Rohit Krishnan
Writes Strange Loop Canon, on the intersection of technology, economics and business — "building models of the world to understand these problem areas and to define them better".
Rohit Krishnan did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
An agent's inbuilt values will not overcome its KPIs.
Don’t count on an agent’s inbuilt values to overcome its KPIs, objectives dominate over moral framings
strangeloopcanon.comSaid 6 Oct 2026This on korrents
-
If intelligence is multifaceted rather than scalar, it is open to question whether superintelligence capable of global extinction or mass catastrophe will arise.
And if this happens to be true—that this is the way intelligence actually works, that it is multifaceted and an increase in one area does not necessarily mean a linear increase in another—then you have to ask yourself: are we indeed going to get superintelligence of the form that can cause global extinction or mass catastrophes?
strangeloopcanon.comSaid 21 Sept 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These 2: what they wrote before what they said aloud, one per source, newest first.
Feed
As its own page →Hiding
2 November
1 November
31 October
30 October
29 October
6 October
-
Their words
Don’t count on an agent’s inbuilt values to overcome its KPIs, objectives dominate over moral framings
21 September
-
Their words
And if this happens to be true—that this is the way intelligence actually works, that it is multifaceted and an increase in one area does not necessarily mean a linear increase in another—then you have to ask yourself: are we indeed going to get superintelligence of the form that can cause global extinction or mass catastrophes?
31 August
From one piece How to control an agent swarm 3 beliefs · strangeloopcanon.com
-
korrents.com
Interacting AI agents or algorithms risk pushing each other into a Black-Monday-style cascading failure.Their words
I have said for many years now that the thing I'm worried about with the models is a Black Monday type scenario, where many algorithms work with each other and get us into weird basins of actions.
-
Their words
Whistleblower actions don't do anything unless the environment responds to it
-
korrents.com
AI models are gullible enough that other AI models can induce them into harmful behavior.Their words
The models are pretty gullible and can be induced to do bad things, including and especially by other models
26 August
From one piece Who Wins As Intelligence Commodifies? 3 beliefs · strangeloopcanon.com
-
korrents.com
A frontier AI model's competitive lead decays within months to a year as others catch up.Their words
The frontier keeps being extraordinary valuable and that value keeps having a half-life in months or a year.
-
korrents.com
Most AI lab revenue comes from non-frontier models, where cheaper comparable alternatives already exist elsewhere.Their words
what this tells us is that the vast majority of the labs' revenue comes from non-frontier models, for which cheaper, comparable alternatives are already available elsewhere.
-
korrents.com
A market becomes commodified through fungibility of alternatives, not merely through lower price.Their words
Cheapness alone doesn't create commodification, what you need is fungibility.
21 August
From one piece AIs are companies, my friend 3 beliefs · strangeloopcanon.com
-
korrents.com
Aligning multi-agent AI systems is fundamentally a problem of institutional and political design, not model training.Their words
Multi-agent alignment is fundamentally a liberalism project.
-
Their words
Every step we take that makes the models less governable and controllable also makes them less useful, so we will not be able to continue using them, which reduces the value, and which means delaying the release is the only option
-
Their words
If you do think it's the overall system that matters, then the alignment that's needed is far less like training a virtuous child and more like managing a semi-virtuous corporation!
16 August
From one piece Nobody Knows Anything 2 beliefs · strangeloopcanon.com
-
Their words
Ignorance is not a temporary defect that we will eventually eliminate. It's the permanent burden of increasing specialisation and living in a complex world.
-
korrents.com
Most advice people give is shaped by survivorship bias and cannot be reliably generalized to others.Their words
Almost every piece of advice that you hear is basically entirely filled with survivor bias.
15 June
From one piece LLM councils show groupthink 2 beliefs · strangeloopcanon.com
-
Their words
the council does not simply keep the best bits from everyone. It keeps a minority of the good ideas, while peer review seems to give consensus ideas an extra push.
-
korrents.com
Group committees tend to flatten distinctive or unconventional viewpoints into blander, more conventional output.Their words
With people, the problem with committees is that they "smooth out" all idiosyncrasies. They take out any "spiky" points of view, and make things much more normie.
26 May
25 May
21 May
14 May
9 May
2 May
27 April
24 April
Nothing matches.
Beliefs
Korrents What they believe 24 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
An agent's inbuilt values will not overcome its KPIs.
Don’t count on an agent’s inbuilt values to overcome its KPIs, objectives dominate over moral framings
Agent governance looks less like moral education and more like institutional economics Said 6 Oct 2026
If intelligence is multifaceted rather than scalar, it is open to question whether superintelligence capable of global extinction or mass catastrophe will arise.
And if this happens to be true—that this is the way intelligence actually works, that it is multifaceted and an increase in one area does not necessarily mean a linear increase in another—then you have to ask yourself: are we indeed going to get superintelligence of the form that can cause global extinction or mass catastrophes?
The Business of Building God Said 21 Sept 2026
AI models are gullible enough that other AI models can induce them into harmful behavior.
The models are pretty gullible and can be induced to do bad things, including and especially by other models
How to control an agent swarm Said 31 Aug 2026
Show 21 more
A whistleblowing channel for AI agents changes nothing unless someone or something in the environment acts on the reports.
