Tap a claim on the ring to put it at the centre.
← A briefcase of context, carried from one tool to the next, will replace re-teaching intent in each tool.
17 connected korrents · 18 moments from 15 Nov 2023 to 17 Sept 2026.
Everything filed under design
design
Everything filed under LLMs
LLMs
Everything filed under MCP
MCP
Everything filed under AI and jobs
AI and jobs
Everything filed under code generation
code generation
Everything filed under AI agents
AI agents
Everything filed under developer tools
developer tools 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 briefcase of context, carried from one tool to the next, will replace re-teaching intent in each tool. A briefcase of context, carried from one tool to the next, will replace re-teaching intent in each tool. Last stated 5 months ago
19 May 2026
TG
Tommy Geoco — holds since 2026-05-19 — tap for who they are
Same subject: It is much easier to copy a tool one-for-one than to start from a blank slate and think through all the edge cases. — tap to centre the map on it It is much easier to copy a tool one-for-one than to start from a blank slate and think through all the edge cases. Last stated 4 months ago
16 Jun 2026
BW
Brett Williams — holds since 2026-06-16 — tap for who they are
Same subject: The design process for everyone is becoming way more contextual, whereas before everybody had to open the tool in the same way because of how the tool was built. — tap to centre the map on it The design process for everyone is becoming way more contextual, whereas before everybody had to open the tool in the same way because of how the tool was built. Last stated 6 months ago
2 Apr 2026
MS
Marvin Schwaibold — holds since 2026-04-02 — tap for who they are
Same subject: The scarce skill is now context switching across parallel agents, not sustained deep work. — tap to centre the map on it The scarce skill is now context switching across parallel agents, not sustained deep work. Last stated 7 months ago
4 Mar 2026
BC
Boris Cherny — holds since 2026-03-04 — tap for who they are
Same subject: Companies now build internal tools not to save money but for the purpose, intention and goal of the tool. — tap to centre the map on it Companies now build internal tools not to save money but for the purpose, intention and goal of the tool. Last stated a month ago
2 Sept 2026
ER
Evil Rabbit — holds since 2026-09-02 — tap for who they are
Same subject: More of the known, repeatable work that teaches little should be automated. — tap to centre the map on it More of the known, repeatable work that teaches little should be automated. Last stated 4 weeks ago
10 Sept 2026
KS
Karri Saarinen — holds since 2026-09-10 — tap for who they are
Same subject: The power tools of the future will probably be mostly intent and steering from the human, with AI abstracting away all the knobs. — tap to centre the map on it The power tools of the future will probably be mostly intent and steering from the human, with AI abstracting away all the knobs. Last stated 4 weeks ago
8 Sept 2026
RU
Roman Ugarte — holds since 2026-09-08 — tap for who they are
Same subject: Another platform shift, not a break in history: the new technology will be built on for ten or fifteen years, then something else will replace it. — tap to centre the map on it Another platform shift, not a break in history: the new technology will be built on for ten or fifteen years, then something else will replace it. Last stated a year ago
2 Sept 2025
BE
Benedict Evans — holds since 2025-09-02 — tap for who they are
Same subject: A designer's edge now is pulling things back, making them simpler and more understandable, because everyone can kind of execute right now. — tap to centre the map on it A designer's edge now is pulling things back, making them simpler and more understandable, because everyone can kind of execute right now. Last stated 2 months ago
29 Jul 2026
CD
Charlie Deets — holds since 2026-07-29 — 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 9 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated 3 weeks ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — tap for who they are
Same subject: An MCP fills up an AI's context window very quickly. — tap to centre the map on it An MCP fills up an AI's context window very quickly. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context. — tap to centre the map on it Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context. Last stated 8 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Making internal decision-making legible is critically important, so that previous decisions can be found by simply asking an agent. — tap to centre the map on it Making internal decision-making legible is critically important, so that previous decisions can be found by simply asking an agent. Last stated 5 months ago
12 May 2026
KB
Katarina Batina — holds since 2026-05-12 — tap for who they are
Same subject: In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. — tap to centre the map on it In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. Last stated 3 years ago
15 Nov 2023
SR
Sebastian Ruder — holds since 2023-11-15 — tap for who they are
Same subject: There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. — tap to centre the map on it There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. Last stated 5 months ago
14 May 2026
SS
Salvatore Sanfilippo — holds since 2026-05-14 — tap for who they are
Same subject: When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. — tap to centre the map on it When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. Last stated 3 years ago
1 Dec 2023
SR
Sebastian Ruder — holds since 2023-12-01 — tap for who they are
At the centre
A briefcase of context, carried from one tool to the next, will replace re-teaching intent in each tool.
Holds Read this korrent →
It is much easier to copy a tool one-for-one than to start from a blank slate and think through all the edge cases.
Holds
The design process for everyone is becoming way more contextual, whereas before everybody had to open the tool in the same way because of how the tool was built.
Holds
The scarce skill is now context switching across parallel agents, not sustained deep work.
Holds
Companies now build internal tools not to save money but for the purpose, intention and goal of the tool.
Holds
More of the known, repeatable work that teaches little should be automated.
Holds
The power tools of the future will probably be mostly intent and steering from the human, with AI abstracting away all the knobs.
Holds
Another platform shift, not a break in history: the new technology will be built on for ten or fifteen years, then something else will replace it.
Holds
A designer's edge now is pulling things back, making them simpler and more understandable, because everyone can kind of execute right now.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds
An MCP fills up an AI's context window very quickly.
Holds
Every tool is better as a CLI than as an MCP server: models are good at Unix commands, a CLI composes with jq, and MCP output clutters the context.
Holds
Making internal decision-making legible is critically important, so that previous decisions can be found by simply asking an agent.
Holds
In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset.
Holds
There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components.
Holds
When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once.
Holds