Rohit Krishnan
Everything, newest first — across every channel. Their profile → · Subscribe
Hiding
2 November
1 November
31 October
30 October
29 October
28 October
27 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, in the piece's order there
-
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, in the piece's order there
-
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, in the piece's order there
-
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, in the piece's order there
-
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 3 beliefs, in the piece's order there
-
korrents.com
Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.Their words
the best way with LLMs usually is to be explicit, since otherwise even if they're aligned they cause emergent problems.
-
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
From one piece Who Audits the Auditors? 3 beliefs, in the piece's order there
-
Their words
institutions don't fail because people are wicked. Evidence, incentives, discretion, and review rights might be flowing in the wrong direction.
-
Their words
AI systems however don't need lunch meetings, careers, or envelopes of cash to have an analogous failure.
-
Their words
audit independence is not a property of the model. It is a property of the system around the model.
25 May
From one piece Introducing BenchBench 2 beliefs, in the piece's order there
-
Their words
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.
-
korrents.com
Designing a good AI benchmark has become a task only the most capable people can do well.Their words
Creating benchmarks is now a job relegated to the smartest and best of us.
21 May
From one piece Homo Agenticus 3 beliefs, in the piece's order there
-
Their words
A pile of agents is not a company for the same reason a pile of smart people is not a company.
-
Their words
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.
-
Their words
Money might still matter for AI agents because it compresses many messy negotiations into one shared signal.
14 May
9 May
2 May
27 April
24 April
20 April
12 April
21 March
Nothing matches.
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.
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.