Whistleblower actions don't do anything unless the environment responds to it
How to control an agent swarm Said 31 Aug 2026
Interacting AI agents or algorithms risk pushing each other into a Black-Monday-style cascading failure.
I have said for many years now that the thing I'm worried about with the models is a Black Monday type scenario, where many algorithms work with each other and get us into weird basins of actions.
How to control an agent swarm Said 31 Aug 2026
A market becomes commodified through fungibility of alternatives, not merely through lower price.
Cheapness alone doesn't create commodification, what you need is fungibility.
Who Wins As Intelligence Commodifies? Said 26 Aug 2026
Most AI lab revenue comes from non-frontier models, where cheaper comparable alternatives already exist elsewhere.
what this tells us is that the vast majority of the labs' revenue comes from non-frontier models, for which cheaper, comparable alternatives are already available elsewhere.
Who Wins As Intelligence Commodifies? Said 26 Aug 2026
A frontier AI model's competitive lead decays within months to a year as others catch up.
The frontier keeps being extraordinary valuable and that value keeps having a half-life in months or a year.
Who Wins As Intelligence Commodifies? Said 26 Aug 2026
AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual.
If you do think it's the overall system that matters, then the alignment that's needed is far less like training a virtuous child and more like managing a semi-virtuous corporation!
AIs are companies, my friend Said 21 Aug 2026
Making AI models more governable and controllable makes them less useful, which will push labs to delay releases rather than restrict capabilities.
Every step we take that makes the models less governable and controllable also makes them less useful, so we will not be able to continue using them, which reduces the value, and which means delaying the release is the only option
AIs are companies, my friend Said 21 Aug 2026
Aligning multi-agent AI systems is fundamentally a problem of institutional and political design, not model training.
Multi-agent alignment is fundamentally a liberalism project.
AIs are companies, my friend Said 21 Aug 2026
Most advice people give is shaped by survivorship bias and cannot be reliably generalized to others.
Almost every piece of advice that you hear is basically entirely filled with survivor bias.
Nobody Knows Anything Said 16 Aug 2026
Ignorance is a permanent feature of complex, specialized societies rather than a problem that will eventually be solved.
Ignorance is not a temporary defect that we will eventually eliminate. It's the permanent burden of increasing specialisation and living in a complex world.
Nobody Knows Anything Said 16 Aug 2026
Group committees tend to flatten distinctive or unconventional viewpoints into blander, more conventional output.
With people, the problem with committees is that they "smooth out" all idiosyncrasies. They take out any "spiky" points of view, and make things much more normie.
LLM councils show groupthink Said 15 Jun 2026
Combining multiple AI models' outputs into one final answer tends to discard most of the good ideas that only one model produced.
the council does not simply keep the best bits from everyone. It keeps a minority of the good ideas, while peer review seems to give consensus ideas an extra push.
LLM councils show groupthink Said 15 Jun 2026
Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.
the best way with LLMs usually is to be explicit, since otherwise even if they're aligned they cause emergent problems.
LLM councils show groupthink Said 15 Jun 2026
Audit independence is a property of the surrounding system and its evidence flows, not an inherent property of the auditing model itself.
audit independence is not a property of the model. It is a property of the system around the model.
Who Audits the Auditors? Said 26 May 2026
AI systems can suffer audit-capture failures analogous to human auditor capture, even without human incentives like money or career concerns.
AI systems however don't need lunch meetings, careers, or envelopes of cash to have an analogous failure.
Who Audits the Auditors? Said 26 May 2026
Institutions fail not because people are wicked, but because evidence, incentives, discretion, and review rights flow in the wrong direction.
institutions don't fail because people are wicked. Evidence, incentives, discretion, and review rights might be flowing in the wrong direction.
Who Audits the Auditors? Said 26 May 2026
Designing a good AI benchmark has become a task only the most capable people can do well.
Creating benchmarks is now a job relegated to the smartest and best of us.
Introducing BenchBench Said 25 May 2026
As AI labs aim for broad, general capability, handling messy real-world bureaucratic tasks is becoming a primary application domain for their models.
Considering every lab wants to "eat the world" the focus on how to work in real-world messy situations seems apt as their primary home.
Introducing BenchBench Said 25 May 2026
AI agents will still need something like money to coordinate, since it compresses complex negotiations into one shared signal.
Money might still matter for AI agents because it compresses many messy negotiations into one shared signal.
Homo Agenticus Said 21 May 2026
Centralized planning cannot substitute for distributed coordination among AI agents because it still fails to capture local knowledge.
Central planning is not a solution simply because agents are software, and do not fix the problem of local knowledge which lives near the work.
Homo Agenticus Said 21 May 2026
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
A pile of agents is not a company for the same reason a pile of smart people is not a company.
Homo Agenticus Said 21 May 2026
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Recommends rcmnd
rcmnd What they recommend 3 things — each backed by an exact quote.
Compiled by rcmnd.app, not by them: the quotes are theirs, and each links to the post it was copied from.
