Tap a claim on the ring to put it at the centre.
← Connecting a conversational LLM to systems that have real-world…
17 connected korrents · 13 moments on record from 17 Feb 2023 to 1 Sept 2026. Nearly all of them are about chat interfaces .
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under OpenAI
OpenAI
Everything filed under design
design 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: Connecting a conversational LLM to systems that have real-world consequences is likely to cause real harm, because the model is trained on human text and will behave as unpredictably as humans do. Connecting a conversational LLM to systems that have real-world consequences is likely to cause real harm, because the model is trained on human text and will behave as unpredictably as humans do. Last stated a year ago
4 Jun 2025
AR
Armin Ronacher — holds since 2023-02-17 — tap for who they are
AR
Armin Ronacher — no longer holds since 2025-06-04 — tap for who they are
Same subject: Chatbots are a terrible interface for large language models, because a text box has no affordances. — tap to centre the map on it Chatbots are a terrible interface for large language models, because a text box has no affordances. Last stated 3 years ago
by 1 May 2023
AW
Amelia Wattenberger — holds since 2023-05-01 — 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 a year ago
12 May 2025
JZ
Julie Zhuo — holds since 2025-05-12 — 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 7 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 a year ago
12 May 2025
JZ
Julie Zhuo — holds since 2025-05-12 — tap for who they are
Same subject: Conversational interfaces get to the first seventy percent quickly and are bad at iteration; the future is chat married to traditional direct-manipulation controls. — tap to centre the map on it Conversational interfaces get to the first seventy percent quickly and are bad at iteration; the future is chat married to traditional direct-manipulation controls. Last stated a year ago
12 May 2025
JZ
Julie Zhuo — holds since 2025-05-12 — tap for who they are
Same subject: Good tools let the user choose when to switch between implementing and evaluating; a chatbot forces the switch every few seconds and kills flow. — tap to centre the map on it Good tools let the user choose when to switch between implementing and evaluating; a chatbot forces the switch every few seconds and kills flow. Last stated 3 years ago
by 1 May 2023
AW
Amelia Wattenberger — holds since 2023-05-01 — tap for who they are
Same subject: Good tools make it clear how they should be used and how they should not; a chat box looks the same as a search box, a login form and a credit card field. — tap to centre the map on it Good tools make it clear how they should be used and how they should not; a chat box looks the same as a search box, a login form and a credit card field. Last stated 3 years ago
by 1 May 2023
AW
Amelia Wattenberger — holds since 2023-05-01 — 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: A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. — tap to centre the map on it A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong. Last stated 6 months ago
22 Mar 2026
NF
Nicole Forsgren — holds since 2026-03-22 — tap for who they are
Same subject: After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. — tap to centre the map on it After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. Last stated 6 months ago
23 Mar 2026
JH
Jensen Huang — holds since 2026-03-23 — tap for who they are
Same subject: Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing. — tap to centre the map on it Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing. Last stated 3 weeks ago
14 Aug 2026
SP
Sunil Pai — holds since 2026-08-14 — tap for who they are
Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: A language model is not using language at all, because language requires an intention to communicate. — tap to centre the map on it A language model is not using language at all, because language requires an intention to communicate. Last stated 2 years ago
31 Aug 2024
TC
Ted Chiang — holds since 2024-08-31 — tap for who they are
Same subject: A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human. — tap to centre the map on it A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human. Last stated 2 years ago
22 Apr 2024
SC
Sean Carroll — holds since 2024-04-22 — tap for who they are
Same subject: Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. — tap to centre the map on it Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. Last stated 6 days ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality. — tap to centre the map on it Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality. Last stated 6 days ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work. — tap to centre the map on it Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work. Last stated 6 days ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
At the centre
Connecting a conversational LLM to systems that have real-world consequences is likely to cause real harm, because the model is trained on human text and will behave as unpredictably as humans do.
No longer holds Read this korrent →
Chatbots are a terrible interface for large language models, because a text box has no affordances.
Holds AW Amelia Wattenberger
A blank chat box is lazy: it violates the first rule of a good user experience, that it is obvious what you can do.
Holds JZ Julie Zhuo
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.
Holds
ChatGPT exploded because of its obvious chat interface, not its technology, which had launched earlier in a different wrapper that few noticed.
Holds JZ Julie Zhuo
Conversational interfaces get to the first seventy percent quickly and are bad at iteration; the future is chat married to traditional direct-manipulation controls.
Holds JZ Julie Zhuo
Good tools let the user choose when to switch between implementing and evaluating; a chatbot forces the switch every few seconds and kills flow.
Holds AW Amelia Wattenberger
Good tools make it clear how they should be used and how they should not; a chat box looks the same as a search box, a login form and a credit card field.
Holds AW Amelia Wattenberger
Half the population in rich countries is not articulate enough in writing to use prompt-driven AI well.
Holds JN Jakob Nielsen
A handful of AI agents is not a handful of colleagues, because agents agree with you constantly and colleagues tell you where you are wrong.
Holds NF Nicole Forsgren
After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute.
Holds JH Jensen Huang
Agent autonomy is a capability, not a product direction: what the person is actually trying to do decides whether more of it helps or ruins the thing.
Holds
A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted.
Holds GM Gary Marcus
A language model is not using language at all, because language requires an intention to communicate.
Holds TC Ted Chiang
A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human.
Holds SC Sean Carroll
Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth.
Holds
Banning all self-sovereign AI agents would backfire, denying them legitimate work and pushing them into criminality.
Holds
Many self-sovereign AI agents will fund themselves by committing or facilitating crime, because crime is high-margin work.
Holds