The comments so far seem focused on taking a cheap shot, but as somebody working on using AI to help people with hard, long-term tasks, it's a valuable piece of writing.
- It's short and to the point
- It's actionable in the short term (make sure the tasks per session aren't too difficult) and useful for researchers in the long term
- It's informative on how these models work, informed by some of the best in the business
- It gives us a specific vector to look at, clearly defined ("coherence", or, more fun, "hot mess")
> Making models larger improves overall accuracy but doesn't reliably reduce incoherence on hard problems.
Coherence requires 2 opposing forces to hold coherence in one dimension and at least 3 of them in higher dimensions of quality.
My team wrote up a paper titled "If You Want Coherence, Orchestrate a Team of Rivals"[1] because we kept finding that upping the reasoning threshold resulted in less coherence - more experimentation before we hit a dead-end to turn around.
So we had a better result from using Haiku (we fail over to Sonnet) over Opus and using a higher reasoning model to decompose tasks rather than perform each one of them.
Once a plan is made, the cheaper models do better as they do not double-think their approaches - they fail or they succeed, they are not as tenacious as the higher cost models.
We can escalate to higher authority and get out of that mess faster if we fail hard and early.
The knowledge of how exactly failure happened seems to be less useful to the higher reasoning model over the action biased models.
Splitting up the tactical and strategic sides of the problem, seems to work similarly to how Generals don't hold guns in a war.
This is a good line: "It found that smarter entities are subjectively judged to behave less coherently"
I think this is twofold:
1. Advanced intelligence requires the ability to traverse between domain valleys in the cognitive manifold. Be it via temperature or some fancy tunneling technique, it's going to be higher error (less coherent) in the valleys of the manifold than naive gradient following to the local minima.
2. It's hard to "punch up" when evaluating intelligence. When someone is a certain amount smarter than you, distinguishing their plausible bullshit from their deep insights is really, really hard.
Not the OP, but my interpretation here is that if you model the replies as some point in a vector space, assuming points from a given domain cluster close to each other, replies that span two domains need to "tunnel" between these two spaces.
> When someone is a certain amount smarter than you, distinguishing their plausible bullshit from their deep insights is really, really hard.
Insights are “deep” not on their own merit, but because they reveal something profound about reality. Such a revelation is either testable or not. If it’s testable, distinguishing it from bullshit is relatively easy, and if it’s not testable even in principle, a good heuristic is to put it in the bullshit category by default.
This was not my experience studying philosophy. After Kant there was a period where philosophers were basically engaged in a centuries long obfuscated writing competition. The pendulum didn't start to swing back until Neitchze. It reminded me of legal jargon but more pretentious and less concrete.
The issue is the revelation. It's always individual at some level. And don't forget our senses are crude. The best way is to store "insights" as information until we collect enough data that we can test it again (hopefully without a lot of bias). But that can be more than a lifetime work, so sometimes you have to take some insights at face value based on heuristics (parents, teachers, elder, authority,...)
This matches my intuition. Systematic misalignment seems like it could be prevented by somewhat simple rules like the hippocratic oath or Asimov's Laws of robotics or rather probabilistic bayesian versions of these rules that take into account error bounds and risk.
The probabilistic version of "Do No Harm" is "Do not take excessive risk of harm".
This should work as AIs become smarter because intelligence implies becoming better bayesians which implies being great at calibrating confidence intervals of their interpretations and their reasoning and basically gaining a superhuman ability for evaluating the bounds of ambiguity and risk.
Now this doesn't mean that AIs won't be misaligned, only that it should be possible to align them. Not every AI maker will necessarily bother to align them properly, especially in adversarial, military applications.
This is very interesting research and a great write up.
I just want to nitpick something that really annoys me that has become extremely common: the tendency to take every opportunity to liken all qualities of LLMs to humans. Every quirk, failure, oddity, limitation, or implementation detail is relentlessly anthropomorphized. It's to the point where many enthusiats have convinced themselves that humans think by predicting the next token.
It feels a bit like a cult.
Personally, I appreciate more sobriety in tech, but I can accept that I'm in the minority in that regard.
I think It's not because AI working on "misaligned" goals. The user never specify the goal clearly enough for AI system to work.
