LLMs reward expertise • Hacker News Board

Re: LLMs reward expertise

#601

Post by IIsi50MHz » Thu, Aug 06, 2026, 10:31 PM UTC

jaggederest wrote: post #228

jerf wrote: post #163

Earlier quoted context omitted.

I've been using a prompt that comes from the opposite direction for non-programming stuff: "Assume the user is an expert in all fields; while this is clearly logically untrue on a literal level, the user prefers to see a field's technical terminology and then ask the AI about terms the user does not understand rather than get an inaccurate statement about some issue." Whether you have to reassure the LLM that this is…

Off topic, but stretching is absolutely useless for ... stretching. And vital for retaining and enhancing usable range of motion (not static stretching, still, but dynamic stretching / mobility under tension). The wildest thing is, there's no evidence that I can find that static stretching does... anything? It increases pain tolerance through the range of motion, but not any more than just asking people to try harder…

Static stretching increases tendon length, among other things. The stretch MUST NOT cause pain, and MUST be steady for the duration of stretch. Some suitable duration increments are 10 sec. (absolute minimum), 30 sec., 60 sec. Multi-minute stretches are suitable if they can be held without discomfort.

Notably, longer tendons are counter-productive for energy return. The fastest runners tend to have increased tightness along the backs of their legs.

Re: LLMs reward expertise

#602

Post by plutokras » Fri, Aug 07, 2026, 10:12 AM UTC

krisoft wrote: post #191

I did a test a few months ago. A friend of mine wanted to develop what i understood to be a simple single page web app. But since she didn’t have any software engineering experience she asked me to help. Around that time everyone was talking about how literally anyone can develop software with LLMs i asked her if she could give it a try first, and if I could watch the attempt. I was fully expecting that writing the c…

> My friend didn’t have the vocabulary to ask the AI to write code

I had the exact same realization using Claude Design. It’s great that "anyone can design" now, but I don't have the domain knowledge to describe what a good design consists of. I know it when I see it, but that is far from enough.

Re: LLMs reward expertise

#603

Post by jainil1729 » Fri, Aug 07, 2026, 1:26 PM UTC

abixb wrote: post #73

The amplifying mirror analogy works best here. LLMs are ultimately a reflection of your own interactions with its weights, the tone you use, the structure with which you construct your prompt, aspects of an issue you tend to focus on, your breadth of vocabulary and world knowledge and whatnot. People who (carefully) use it as an extension of their own mind and senses will very likely thrive, and those who use it as a…

Can you share more about the skill please?

Re: LLMs reward expertise

#604

Post by sedivy94 » Sat, Aug 08, 2026, 6:03 AM UTC

lowsong wrote: post #575

ramraj07 wrote: post #167

Earlier quoted context omitted.

The amplifying mirror is not just a characteristic, but the fundamental driving force of LLMs. With every token it consumes, its primary goal is to understand who you are and what you intend. If you type Hola thats sufficient to tell it so much more than if you type hi.

LLMs do not have goals and cannot understand. Please don't anthropomorphize.

One does not need to be human to understand. Animals understand. Saying “he” or “she” would be closer to anthropomorphism than the parent comment, but still does not sufficiently satisfy the definition of anthropomorphism (giving human form).

I see you pushing back on related topics in a few comment threads. I’m not sure if I can define “understanding” but I think “intelligence” is a fair synonym for this conversation. I see your passion for clarifying that LLMs are not intelligent, and I’m sensing you’re conflating that with “consciousness” and trying to hedge against other people inadvertently making that same error.

Intelligence is not uniquely human. And not constrained to consciousness. Even consciousness itself, under fringe definitions like exhibiting non-deterministic behavior, is not constrained to living beings. Systems, for example, exhibit intelligence all the time - groups of people, colonies of ants, weather systems, self-organized criticality like blooming forest fires or abelian sand piles, evolutionary processes, and so on.

Your counter argument - that LLM responses are “just” statically probable (i.e. predictions) - actually supports this notion. Many intelligent statements we make are probably right or probably wrong, in part or in whole. We as humans are far more than statistical computers, but our intelligence in isolation doesn’t seem far off from that of LLMs (not mechanistically, but rather qualitatively).

3Blue1Brown recently posted a video called something like “Compression is Intelligence”. Worth a watch.

Re: LLMs reward expertise

#605

Post by bhk » Sat, Aug 08, 2026, 7:29 PM UTC

marssaxman wrote: post #116

bumblehean wrote: post #68

Earlier quoted context omitted.

>Hours + Hours of reading and a lot of trial-and-error. The loop was so long and sooo slow. But that's how you learn...

I lost my desire to learn anything about web development twenty years ago and specialized my career in a completely different direction. I had not touched HTML at all since then until earlier this year, when I discovered that AI robots could do it for me. Now I am happy to whip up HTML/CSS/JavaScript visualizers, explorers, and even one-off interactive report presentations whenever they might be useful, precisely bec…

Working with the browser technology stack is living in a dystopian world of overcomplicated, often duplicative features defined in many thousands of pages of specifications, often revised and/or contradicted by other specifications, many of which do not apply to the reality of actual implementations, so encyclopedic knowledge of the specifications is not enough -- you need familiarity with everything written on the internet about these APIs. Accessing even conceptually simple features can require navigating through multiple APIs that purport to provide that feature, most of which have fatal shortcomings in design, specification, or real-world support. AI is a godsend here, at least for now ... I wonder what the impending post-human-developer "model collapse" will yield.

Re: LLMs reward expertise

#606

Post by lowsong » Sat, Aug 08, 2026, 11:00 PM UTC

sedivy94 wrote: post #604

lowsong wrote: post #575

Earlier quoted context omitted.

LLMs do not have goals and cannot understand. Please don't anthropomorphize.

One does not need to be human to understand. Animals understand. Saying “he” or “she” would be closer to anthropomorphism than the parent comment, but still does not sufficiently satisfy the definition of anthropomorphism (giving human form). I see you pushing back on related topics in a few comment threads. I’m not sure if I can define “understanding” but I think “intelligence” is a fair synonym for this conversatio…

You're arguing semantics, but I think that expanding your definition of intelligence to include ant colonies and weather systems is going to make it completely useless to say anything at all about an LLM.

The problem with all of this is that because an LLM gives a facsimile of language and conversation people believe it can "comprehend" or "understand" or whatever word you want to use. This problem isn't new, AI research has had this issue for decades. The risk is that this makes people misunderstand and offload their decision making to it, treating it like a person to be instructed or reasoned with. It isn't, and can never be.