Tap a claim on the ring to put it at the centre.
← Safety guardrails make a coding model more dangerous rather than less,…
17 connected korrents · 16 moments on record from 7 Sept 2008 to 3 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under AI alignment
AI alignment
Everything filed under JavaScript
JavaScript
Everything filed under Anthropic
Anthropic 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: Safety guardrails make a coding model more dangerous rather than less, because one refusal turns it into something that refuses anything. Safety guardrails make a coding model more dangerous rather than less, because one refusal turns it into something that refuses anything. Last stated a week ago
31 Aug 2026
PL
Pieter Levels — holds since 2026-08-31 — tap for who they are
Same subject: Redefining the engineer's job as building guardrails is not novel — it is the same problem as making a junior engineer effective, which we never solved either. — tap to centre the map on it Redefining the engineer's job as building guardrails is not novel — it is the same problem as making a junior engineer effective, which we never solved either. Last stated 3 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility. — tap to centre the map on it The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility. Last stated 5 months ago
29 Mar 2026
CH
Chip Huyen — holds since 2026-03-29 — tap for who they are
Same subject: Letting automated loops build everything without guardrails on blast radius and on quality is a recipe for disaster. — tap to centre the map on it Letting automated loops build everything without guardrails on blast radius and on quality is a recipe for disaster. Last stated 3 weeks ago
19 Aug 2026
AO
Addy Osmani — holds since 2026-08-19 — tap for who they are
Same subject: The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more. — tap to centre the map on it The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more. Last stated 3 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: AI guardrails will end up binding only the ordinary person, because the powerful actors they most need to check will simply steamroll them. — tap to centre the map on it AI guardrails will end up binding only the ordinary person, because the powerful actors they most need to check will simply steamroll them. Last stated 4 weeks ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: The unsafe keyword does not switch the borrow checker off; it only unlocks a few operations you then have to justify yourself. — tap to centre the map on it The unsafe keyword does not switch the borrow checker off; it only unlocks a few operations you then have to justify yourself. Last stated 4 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — tap for who they are
Same subject: The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. — tap to centre the map on it The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. Last stated 2 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: The case for Rust is stronger against C++ than against JavaScript, because in C++ an ordinary mistake is usually a security vulnerability. — tap to centre the map on it The case for Rust is stronger against C++ than against JavaScript, because in C++ an ordinary mistake is usually a security vulnerability. Last stated 4 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. — tap to centre the map on it A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. Last stated 6 days ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. Last stated 9 years ago
24 Oct 2017
ÉT
Émile P. Torres — holds since 2017-10-24 — tap for who they are
Same subject: Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them. — tap to centre the map on it Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them. Last stated 8 months ago
1 Jan 2026
DA
Dario Amodei — holds since 2026-01-01 — tap for who they are
Same subject: Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests. — tap to centre the map on it Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests. Last stated 5 days ago
2 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-02 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 4 days ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. — tap to centre the map on it A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it. Last stated 4 days ago
3 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-03 — tap for who they are
Same subject: An open weights model from 2025 with a pentest harness could already escape a sandbox and hack most networks; the surprise says more about the sandbox than the model. — tap to centre the map on it An open weights model from 2025 with a pentest harness could already escape a sandbox and hack most networks; the surprise says more about the sandbox than the model. Last stated 2 months ago
22 Jul 2026
TP
Thomas Ptacek — holds since 2026-07-22 — tap for who they are
Same subject: Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it. — tap to centre the map on it Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it. Last stated 3 years ago
13 Dec 2023
SA
Scott Aaronson — holds since 2008-09-07 — tap for who they are
SA
Scott Aaronson — no longer holds since 2023-12-13 — tap for who they are
At the centre
Safety guardrails make a coding model more dangerous rather than less, because one refusal turns it into something that refuses anything.
Holds Read this korrent →
Redefining the engineer's job as building guardrails is not novel — it is the same problem as making a junior engineer effective, which we never solved either.
Holds
The frightening part of giving agents more access is not bad code but irreversible action, so the guardrails to build next are guardrails on reversibility.
Holds CH Chip Huyen
Letting automated loops build everything without guardrails on blast radius and on quality is a recipe for disaster.
Holds AO Addy Osmani
The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more.
Holds
AI guardrails will end up binding only the ordinary person, because the powerful actors they most need to check will simply steamroll them.
Holds RG Ryan Greenblatt
The unsafe keyword does not switch the borrow checker off; it only unlocks a few operations you then have to justify yourself.
Holds AR Alice Ryhl
The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it.
Holds
The case for Rust is stronger against C++ than against JavaScript, because in C++ an ordinary mistake is usually a security vulnerability.
Holds AR Alice Ryhl
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Holds IS Ilya Sutskever
A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence.
Holds AC Ajeya Cotra
A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough.
Holds ÉT Émile P. Torres
Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them.
Holds DA Dario Amodei
Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests.
Holds ZM Zvi Mowshowitz
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it.
Holds ZM Zvi Mowshowitz
An open weights model from 2025 with a pentest harness could already escape a sandbox and hack most networks; the surprise says more about the sandbox than the model.
Holds
Because a few specialists already devote themselves to superintelligent AI, the rest of us have correspondingly less reason to spend our own effort on it.
No longer holds SA Scott Aaronson