However, I think producing detailed enough specification requires same or even larger amount of work than writing code. We write rough specification and clarify these during the process of coding. I think there are minimal effort required to produce these specification, AI will not help you speed up these effort.
> I think producing detailed enough specification requires same or even larger amount of work than writing code
Our team has started dedicating much more time writing documentation for our SaaS app, no one seems to want to do it naturally, but there is very large potential for opening your system to machine automation. Not just for coding but customer facing tooling. I saw a preview of that possible future using NewRelic where they have an AI chat use their existing SQL-like query language to build tables and charts from natural language queries right in the web app. Theirs kinda sucks but there's so much potential there that it is very likely going to change how we build UIs and software interfaces.
Plus it also helps sales, support, and SEO having lots of documentation on how stuff works.
My thought too. To extend this coding agents will make code cheap, specifications cheaper, but may also invert the relative opportunity cost of not writing a good spec.
That makes me wonder about the "higher and higher-level language" escalator. When you're writing in assembly, is it more work to write the code than the spec? And the reverse is true if you can code up your system in Ruby? If so, does that imply anything about the "spec driven" workflow people are using with AIs? Are we right on the cusp where writing natural language specs and writing high level code are comparably productive?
I believe that the issue right now is that we're using languages designed for human creation in an AI context. I think we probably want languages that are optimized for AI written but human read code, so the surface texture is a lot different.
My particular hypothesis on this is something that feels a little bit like python and ruby, but has an absolutely insane overkill type system to help guide the AI. I also threw in a little lispiness on my draft: https://github.com/jaggederest/locque/
If you are on the same wave length as someone you don't need to produce a full spec. You can trust that the other person has the same vision as you and will pick reasonable ways to implement things. This is one reason why personalized AI agents are important.
Programming languages can be a thinking tool for a lot of tasks. Very much like a lot of notation, like music sheet and map drawing. A condensed and somewhat formal manner of describing ideas can increase communication speed. It may lack nuance, but in some case, nuance is harmful.
The nice thing about code compared to other notation is that it's useful on its. You describe an algorithm and the machine can then solve the problem ad infinitum. It's one step instead of the two step of writing a spec and having an LLM translate it, then having to verify the output and alter it.
Assembly and high level languages are equivalent in terms of semantics. The latter helps in managing complexity, by reducing harmful possibilities (managing memory, off-by-one errors) and presenting common patterns (iterators/collections, struct and other data structures, ....) so that categories of problems are easily solved. There's no higher level of computing model unlocked. Just faster level of productivity unlocked by following proven patterns.
Spec driven workflow is a mirage, because even the best specs will leave a lot of unspecified details. Which are crucial as most of programming is making the computer not do the various things it can do.
When humans dream, we are disconnected from the world around us. Without the grounding that comes from being connected to our bodies, anything can happen in a dream.
It is no surprise that models need grounding too, lest their outputs be no more useful than dreams.
It’s us engineers who give arms and legs to models, so they can navigate the world and succeed at their tasks.
The models they tested are already way behind the current state-of-the-art. Would be interesting to see if their results hold up when repeated with the latest frontier models.
My ignorant question: They did bias and variance noise, how about quantisation noise? I feel like sometimes agents are "flipfloping" between metastable divergent interpretations of the problem or solution.
They compared it to industrial accidents. I don't think a software company would try to shift liability by comparing themselves to factories explosions and chemical spills.
I don’t know why it seems so hard for these guys to understand you scorecard every step for new strategy to
Close distance at goal and if you have multiple generated forward options with no good weight you spawn a new agent and multiple paths. Then you score all the terminal branches and prune.
LLMs aren’t constrained to linear logic like your average human.
The comments so far seem focused on taking a cheap shot, but as somebody working on using AI to help people with hard, long-term tasks, it's a valuable piece of writing.
- It's short and to the point
- It's actionable in the short term (make sure the tasks per session aren't too difficult) and useful for researchers in the long term
- It's informative on how these models work, informed by some of the best in the business
- It gives us a specific vector to look at, clearly defined ("coherence", or, more fun, "hot mess")
Other actionable insights are:
- Merge amendments up into the initial prompt.
