Tap a claim on the ring to put it at the centre.
← Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs.
17 connected korrents · 16 moments from 10 Dec 2015 to 22 Oct 2026.
Everything filed under LLMs
LLMs
Everything filed under cybersecurity
cybersecurity
Everything filed under neural networks
neural networks
Everything filed under scaling laws
scaling laws
Everything filed under AI and science
AI and science
Everything filed under AI alignment
AI alignment 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: Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs. Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs. Last stated 2 years ago
1 May 2025
LW
Lilian Weng — holds since 2025-05-01 — tap for who they are
Same subject: Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. — tap to centre the map on it Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. Last stated 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs. — tap to centre the map on it Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs. Last stated 3 months ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: Higher-perplexity adversarial attack text is easier to detect and mitigate. — tap to centre the map on it Higher-perplexity adversarial attack text is easier to detect and mitigate. Last stated 3 years ago
25 Oct 2023
LW
Lilian Weng — holds since 2023-10-25 — tap for who they are
Same subject: Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort. — tap to centre the map on it Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort. Last stated 4 months ago
18 Jul 2026
SR
Sebastian Raschka — holds since 2026-07-18 — tap for who they are
Same subject: There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. — tap to centre the map on it There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost. — tap to centre the map on it More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost. Last stated a year ago
19 Aug 2025
JA
Jay Alammar — holds since 2025-08-19 — tap for who they are
Same subject: The strongest reason to keep training much smarter models quickly is to build defences against other AI. — tap to centre the map on it The strongest reason to keep training much smarter models quickly is to build defences against other AI. Last stated 2 months ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Extra thinking time cannot help with factual recall: a model that does not know a date will not know it after a week either. — tap to centre the map on it Extra thinking time cannot help with factual recall: a model that does not know a date will not know it after a week either. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — 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: A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that. — tap to centre the map on it A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that. Last stated 2 weeks ago
22 Oct 2026
TE
Terence Eden — holds since 2026-10-22 — tap for who they are
Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. Last stated 2 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — tap for who they are
Same subject: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on it A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. Last stated 9 years ago
9 Mar 2018
MC
Michael Carbin — holds since 2018-03-09 — tap for who they are
JF
Jonathan Frankle — holds since 2018-03-09 — tap for who they are
Same subject: A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. Last stated 2 weeks ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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 3 weeks ago
14 Oct 2026
GR
Guillermo Rauch — holds since 2026-10-14 — 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 3 months ago
22 Jul 2026
TP
Thomas Ptacek — holds since 2026-07-22 — tap for who they are
At the centre
Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs.
Holds Read this korrent →
Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch.
Holds
Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs.
Holds
Higher-perplexity adversarial attack text is easier to detect and mitigate.
Holds
Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort.
Holds
There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck.
Holds
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost.
Holds
The strongest reason to keep training much smarter models quickly is to build defences against other AI.
Holds
Extra thinking time cannot help with factual recall: a model that does not know a date will not know it after a week either.
Holds
A breached organisation owes its customers a fast and transparent disclosure, and that obligation applies to the person saying it too.
Holds
A correctly configured TLS server should send its intermediate certificates, not just its own certificate, to let clients chain back to a trusted root.
Holds
A device with always-on WiFi and a default password that users are unlikely to change is not adequately secure, and the maker's reply that users can change it does not fix that.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Holds
A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it.
Holds
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Holds
Agent containment will be one of the most important priorities for any AI infra company.
Holds
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