That is not how CoT works. It is all in context. All influenced by context. This is a common and significant misunderstanding of autoregressive models and I see it on HN a lot.

That "unproven claim" is actually a well-established concept called Chain of Thought (CoT). LLMs literally use intermediate tokens to "think" through problems step by step. They have to generate tokens to talk to themselves, debug, and plan. Forcing them to skip that process by cutting tokens, like making them talk in caveman speak, directly restricts their ability to reason.

Agents can simply be told to write code in a functional style. They won’t complain. Think of it like a constraint system or proofs system. The agent can better reason about the code and side effects. Etc. Agents are very good at following and validating constraints and hill climbing. This makes sense to me. Humans benefit too, but it is hard to get a bunch of humans to follow the style and maintain it over time.

Agents are useful because they don't inherit context from their parent context. They're basically "compaction" at a small scale. They succeed because context pollution create greater indeterminancy. The fact that you can spin up many of them is not primary benefit of them.

Hmm? How does this relate to functional programming helping agents code better?

> The agent can better reason about the code and side effects. Etc. Agents are very good at following and validating constraints and hill climbing

You're treating an agent like its something other than an LLM with limited context. I'm just trying to surface a incorrect assumption.

You're just talking about LLMs. Whether they're a child of a primary LLM is irrelevent to your conception.

It'd be interesting if you posited that LLMs doing functional style could handle more context without service degradation.

There will always be more bugs than we can fix. AI can patch as well, but if your system is difficult to test and doesn't have rigorous validation you will likely get an unacceptable amount of regression.

There is something powerful about environment and what it does to our minds. For the author, giving up the monitor is totally valid and may work for many people. I can often convince myself to chance a habit by adding a simple extra physical step. This is harder on a computer. It takes discipline to not just end up with dozens of windows and even more browser tabs in some roles. I just aggressively close windows when starting a new task or thinking. Most likely you don't need whatever you are closing :)

Don’t be greedy is probably a good rule when criming. But also, probably testing the system. Who knows who else was using it and how :)

It is amusing that casino machines and games (like digital slot machines) are more tightly regulated than voting machines.

I’ve never trusted video slot machines despite regulations.

And even 50 year old computer games generally have better UX.

Forcing short responses will hurt reasoning and chain of thought. There are some potential benefits but forcing response length and when it answers things ironically increases odds of hallucinations if it prioritizes getting the answer out. If it needed more tokens to reason with and validate the response further. It is generally trained to use multiple lines to reason with. It uses english as its sole thinking and reasoning system.

For complex tasks this is not a useful prompt.

Trivers mapped the evolutionary algorithms, but modern network neuroscience maps the actual hardware running those algorithms right now. When Trivers talks about "self-deception for social advantage," he's describing a highly weighted survival prior that was genetically selected for over millennia. But he doesn't have the real-time mechanics. Today, Friston’s predictive processing and the tri-network model show us exactly how that prior executes in the tissue: the Default Mode Network simply ignores contradictory sensory data from the insula because updating its rigid self-model costs too much metabolic energy. Humans are not running elaborate plots, our brain is just minimizing free energy and avoiding prediction errors in the present moment.

Trivers work is not useful for explaining psychological suffering or real time behavior in a local family environment. We know a lot more than we did in the past. He basically could not separate out what our DMN is and used an elaborate narrative that fit at some macro level but falls apart when looked at closely. He gets the cost right. But we can now say with confidence the mind is not divided in the way he proposes. The narrative creates this division in the reader’s mind, but it is not real. Illusion.

Pinker is really falling for the narrative and ideas here and spends a lot of words in a topic that modern neuroscience pretty easily explains. To push back at Pinker’s conclusion: A rigid self identity with priors that are not updated also explains Triver’s many conflicts and social outcomes. The dude (Trivers) ended up being a creep FWIW.

>... Humans are not running elaborate plots, our brain is just minimizing free energy and avoiding prediction errors in the present moment.

It is crucial to recognize that this is still one interpretation under a theory constrained by a certain framework, and not an absolutely solved and settled mechanism as indicated by the choice of words.

Agreed. It is itself a predictive model. But it works far, far, better than anything prior.

The Epstein “academics” were all running an h-index pumping citation ring — to sell narratives that would be lucrative for various industries and interests. Chomsky, Ito, Trivers, Pinker… they will all be forgotten, and the world will be better for it.

I used to like some of Pinker’s ideas, but yeah. This whole article is just unprincipled garbage in 2026. Neuroscience caught up. Advocating Trivers’ now is nonsense. Interestingly many thinkers of that same era (e.g Krishnamurti, Bohm) were staring right at the modern neuroscience lens and explaining it pretty accurately in the same era Triver’s wrote his essays.

Yes? Right now it is relatively expensive to search video. As embedding tech like this advances and makes it even cheaper it just increases the ability to search and analyze every movement. “Locate speech patterns that indicate dissident activity using the dissident activity skill”