holds
The skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong.
Holds
A detailed, specific AI prompt produces a better answer than a vague, simple one.
Holds
Prompt engineering is not a durable skill, because a good product is one that works for the user who never learned to phrase a question.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
Holds
Agents are going to be incorporated into mainstream interfaces
Holds
"Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next.
Holds
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Holds
A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from.
Holds
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds