Tap a claim on the ring to put it at the centre.
← Don't ask Claude for a design without context: give it as much context…
17 connected korrents · 15 moments from 21 Mar 2023 to 29 Sept 2026. Nearly all of them are about Anthropic and design .
Everything filed under LLMs
LLMs
Everything filed under coding agents
coding agents
Everything filed under hiring
hiring
Everything filed under taste
taste 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: Don't ask Claude for a design without context: give it as much context as you can, be prescriptive, and don't trust it to be an amazing designer on its own. Don't ask Claude for a design without context: give it as much context as you can, be prescriptive, and don't trust it to be an amazing designer on its own. Last stated 2 months ago
4 Aug 2026
NP
Nate Parrott — holds since 2026-08-04 — 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 6 days 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 6 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: Designers should code and ship, and a tool like Claude Design is for everything else, such as communicating an idea. — tap to centre the map on it Designers should code and ship, and a tool like Claude Design is for everything else, such as communicating an idea. Last stated 2 months ago
4 Aug 2026
NP
Nate Parrott — holds since 2026-08-04 — tap for who they are
Same subject: Every designer should use Claude Code if part of the team's end product is code, because it beats going back and forth with an engineer. — tap to centre the map on it Every designer should use Claude Code if part of the team's end product is code, because it beats going back and forth with an engineer. Last stated 2 months ago
4 Aug 2026
NP
Nate Parrott — holds since 2026-08-04 — tap for who they are
Same subject: Hiring managers can ask for a "design engineer" and mean two very different people: a designer who knows how to use Claude Code, or someone trained as an engineer who can design for themselves. — tap to centre the map on it Hiring managers can ask for a "design engineer" and mean two very different people: a designer who knows how to use Claude Code, or someone trained as an engineer who can design for themselves. Last stated 6 days ago
29 Sept 2026
DM
Danny Martinez — holds since 2026-09-29 — tap for who they are
Same subject: Sketching a fix in a design tool is probably quicker, and closer to the intended result, than going back and forth in words with an AI. — tap to centre the map on it Sketching a fix in a design tool is probably quicker, and closer to the intended result, than going back and forth in words with an AI. Last stated 4 months ago
9 Jun 2026
RG
Ron Goldin — holds since 2026-06-09 — tap for who they are
Same subject: The invisible thinking behind a product, the mental model, the interaction model and the base primitives, has long been the unsung hero of product designers. — tap to centre the map on it The invisible thinking behind a product, the mental model, the interaction model and the base primitives, has long been the unsung hero of product designers. Last stated 3 months ago
8 Jul 2026
MC
Meaghan Choi — holds since 2026-07-08 — 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: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. — tap to centre the map on it An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected. Last stated 4 years ago
21 Mar 2023
BC
Bryan Caplan — holds since 2023-03-21 — 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
Don't ask Claude for a design without context: give it as much context as you can, be prescriptive, and don't trust it to be an amazing designer on its own.
Holds Read this korrent →
Being able to put your thinking into writing that does not read as written by Claude is a green flag in a design candidate.
Holds
Claude has surprisingly good design taste for SwiftUI applications.
Holds
Claude tends to have good default taste in web page design.
Holds
Designers should code and ship, and a tool like Claude Design is for everything else, such as communicating an idea.
Holds
Every designer should use Claude Code if part of the team's end product is code, because it beats going back and forth with an engineer.
Holds
Hiring managers can ask for a "design engineer" and mean two very different people: a designer who knows how to use Claude Code, or someone trained as an engineer who can design for themselves.
Holds
Sketching a fix in a design tool is probably quicker, and closer to the intended result, than going back and forth in words with an AI.
Holds
The invisible thinking behind a product, the mental model, the interaction model and the base primitives, has long been the unsung hero of product designers.
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
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds
An AI can already earn an A on a university economics midterm, years earlier than informed forecasters expected.
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