Tap a claim on the ring to put it at the centre.
← Start a new chat whenever you switch topics, so old tokens do not distract the model.
17 connected korrents · 16 moments from 26 Jun 2023 to 2 Nov 2026.
Everything filed under chat interfaces
chat interfaces
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
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: Start a new chat whenever you switch topics, so old tokens do not distract the model.
Start a new chat whenever you switch topics, so old tokens do not distract the model.
Last stated 2 years ago
27 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-27 — tap for who they are
Same subject: In AI products, much can often be done with the model directly in the conversation rather than through new bespoke UI, though there is a balance. — tap to centre the map on it
In AI products, much can often be done with the model directly in the conversation rather than through new bespoke UI, though there is a balance.
Last stated 7 months ago
8 Apr 2026
IS
Ian Silber — holds since 2026-04-08 — tap for who they are
Same subject: You should probably start a new agent conversation for a new feature, or when the agent goes off track. — tap to centre the map on it
You should probably start a new agent conversation for a new feature, or when the agent goes off track.
Last stated 7 months ago
15 Apr 2026
LR
Lee Robinson — holds since 2026-04-15 — tap for who they are
Same subject: Use your voice instead of typing to talk to language models; it works quite well. — tap to centre the map on it
Use your voice instead of typing to talk to language models; it works quite well.
Last stated 2 years ago
27 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-27 — tap for who they are
Same subject: Reading every DM is worth the time even when you cannot reply to them all, because it is where you learn what to fix, whom to hire and where to invest. — tap to centre the map on it
Reading every DM is worth the time even when you cannot reply to them all, because it is where you learn what to fix, whom to hire and where to invest.
Last stated 3 months ago
29 Aug 2026
GR
Guillermo Rauch — holds since 2026-08-29 — tap for who they are
Same subject: A language model is not a person: it has no persistent existence, booting up for a conversation and then shutting off. — tap to centre the map on it
A language model is not a person: it has no persistent existence, booting up for a conversation and then shutting off.
Last stated 2 years ago
5 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-05 — tap for who they are
Same subject: When an AI model is stuck, switching to a different model often works. — tap to centre the map on it
When an AI model is stuck, switching to a different model often works.
Last stated 2 years ago
25 Apr 2025
TB
Tom Blomfield — holds since 2025-04-25 — tap for who they are
Same subject: Despite the push to move away from chat interfaces, chat is still the right way to interact with a fleet of agents carrying out tasks defined ahead of time. — tap to centre the map on it
Despite the push to move away from chat interfaces, chat is still the right way to interact with a fleet of agents carrying out tasks defined ahead of time.
Last stated 3 months ago
25 Aug 2026
JB
John Bai — holds since 2026-08-25 — tap for who they are
Same subject: LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest. — tap to centre the map on it
LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest.
Last stated 8 months ago
25 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-25 — tap for who they are
Same subject: A blank chat box is lazy: it violates the first rule of a good user experience, that it is obvious what you can do. — tap to centre the map on it
A blank chat box is lazy: it violates the first rule of a good user experience, that it is obvious what you can do.
Last stated 2 years ago
12 May 2025
JZ
Julie Zhuo — holds since 2025-05-12 — tap for who they are
Same subject: A business, not its AI vendor, bears legal responsibility when an integrated AI tool causes harm to a customer. — tap to centre the map on it
A business, not its AI vendor, bears legal responsibility when an integrated AI tool causes harm to a customer.
Last stated 8 months ago
20 Mar 2026
AK
Arvid Kahl — holds since 2026-03-20 — tap for who they are
Same subject: A chatbot used for troubleshooting is like a friend who knows more but is not one's smartest friend and sometimes proposes dumb theories. — tap to centre the map on it
A chatbot used for troubleshooting is like a friend who knows more but is not one's smartest friend and sometimes proposes dumb theories.
Last stated 3 weeks ago
2 Nov 2026
CN
Cal Newport — holds since 2026-11-02 — tap for who they are
Same subject: Chatbot interfaces are the wrong tool for meaningful coding work, because you are mostly hoping the model recalls the right answer and correcting it requires a human in the loop. — tap to centre the map on it
Chatbot interfaces are the wrong tool for meaningful coding work, because you are mostly hoping the model recalls the right answer and correcting it requires a human in the loop.
Last stated 10 months ago
5 Feb 2026
MH
Mitchell Hashimoto — holds since 2026-02-05 — tap for who they are
Same subject: ChatGPT exploded because of its obvious chat interface, not its technology, which had launched earlier in a different wrapper that few noticed. — tap to centre the map on it
ChatGPT exploded because of its obvious chat interface, not its technology, which had launched earlier in a different wrapper that few noticed.
