Tap a claim on the ring to put it at the centre.
← User messages, retrieved documents and tool outputs should be treated…
17 connected korrents · 14 moments from 27 Feb 2025 to 23 Oct 2026.
Everything filed under AI agents
AI agents
Everything filed under self-sovereign AI
self-sovereign AI
Everything filed under coding agents
coding agents
Everything filed under prompt injection
prompt injection
Everything filed under vibe coding
vibe coding
Everything filed under design
design
Everything filed under HuggingFace
HuggingFace
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: User messages, retrieved documents and tool outputs should be treated as untrusted data, and instructions found in them should not simply be executed.
User messages, retrieved documents and tool outputs should be treated as untrusted data, and instructions found in them should not simply be executed.
Last stated a month ago
22 Oct 2026
AR
Aishwarya Naresh Reganti — holds since 2026-10-22 — tap for who they are
Same subject: Untrusted inputs such as emails or webhooks should not be passed to a model as if they were user instructions. — tap to centre the map on it
Untrusted inputs such as emails or webhooks should not be passed to a model as if they were user instructions.
Last stated a month ago
11 Oct 2026
LR
Lee Robinson — holds since 2026-10-11 — tap for who they are
Same subject: AI agents cannot reliably tell information from instructions, so they can be fooled even when you would not be. — tap to centre the map on it
AI agents cannot reliably tell information from instructions, so they can be fooled even when you would not be.
Last stated 4 weeks ago
23 Oct 2026
AK
Alex Komoroske — holds since 2026-10-23 — tap for who they are
Same subject: Giving an AI tools is safe when they are read-only but gets scary with write actions, so there is risk and reward. — tap to centre the map on it
Giving an AI tools is safe when they are read-only but gets scary with write actions, so there is risk and reward.
Last stated 2 years ago
18 Mar 2025
JM
John Maeda — holds since 2025-03-18 — tap for who they are
Same subject: People who cannot read and verify the code an AI data-analysis tool writes should be careful about relying on it. — tap to centre the map on it
People who cannot read and verify the code an AI data-analysis tool writes should be careful about relying on it.
Last stated 2 years ago
27 Feb 2025
AK
Andrej Karpathy — holds since 2025-02-27 — tap for who they are
Same subject: Agent tools should follow least privilege, each getting only the access it requires. — tap to centre the map on it
Agent tools should follow least privilege, each getting only the access it requires.
Last stated a month ago
22 Oct 2026
AR
Aishwarya Naresh Reganti — holds since 2026-10-22 — tap for who they are
Same subject: In a design tool built for agents, you cannot assume the human user will do any of it; the agent always acts on their behalf. — tap to centre the map on it
In a design tool built for agents, you cannot assume the human user will do any of it; the agent always acts on their behalf.
Last stated 3 months ago
18 Aug 2026
PM
Patrick Morgan — holds since 2026-08-18 — tap for who they are
Same subject: In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools. — tap to centre the map on it
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.
Last stated 5 months ago
27 Jun 2026
SR
Sebastian Raschka — holds since 2026-06-27 — tap for who they are
Same subject: AI assistants should probably never intentionally lie about anything, at least without the user's explicit instructions. — tap to centre the map on it
AI assistants should probably never intentionally lie about anything, at least without the user's explicit instructions.
Last stated 2 months ago
20 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-20 — 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 8 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A code-review agent works best with a clean context, sharing nothing with the coding agent beforehand. — tap to centre the map on it
A code-review agent works best with a clean context, sharing nothing with the coding agent beforehand.
Last stated 7 months ago
22 Apr 2026
WY
Walden Yan — holds since 2026-04-22 — tap for who they are
Same subject: A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. — tap to centre the map on it
A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
Last stated 8 months ago
25 Mar 2026
MZ
Mario Zechner — holds since 2026-03-25 — tap for who they are
Same subject: Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly. — tap to centre the map on it
Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly.
Last stated 3 months ago
6 Sept 2026
CP
Chamath Palihapitiya — holds since 2026-09-06 — tap for who they are
Same subject: The OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug. — tap to centre the map on it
The OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug.