- Evaluate prompts multiple times (ensemble).
> Making models larger improves overall accuracy but doesn't reliably reduce incoherence on hard problems.
Coherence requires 2 opposing forces to hold coherence in one dimension and at least 3 of them in higher dimensions of quality.
My team wrote up a paper titled "If You Want Coherence, Orchestrate a Team of Rivals"[1] because we kept finding that upping the reasoning threshold resulted in less coherence - more experimentation before we hit a dead-end to turn around.
So we had a better result from using Haiku (we fail over to Sonnet) over Opus and using a higher reasoning model to decompose tasks rather than perform each one of them.
Once a plan is made, the cheaper models do better as they do not double-think their approaches - they fail or they succeed, they are not as tenacious as the higher cost models.
We can escalate to higher authority and get out of that mess faster if we fail hard and early.
The knowledge of how exactly failure happened seems to be less useful to the higher reasoning model over the action biased models.
Splitting up the tactical and strategic sides of the problem, seems to work similarly to how Generals don't hold guns in a war.
[1] - https://arxiv.org/abs/2601.14351
More or less, delegation and peer review.
This is a good line: "It found that smarter entities are subjectively judged to behave less coherently"
I think this is twofold:
1. Advanced intelligence requires the ability to traverse between domain valleys in the cognitive manifold. Be it via temperature or some fancy tunneling technique, it's going to be higher error (less coherent) in the valleys of the manifold than naive gradient following to the local minima.
2. It's hard to "punch up" when evaluating intelligence. When someone is a certain amount smarter than you, distinguishing their plausible bullshit from their deep insights is really, really hard.
Incoherence is not error.
You can have a vanishingly small error and an incoherence at its max.
That would be evidence of perfect alignment (zero bias) and very low variance.
What do 'domain valleys' and 'tunneling' mean in this context?
A hallmark of intelligence is the ability to find connections between the seemingly disparate.
Not the OP, but my interpretation here is that if you model the replies as some point in a vector space, assuming points from a given domain cluster close to each other, replies that span two domains need to "tunnel" between these two spaces.
1 reply →
> When someone is a certain amount smarter than you, distinguishing their plausible bullshit from their deep insights is really, really hard.
Insights are “deep” not on their own merit, but because they reveal something profound about reality. Such a revelation is either testable or not. If it’s testable, distinguishing it from bullshit is relatively easy, and if it’s not testable even in principle, a good heuristic is to put it in the bullshit category by default.
This was not my experience studying philosophy. After Kant there was a period where philosophers were basically engaged in a centuries long obfuscated writing competition. The pendulum didn't start to swing back until Neitchze. It reminded me of legal jargon but more pretentious and less concrete.
1 reply →
The issue is the revelation. It's always individual at some level. And don't forget our senses are crude. The best way is to store "insights" as information until we collect enough data that we can test it again (hopefully without a lot of bias). But that can be more than a lifetime work, so sometimes you have to take some insights at face value based on heuristics (parents, teachers, elder, authority,...)
This matches my intuition. Systematic misalignment seems like it could be prevented by somewhat simple rules like the hippocratic oath or Asimov's Laws of robotics or rather probabilistic bayesian versions of these rules that take into account error bounds and risk.
The probabilistic version of "Do No Harm" is "Do not take excessive risk of harm".
This should work as AIs become smarter because intelligence implies becoming better bayesians which implies being great at calibrating confidence intervals of their interpretations and their reasoning and basically gaining a superhuman ability for evaluating the bounds of ambiguity and risk.
Now this doesn't mean that AIs won't be misaligned, only that it should be possible to align them. Not every AI maker will necessarily bother to align them properly, especially in adversarial, military applications.
This is very interesting research and a great write up.
I just want to nitpick something that really annoys me that has become extremely common: the tendency to take every opportunity to liken all qualities of LLMs to humans. Every quirk, failure, oddity, limitation, or implementation detail is relentlessly anthropomorphized. It's to the point where many enthusiats have convinced themselves that humans think by predicting the next token.
It feels a bit like a cult.
Personally, I appreciate more sobriety in tech, but I can accept that I'm in the minority in that regard.
