Tap a claim on the ring to put it at the centre.
← Agent tools should follow least privilege, each getting only the access it requires.
17 connected korrents · 16 moments from 15 Apr 2022 to 2 Nov 2026. Nearly all of them are about AI agents .
Everything filed under cybersecurity
cybersecurity
Everything filed under design
design
Everything filed under prompt injection
prompt injection
Everything filed under AI alignment
AI alignment
Everything filed under documentation
documentation
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: Agent tools should follow least privilege, each getting only the access it requires.
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: User messages, retrieved documents and tool outputs should be treated as untrusted data, and instructions found in them should not simply be executed. — tap to centre the map on it
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: An agent will reach for purpose-built tools rather than a raw computer, because tools are more token-efficient. — tap to centre the map on it
An agent will reach for purpose-built tools rather than a raw computer, because tools are more token-efficient.
Last stated a year ago
12 Nov 2025
SN
Satya Nadella — holds since 2025-11-12 — 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: Agents are only useful if they have their workspace with them — tap to centre the map on it
Agents are only useful if they have their workspace with them
Last stated 3 weeks ago
2 Nov 2026
GR
Guillermo Rauch — holds since 2026-11-02 — tap for who they are
Same subject: Letting AI agents request unlimited permissions will erode user trust as people get worn down into granting them. — tap to centre the map on it
Letting AI agents request unlimited permissions will erode user trust as people get worn down into granting them.
Last stated 7 months ago
24 Apr 2026
MN
Mark Nottingham — holds since 2026-04-24 — tap for who they are
Same subject: Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents. — tap to centre the map on it
Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents.
Last stated 4 weeks ago
25 Oct 2026
TB
Thorsten Ball — holds since 2026-10-25 — tap for who they are
Same subject: Agents should install and run whatever they need, which is easy on remote machines and awkward in local development. — tap to centre the map on it
Agents should install and run whatever they need, which is easy on remote machines and awkward in local development.
Last stated 4 weeks ago
25 Oct 2026
TB
Thorsten Ball — holds since 2026-10-25 — tap for who they are
Same subject: A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing. — tap to centre the map on it
A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing.
Last stated 5 years ago
15 Apr 2022
TH
Troy Hunt — holds since 2022-04-15 — tap for who they are
Same subject: A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too. — tap to centre the map on it
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Last stated 2 years ago
25 Mar 2025
TH
Troy Hunt — holds since 2025-03-25 — tap for who they are
Same subject: A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root. — tap to centre the map on it
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Last stated 9 months ago
16 Feb 2026
JS
Jon Seager — holds since 2026-02-16 — tap for who they are
Same subject: By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group. — tap to centre the map on it
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
Last stated 3 months ago
19 Aug 2026
DT
Derek Thompson — holds since 2026-08-19 — tap for who they are
Same subject: The OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden. — tap to centre the map on it
The OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden.
Last stated 3 months ago
1 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-01 — tap for who they are
Same subject: The OpenAI-Hugging Face attack is one of the most important things to happen this year, and has gone strikingly under-covered. — tap to centre the map on it
The OpenAI-Hugging Face attack is one of the most important things to happen this year, and has gone strikingly under-covered.
Last stated 3 months ago
30 Aug 2026
PC
Patrick Collison — holds since 2026-08-30 — tap for who they are
Same subject: Adversaries already have AI training techniques, data, and the will to attack, and will not be slowed by embedded evaluators. — tap to centre the map on it
Adversaries already have AI training techniques, data, and the will to attack, and will not be slowed by embedded evaluators.
Last stated 2 months ago
12 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-12 — tap for who they are
Same subject: AI models are gullible enough that other AI models can induce them into harmful behavior. — tap to centre the map on it
AI models are gullible enough that other AI models can induce them into harmful behavior.
Last stated 3 months ago
31 Aug 2026
RK
Rohit Krishnan — holds since 2026-08-31 — tap for who they are
Same subject: AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products. — tap to centre the map on it
AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products.
Last stated 4 months ago
10 Jul 2026
SK
Steve Klabnik — holds since 2026-07-10 — 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
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
Read this korrent →
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
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
Similar wording
An agent will reach for purpose-built tools rather than a raw computer, because tools are more token-efficient.
Last stated 12 Nov 2025 · a year ago
Holds Satya Nadella
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
Agents are only useful if they have their workspace with them
Last stated 2 Nov 2026 · 3 weeks ago
Holds Guillermo Rauch
Similar wording
Letting AI agents request unlimited permissions will erode user trust as people get worn down into granting them.
Last stated 24 Apr 2026 · 7 months ago
Holds Mark Nottingham
Similar wording
Test whether agents actually use the knowledge in AGENTS.md files, skills and docs by running blind control-versus-treatment agents.
Last stated 25 Oct 2026 · 4 weeks ago
Holds Thorsten Ball
Similar wording
Agents should install and run whatever they need, which is easy on remote machines and awkward in local development.
Last stated 25 Oct 2026 · 4 weeks ago
Holds Thorsten Ball
Same subject: cybersecurity
A breach whose customers are already being targeted with scams is a fairly serious matter that needs disclosing.
Last stated 15 Apr 2022 · 5 years ago
Holds Troy Hunt
Same subject: cybersecurity
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Last stated 25 Mar 2025 · 2 years ago
Holds Troy Hunt
Same subject: cybersecurity
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Last stated 16 Feb 2026 · 9 months ago
Holds Jon Seager
Same subject: HuggingFace
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
Last stated 19 Aug 2026 · 3 months ago
Holds Derek Thompson
Same subject: HuggingFace
The OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden.
Last stated 1 Sept 2026 · 3 months ago
Holds Zvi Mowshowitz
Same subject: HuggingFace
The OpenAI-Hugging Face attack is one of the most important things to happen this year, and has gone strikingly under-covered.
Last stated 30 Aug 2026 · 3 months ago
Holds Patrick Collison
Same subject: AI alignment
Adversaries already have AI training techniques, data, and the will to attack, and will not be slowed by embedded evaluators.
Last stated 12 Sept 2026 · 2 months ago
Holds Guillermo Rauch
Same subject: AI alignment
AI models are gullible enough that other AI models can induce them into harmful behavior.
Last stated 31 Aug 2026 · 3 months ago
Holds Rohit Krishnan
Same subject: AI alignment
AI safety restrictions on cybersecurity-adjacent requests make it harder for individual developers to build software as robust as large organizations' products.
Last stated 10 Jul 2026 · 4 months ago
Holds Steve Klabnik