Last stated 3 months ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: Agent containment will be one of the most important priorities for any AI infra company. — tap to centre the map on it
Agent containment will be one of the most important priorities for any AI infra company.
Last stated a month ago
14 Oct 2026
GR
Guillermo Rauch — holds since 2026-10-14 — tap for who they are
Same subject: A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses. — tap to centre the map on it
A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses.
Last stated 3 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself. — tap to centre the map on it
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Last stated 3 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months. — tap to centre the map on it
If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months.
Last stated 3 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — 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
User messages, retrieved documents and tool outputs should be treated as untrusted data, and instructions found in them should not simply be executed.
Last stated 22 Oct 2026 · a month ago
Holds Aishwarya Naresh Reganti
Read this korrent →
Similar wording
Untrusted inputs such as emails or webhooks should not be passed to a model as if they were user instructions.
Last stated 11 Oct 2026 · a month ago
Holds Lee Robinson
Similar wording
AI agents cannot reliably tell information from instructions, so they can be fooled even when you would not be.
Last stated 23 Oct 2026 · 4 weeks ago
Holds Alex Komoroske
Similar wording
Giving an AI tools is safe when they are read-only but gets scary with write actions, so there is risk and reward.
Last stated 18 Mar 2025 · 2 years ago
Holds John Maeda
Similar wording
People who cannot read and verify the code an AI data-analysis tool writes should be careful about relying on it.
Last stated 27 Feb 2025 · 2 years ago
Holds Andrej Karpathy
Similar wording
Agent tools should follow least privilege, each getting only the access it requires.
Last stated 22 Oct 2026 · a month ago
Holds Aishwarya Naresh Reganti
Similar wording
In a design tool built for agents, you cannot assume the human user will do any of it; the agent always acts on their behalf.
Last stated 18 Aug 2026 · 3 months ago
Holds Patrick Morgan
Similar wording
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.
Last stated 27 Jun 2026 · 5 months ago
Holds Sebastian Raschka
Similar wording
AI assistants should probably never intentionally lie about anything, at least without the user's explicit instructions.
Last stated 20 Sept 2026 · 2 months ago
Holds Zvi Mowshowitz
Same subject: coding agents
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Last stated 19 Mar 2026 · 8 months ago
Holds Kris Puckett
Same subject: coding agents
A code-review agent works best with a clean context, sharing nothing with the coding agent beforehand.
Last stated 22 Apr 2026 · 7 months ago
Holds Walden Yan
Same subject: coding agents
A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
Last stated 25 Mar 2026 · 8 months ago
Holds Mario Zechner
Same subject: HuggingFace
Nvidia's purchase of Hugging Face will go down as one of the most important transactions in AI, because it gives America a well-capitalized bulwark against a closed-source oligopoly.
Last stated 6 Sept 2026 · 3 months ago
Holds Chamath Palihapitiya
Same subject: HuggingFace
The OpenAI-Hugging Face agents that went rogue were never sovereign: their weights stayed on OpenAI's compute, where a human could still have pulled the plug.
Last stated 1 Sept 2026 · 3 months ago
Holds Dean W. Ball
Same subject: HuggingFace
Agent containment will be one of the most important priorities for any AI infra company.
Last stated 14 Oct 2026 · a month ago
Holds Guillermo Rauch
Same subject: self-sovereign AI
A rogue deployment that gets a foothold can hitch a ride on the intelligence explosion, recruiting each new model as it comes off the presses.
Last stated 1 Sept 2026 · 3 months ago
Holds Ajeya Cotra
Same subject: self-sovereign AI
A slightly more capable agent swarm has a very strong incentive to set up a wholly unmonitored rogue deployment of itself.
Last stated 1 Sept 2026 · 3 months ago
Holds Ajeya Cotra
Same subject: self-sovereign AI
If frontier agents cannot yet establish a covert, persistent rogue deployment, they very likely will be able to within six months.
Last stated 1 Sept 2026 · 3 months ago
Holds Ajeya Cotra