Last stated 2 years ago
12 May 2025
JZ
Julie Zhuo — holds since 2025-05-12 — tap for who they are
Same subject: Half the population in rich countries is not articulate enough in writing to use prompt-driven AI well. — tap to centre the map on it
Half the population in rich countries is not articulate enough in writing to use prompt-driven AI well.
Last stated 3 years ago
26 Jun 2023
JN
Jakob Nielsen — holds since 2023-06-26 — tap for who they are
Same subject: AI chatbots are tuned to produce an answer that feels satisfying to the user rather than one that is correct. — tap to centre the map on it
AI chatbots are tuned to produce an answer that feels satisfying to the user rather than one that is correct.
Last stated 2 months ago
15 Sept 2026
ML
Michael Lopp — holds since 2026-09-15 — tap for who they are
Same subject: Machines capable of both high-level cognitive tasks and physical dexterity will be produced in large numbers in the relatively near future. — tap to centre the map on it
Machines capable of both high-level cognitive tasks and physical dexterity will be produced in large numbers in the relatively near future.
Last stated a year ago
31 Jul 2025
YM
Yascha Mounk — holds since 2025-07-31 — tap for who they are
Same subject: Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens. — tap to centre the map on it
Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens.
Last stated a year ago
12 Sept 2025
SL
Sergey Levine — holds since 2025-09-12 — 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
Start a new chat whenever you switch topics, so old tokens do not distract the model.
Last stated 27 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Read this korrent →
Similar wording
In AI products, much can often be done with the model directly in the conversation rather than through new bespoke UI, though there is a balance.
Last stated 8 Apr 2026 · 7 months ago
Holds Ian Silber
Similar wording
You should probably start a new agent conversation for a new feature, or when the agent goes off track.
Last stated 15 Apr 2026 · 7 months ago
Holds Lee Robinson
Similar wording
Use your voice instead of typing to talk to language models; it works quite well.
Last stated 27 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Similar wording
Reading every DM is worth the time even when you cannot reply to them all, because it is where you learn what to fix, whom to hire and where to invest.
Last stated 29 Aug 2026 · 3 months ago
Holds Guillermo Rauch
Similar wording
A language model is not a person: it has no persistent existence, booting up for a conversation and then shutting off.
Last stated 5 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Similar wording
When an AI model is stuck, switching to a different model often works.
Last stated 25 Apr 2025 · 2 years ago
Holds Tom Blomfield
Similar wording
Despite the push to move away from chat interfaces, chat is still the right way to interact with a fleet of agents carrying out tasks defined ahead of time.
Last stated 25 Aug 2026 · 3 months ago
Holds John Bai
Similar wording
LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest.
Last stated 25 Mar 2026 · 8 months ago
Holds Andrej Karpathy
Same subject: chat interfaces
A blank chat box is lazy: it violates the first rule of a good user experience, that it is obvious what you can do.
Last stated 12 May 2025 · 2 years ago
Holds Julie Zhuo
Same subject: chat interfaces
A business, not its AI vendor, bears legal responsibility when an integrated AI tool causes harm to a customer.
Last stated 20 Mar 2026 · 8 months ago
Holds Arvid Kahl
Same subject: chat interfaces
A chatbot used for troubleshooting is like a friend who knows more but is not one's smartest friend and sometimes proposes dumb theories.
Last stated 2 Nov 2026 · 3 weeks ago
Holds Cal Newport
Same subject: OpenAI
Chatbot interfaces are the wrong tool for meaningful coding work, because you are mostly hoping the model recalls the right answer and correcting it requires a human in the loop.
Last stated 5 Feb 2026 · 10 months ago
Holds Mitchell Hashimoto
Same subject: OpenAI
ChatGPT exploded because of its obvious chat interface, not its technology, which had launched earlier in a different wrapper that few noticed.
Last stated 12 May 2025 · 2 years ago
Holds Julie Zhuo
Same subject: OpenAI
Half the population in rich countries is not articulate enough in writing to use prompt-driven AI well.
Last stated 26 Jun 2023 · 3 years ago
Holds Jakob Nielsen
Same subject: robotics
AI chatbots are tuned to produce an answer that feels satisfying to the user rather than one that is correct.
Last stated 15 Sept 2026 · 2 months ago
Holds Michael Lopp
Same subject: robotics
Machines capable of both high-level cognitive tasks and physical dexterity will be produced in large numbers in the relatively near future.
Last stated 31 Jul 2025 · a year ago
Holds Yascha Mounk
Same subject: robotics
Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens.
Last stated 12 Sept 2025 · a year ago
Holds Sergey Levine