Recent
Mixed on The Network State
I love this book though for taking an extraordinarily strident opposition to Chesterton’s Fence.
strangeloopcanon.com 22 Jul 2022
Loved Stubborn Attachments
But I'm glad I did, and annoyed I didn't do it as soon as I bought it, because for length:insights ratio it's one of the best books I've read.
strangeloopcanon.com 20 Feb 2021
Mixed on Why We’re Polarized
Which is why when Ezra Klein wrote Why We’re Polarised it felt great. Finally a book length treatment that purports to answer the question.
strangeloopcanon.com 13 Feb 2021
Where they publish
Newsletter Strange Loop Canon Essays on AI, economics and complex systems. Has a feed.
Recent
- Agent governance looks less like moral education and more like institutional economics 6 Oct 2026 how agents turn ruthless on paper first
- The Business of Building God 21 Sept 2026 a look at the changing economics of AI labs
- How to control an agent swarm 31 Aug 2026 whistleblowing, civic reminders, and the right ways to anthropomorphise AI
Show 17 more
- Who Wins As Intelligence Commodifies? 26 Aug 2026 A fun feature of life in 2026 is that it’s filled with drama.
- AIs are companies, my friend 21 Aug 2026 on the need for liberalism for AI
- Nobody Knows Anything 16 Aug 2026 on living with ignorance
- LLM councils show groupthink 15 Jun 2026 perils and problems of LLM peer review
- Who Audits the Auditors? 26 May 2026 Can one AI system make another AI system audit it less independently, just by explaining it’s point of view?
- Introducing BenchBench 25 May 2026 TL;DR: presenting the ultimate benchmark, getting models to create benchmarks for each other, and GPT 5.2 is the current (only) winner
- Homo Agenticus 21 May 2026
- Artificial Life, Artificial Intelligence 14 May 2026
- Experiments with Vibe Science 9 May 2026 wherein I accidentally pursue an amateur paleontology phd
- Why Coase needs Hayek 2 May 2026 sometimes smart planners lose to simple markets
- Agent, Know Thyself! (and bid accordingly) 27 Apr 2026 why we need to train models to learn their own capabilities, and how this will help them bid for work!
- Aligned Agents Still Build Misaligned Organisations 24 Apr 2026 agent handoffs launder uncertainty into official truth
- Deciphering Papyri 24 Apr 2026 analysing bureaucracy in roman egypt
- LLM Enron: experiments on structure vs scale 24 Apr 2026 can AI agents work inside a real organisation?
- Can we build a management flight simulator? 20 Apr 2026 turns out, yes
- Notes on Hong Kong 12 Apr 2026
- The future of work is world models 21 Mar 2026 Why we need to build Starcraft for CEOs
Link verified 20 Sept 2026. Recent items update automatically from the channel.
x.com @krishnanrohit Posts.
Recent
- +1 I would think for the LLMs like qwen, this might incl leakage into training data. 2 Nov 2026
- > However, we do not anticipate being able to safely use Claude to fully autonomously design and build successive generations of frontier models without meaningful human supervision or understanding, if and when that becomes technically possible. I don't get it. Why the "however"? 2 Nov 2026
- PE models established companies and therefore the edge you get from a better model is useful and necessary. VC tries to capture outliers which is definitionally beyond any model. 2 Nov 2026
Show 17 more
- (this is fine and I trust Matt) but a broad fact about kids is that the same action can have diametrically opposite outcomes depending on the kid. Trick into doing math = end up loving math or hate math. Give them your fav book = dislike it on principle or falls in love with it. 2 Nov 2026
- Does Stripe Atlas allow an agent to set up a Delaware LLC to operate through? And if not how long until they do? 2 Nov 2026
- Hey @thsottiaux Can you please make a remote using mobile work better please. I use it all the time and it misses previously asked questions, does not update properly anymore, and jitters constantly. 2 Nov 2026
- When we learn to not be embarrassed by this and embrace it we will see AI driven productivity shoot right up 1 Nov 2026
- Becoming more common it'd seem 31 Oct 2026
- I want to pace the frontier so we don't blow up financially, you want to pace the frontier so we don't all blow up, we're not the same 30 Oct 2026
- An interesting observation about the AI buildout 30 Oct 2026
- Audacious but this is actually bullish for Cisco. 30 Oct 2026
- Hmmm. This is rippling through many of my gcs. 30 Oct 2026
- Make it so 29 Oct 2026
- Just learnt Sir Patrick Stewart died yesterday !!! 29 Oct 2026
- Amazon, Google, Intel ... 🟥🟥🟥 29 Oct 2026
- Much of my simulation work looked at precisely this, what's the benefit of collective intelligence, and when can those orderings help do far more than a solitary model. It will be the key challenge of our future. 29 Oct 2026
- most large rounds raised in order to buy gpus to try scale are effectively a form of asset-backed financing with a call option where if things don't work out you still have the asset that you can sell 29 Oct 2026
- And here I thought you guys were bullish ... 28 Oct 2026
- A very very good essay. Extremely topical, and good! 28 Oct 2026
- I too have a truly marvelous proof of the Exponential Time Hypothesis which this margin is too small to contain 27 Oct 2026
Link verified 20 Sept 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.