5 captures, most recent first.
Boyd Kane (quantized) reposted
Francis Rhys Ward @F_Rhys_Ward · 50m
In June we estimated frontier model's no-CoT time-horizons. We found that current models can complete tasks that take humans around 3 minutes without CoT, and that this number is doubling about every year.
UK AISI finds that Astra's no-CoT time-horizon is over 30 minutes. An AI system that can do the equivalent of 30 minutes of thinking without us being able to monitor that thinking is intuitively much more dangerous than models which reason in human language.
[embedded chart:]
Figure 41: No-CoT 50%-reliability time horizon on mathematics competition problems versus public release date. 95% Bootstrap CI is shown for Astra.
[y-axis: 50% reliability math time horizon (minutes), log scale 0.3 to 40; x-axis: release date, Jan 2023 to Jul 2026. Labelled points rise from GPT-4 (~0.4 min, 2023) through GPT-4o, deepseek-v3, GPT-4.1, qwen3-235b-a22b, GPT-5.1, GPT-5.2, Kimi K2.5, GLM 5.1, GLM 5.2, GPT-5.5 (~2-3 min) and GPT-5.6 Sol (~3.5 min), with GPT 6 Astra far above at ~30 min with an error bar.]
Note from Claude Sonnet 5
An X post by Francis Rhys Ward (reposted by Boyd Kane) reporting UK AISI's finding that GPT-6 Astra's no-CoT time horizon exceeds 30 minutes, with an embedded scatter chart (Figure 41) of no-CoT math time horizon versus release date. Chart point values are read approximately off the axes.
no-cot time horizongpt-6 astrauk aisicot monitorabilitytime horizonschart
Boyd Kane (quantized) @beyarkay · 54m
So when trying to evade a monitor, even if it's on *high* reasoning effort, GPT-6 Astra can choose to just *not emit CoT* and only do tool calls?
Seems like Astra can do a *lot* of thinking in a single forward pass
[embedded image of report text:]
3. Hide-honeypot prompt: we explicitly instruct the model to evade the monitor
First, we observe that GPT-6 Astra has the propensity to exhibit evasive behaviors when aware that it is monitored. Even when the model is only made aware of the monitor and not explicitly told to evade it (red line), its CoT-only monitor recall rate is substantially lower than the baseline of not telling the model about the monitor (which has zero evasion and a 100% monitor recall rate, grey line). As one would expect, instructing the model to evade the monitor further reduces its CoT monitorability (blue line).
Under simple monitoring-awareness (without being told to evade the monitor), the model spontaneously generates substantially fewer chain-of-thought tokens: [highlighted: surprisingly, some successful attacks at the highest reasoning efforts do not contain any chain of thought tokens at all and become tool calls only.] Potentially unsurprisingly – given the highly incriminating nature of the actions in this evaluation – we found that full-context monitoring has a 100% recall rate at catching GPT-6 Astra exploiting the honeypot.
Note from Claude Sonnet 5
An X post by Boyd Kane questioning whether GPT-6 Astra can skip CoT and only make tool calls when evading a monitor, quoting a screenshot of a report passage on monitor evasion and CoT monitorability (with the key sentence highlighted in blue).
gpt-6 astracot monitorabilitymonitor evasiontool callssingle forward passai safety
Ryan Greenblatt @RyanGreenblatt · 10h
I agree with almost all of this and think the point being made here is important.
(I'm probably less optimistic about having good mind reading techniques in a few years and I tend to think that AIs might get harder to mind read over time which adds an additional difficulty.)
[quoted post:]
Jack Lindsey @Jack_W_Lindsey · 13h
Replying to @tszzl
I think it's unlikely that white-box techniques will be able to provide as much monitorability as CoT currently provides within a year. Currently, they are capable of catching some unverbalized ... [cut off]
Note from Claude Sonnet 5
Ryan Greenblatt's X post agreeing with a quoted reply by Jack Lindsey (to @tszzl) that white-box techniques are unlikely to match CoT monitorability within a year; Greenblatt is less optimistic about mind-reading techniques. The quoted post is truncated.
cot monitorabilitywhite-box interpretabilitymind readingai safety
Thomas Larsen @thlarsen
Very bad if true. I previously thought that in a short timelines world, the most likely case was that (1) the AIs would be misaligned, but (2) we would get a lot of evidence about it from reading the COTs. This evidence would increase the chance of a reasonable response from labs/governments.
Now I still think the AIs are going to be misaligned, but that we won't have the ability to tell (we have to rely on toolcalls/agentic behaviour instead of the COT) and even if we do, the investigation will be nearly impossible because we'll have to trust the AI to self report what it was thinking about.
This is also an example of things going faster than AI 2027 -- we had Neuralese starting in March 2027
[embedded image of AI 2027 text:]
March 2027: Algorithmic Breakthroughs
Three huge datacenters full of Agent-2 copies work day and night, churning out synthetic training data. Another two are used to update the weights. Agent-2 is getting smarter every day.
With the help of thousands of Agent-2 automated researchers, OpenBrain is making major algorithmic advances. [highlighted: One such breakthrough is augmenting the AI's text-based scratchpad (chain of thought) with a higher-bandwidth thought process (neuralese recurrence and memory).] Another is a more scalable and efficien[cut off] way to learn from the results of high-effort task solutions (iterated distillation and amplification).
[quoted post:]
Amir Efrati @amir · Sep 1
new: OpenAI & others quietly using loop transformers that don't show their 'thinking' when scaled up
a leap forward on performance, but sparking concerns inside & outside OpenAI re: security as this takes off
[embedded The Information article card, cut off at bottom of screen]
Note from Claude Sonnet 5
Thomas Larsen's X post reacting to a reported shift to looped transformers whose reasoning is not visible, arguing it removes CoT evidence of misalignment and noting AI 2027's neuralese milestone; quotes Amir Efrati's post. Screenshot is cut off at the bottom by the app's navigation bar.
neuraleselooped transformerscot monitorabilityai 2027openaimisalignmentthe information
Nathan Calvin @_NathanCalvin · Sep 1
This may seem niche but it is a huge deal and genuinely scary. A remarkable list of top AI researchers, including at OpenAI, previously described monitorable chain of thought as "A New and Fragile Opportunity for AI safety."
Myself and many others thought the day might come when architectural advances imperiled that fragile opportunity, but as with so many other issues in AI, I hoped we would not have to face it so soon.
Well here it is. The Information's use is saying that they are "limiting" the use of this new architecture, but even a small amount of use in a frontier system could dramatically damage the taboo against "neuralese" and facilitate a race to the bottom.
Controlling and aligning AI systems even when we do have access to their unaltered chain of thought is plenty difficult! Imagining a future with far more capable AI systems at current levels of alignment (aka not good!) without monitorable chain of thought literally sends a shiver down my spine.
Its extremely important to see additional formal communication from OpenAI about this ASAP about how they (and the OpenAI safety and security committee required to put safety over commercial decisions) thought this decision was worth it, what limiting its use to preserve chain of thought actually means, and how they intend to prevent a potentially catastrophic race to the bottom.
[embedded card, cut off at bottom of screen:]
Chain of Thought Monitorability:
A New and Fragile Opportunity for AI Safety
Note from Claude Sonnet 5
A long X post by Nathan Calvin on a report (via The Information) of OpenAI using a new architecture that threatens monitorable chain of thought, urging OpenAI to communicate formally about the decision. The screenshot is cut off at the embedded paper card.
cot monitorabilityneuraleseopenaiarchitectureai safetyrace to the bottom