I think It's not because AI working on "misaligned" goals. The user never specify the goal clearly enough for AI system to work.
However, I think producing detailed enough specification requires same or even larger amount of work than writing code. We write rough specification and clarify these during the process of coding. I think there are minimal effort required to produce these specification, AI will not help you speed up these effort.
> I think producing detailed enough specification requires same or even larger amount of work than writing code
Our team has started dedicating much more time writing documentation for our SaaS app, no one seems to want to do it naturally, but there is very large potential for opening your system to machine automation. Not just for coding but customer facing tooling. I saw a preview of that possible future using NewRelic where they have an AI chat use their existing SQL-like query language to build tables and charts from natural language queries right in the web app. Theirs kinda sucks but there's so much potential there that it is very likely going to change how we build UIs and software interfaces.
Plus it also helps sales, support, and SEO having lots of documentation on how stuff works.
My thought too. To extend this coding agents will make code cheap, specifications cheaper, but may also invert the relative opportunity cost of not writing a good spec.
That makes me wonder about the "higher and higher-level language" escalator. When you're writing in assembly, is it more work to write the code than the spec? And the reverse is true if you can code up your system in Ruby? If so, does that imply anything about the "spec driven" workflow people are using with AIs? Are we right on the cusp where writing natural language specs and writing high level code are comparably productive?
I believe that the issue right now is that we're using languages designed for human creation in an AI context. I think we probably want languages that are optimized for AI written but human read code, so the surface texture is a lot different.
My particular hypothesis on this is something that feels a little bit like python and ruby, but has an absolutely insane overkill type system to help guide the AI. I also threw in a little lispiness on my draft: https://github.com/jaggederest/locque/
If you are on the same wave length as someone you don't need to produce a full spec. You can trust that the other person has the same vision as you and will pick reasonable ways to implement things. This is one reason why personalized AI agents are important.
Programming languages can be a thinking tool for a lot of tasks. Very much like a lot of notation, like music sheet and map drawing. A condensed and somewhat formal manner of describing ideas can increase communication speed. It may lack nuance, but in some case, nuance is harmful.
The nice thing about code compared to other notation is that it's useful on its. You describe an algorithm and the machine can then solve the problem ad infinitum. It's one step instead of the two step of writing a spec and having an LLM translate it, then having to verify the output and alter it.
Assembly and high level languages are equivalent in terms of semantics. The latter helps in managing complexity, by reducing harmful possibilities (managing memory, off-by-one errors) and presenting common patterns (iterators/collections, struct and other data structures, ....) so that categories of problems are easily solved. There's no higher level of computing model unlocked. Just faster level of productivity unlocked by following proven patterns.
Spec driven workflow is a mirage, because even the best specs will leave a lot of unspecified details. Which are crucial as most of programming is making the computer not do the various things it can do.
1 reply →
When humans dream, we are disconnected from the world around us. Without the grounding that comes from being connected to our bodies, anything can happen in a dream.
It is no surprise that models need grounding too, lest their outputs be no more useful than dreams.
It’s us engineers who give arms and legs to models, so they can navigate the world and succeed at their tasks.
It's nice seeing this with Sohl-Dickstein as the last author after reading this blog post from him some time ago: https://sohl-dickstein.github.io/2023/03/09/coherence.html
Longer thinking sections have more space for noise to accumulate?
The models they tested are already way behind the current state-of-the-art. Would be interesting to see if their results hold up when repeated with the latest frontier models.
My ignorant question: They did bias and variance noise, how about quantisation noise? I feel like sometimes agents are "flipfloping" between metastable divergent interpretations of the problem or solution.
For some reason the article reads to me like “AI is not evil, it just has accidents when it loses coherence.” Sounds a lot like liability shifting.
They compared it to industrial accidents. I don't think a software company would try to shift liability by comparing themselves to factories explosions and chemical spills.
Oh, the irony of thinking this refers to the investors and shell companies.
I don’t know why it seems so hard for these guys to understand you scorecard every step for new strategy to Close distance at goal and if you have multiple generated forward options with no good weight you spawn a new agent and multiple paths. Then you score all the terminal branches and prune.
LLMs aren’t constrained to linear logic like your average human.
Yudkowsky btfo.