Tap a claim on the ring to put it at the centre.
← A carmaker's claim to be the safest is mostly an artefact of comparing…
17 connected korrents · 16 moments from 5 Nov 2019 to 21 Sept 2026.
Everything filed under benchmarks
benchmarks
Everything filed under self-driving cars
self-driving cars
Everything filed under ARC-AGI
ARC-AGI
Everything filed under LLMs
LLMs
Everything filed under America
America
Everything filed under design
design
Everything filed under capitalism
capitalism 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: A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old. A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old. Last stated 3 years ago
19 Dec 2023
PK
Philip Koopman — holds since 2023-12-19 — tap for who they are
Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe because they are not smart enough, not because they are too smart. Last stated a month ago
13 Sept 2026
FC
François Chollet — holds since 2026-09-13 — tap for who they are
Same subject: A self-driving car should be roughly ten times safer than a human driver before it is deployed, to leave engineering margin for what nobody can predict. — tap to centre the map on it A self-driving car should be roughly ten times safer than a human driver before it is deployed, to leave engineering margin for what nobody can predict. Last stated 4 years ago
8 Jan 2023
PK
Philip Koopman — holds since 2023-01-08 — tap for who they are
Same subject: At current ride volumes it would take a leading robotaxi fleet about twenty years without a single fatality to show it is as safe as the average human driver. — tap to centre the map on it At current ride volumes it would take a leading robotaxi fleet about twenty years without a single fatality to show it is as safe as the average human driver. Last stated 2 years ago
17 Jun 2024
PK
Philip Koopman — holds since 2024-06-17 — tap for who they are
Same subject: The United States' current AI strategy is focused on accelerating capability rather than investing in safety measures. — tap to centre the map on it The United States' current AI strategy is focused on accelerating capability rather than investing in safety measures. Last stated a month ago
21 Sept 2026
JC
Jack Clark — holds since 2026-09-21 — tap for who they are
Same subject: The first part of safety is that the thing works as advertised, not that nobody can misuse it. — tap to centre the map on it The first part of safety is that the thing works as advertised, not that nobody can misuse it. Last stated 9 months ago
8 Jan 2026
JH
Jensen Huang — holds since 2026-01-08 — tap for who they are
Same subject: France and Germany will ban Tesla's full self-driving to protect their own car industry. — tap to centre the map on it France and Germany will ban Tesla's full self-driving to protect their own car industry. Last stated 3 months ago
22 Jul 2026
PL
Pieter Levels — holds since 2026-07-22 — tap for who they are
Same subject: A self-driving car is more trustworthy than a random human driver. — tap to centre the map on it A self-driving car is more trustworthy than a random human driver. Last stated 2 years ago
7 Jan 2025
CH
Chip Huyen — holds since 2025-01-07 — tap for who they are
Same subject: Left to their own devices and under competitive pressure, companies will cut safety corners even when safer alternatives are possible. — tap to centre the map on it Left to their own devices and under competitive pressure, companies will cut safety corners even when safer alternatives are possible. Last stated 8 months ago
22 Feb 2026
MB
Miles Brundage — holds since 2026-02-22 — tap for who they are
Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — 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 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A company should define what great looks like for its own role rather than borrow another company's definition. — tap to centre the map on it A company should define what great looks like for its own role rather than borrow another company's definition. Last stated 2 months ago
9 Aug 2026
AW
Adam Ward — holds since 2026-08-09 — tap for who they are
Same subject: A model's capability is now a function of how much money you spend on it, so asking what a model can do means nothing until you name a budget. — tap to centre the map on it A model's capability is now a function of how much money you spend on it, so asking what a model can do means nothing until you name a budget. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores. — tap to centre the map on it Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores. Last stated 2 years ago
13 May 2024
SR
Sebastian Ruder — holds since 2024-05-13 — tap for who they are
Same subject: Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used. — tap to centre the map on it Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: The Abstraction and Reasoning Corpus can measure human-like general fluid intelligence and enable fair comparisons between AI systems and humans. — tap to centre the map on it The Abstraction and Reasoning Corpus can measure human-like general fluid intelligence and enable fair comparisons between AI systems and humans. Last stated 7 years ago
5 Nov 2019
FC
François Chollet — holds since 2019-11-05 — tap for who they are
Same subject: Combining an avocado and a chair into one image is evidence a model conceptually understands both, not that it memorised pictures of them. — tap to centre the map on it Combining an avocado and a chair into one image is evidence a model conceptually understands both, not that it memorised pictures of them. Last stated 2 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence. — tap to centre the map on it Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence. Last stated 2 years ago
20 Dec 2024
FC
François Chollet — holds since 2024-12-20 — tap for who they are
At the centre
A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old.
Holds Read this korrent →
Current models are unsafe because they are not smart enough, not because they are too smart.
Holds
A self-driving car should be roughly ten times safer than a human driver before it is deployed, to leave engineering margin for what nobody can predict.
Holds
At current ride volumes it would take a leading robotaxi fleet about twenty years without a single fatality to show it is as safe as the average human driver.
Holds
The United States' current AI strategy is focused on accelerating capability rather than investing in safety measures.
Holds
The first part of safety is that the thing works as advertised, not that nobody can misuse it.
Holds
France and Germany will ban Tesla's full self-driving to protect their own car industry.
Holds
A self-driving car is more trustworthy than a random human driver.
Holds
Left to their own devices and under competitive pressure, companies will cut safety corners even when safer alternatives are possible.
Holds
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Holds
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 company should define what great looks like for its own role rather than borrow another company's definition.
Holds
A model's capability is now a function of how much money you spend on it, so asking what a model can do means nothing until you name a budget.
Holds
Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores.
Holds
Model comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used.
Holds
The Abstraction and Reasoning Corpus can measure human-like general fluid intelligence and enable fair comparisons between AI systems and humans.
Holds
Combining an avocado and a chair into one image is evidence a model conceptually understands both, not that it memorised pictures of them.
Holds
Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence.
Holds