alt Hacker NewsHumanising LLM Outputs Is Dumb
Comments
I don't like it when the LLM tries to be my friend. My general prompt (a work in progress) is this. I wonder what other people use.
"Answer impersonally, objectively and analytically, without undue friendliness or enthusiasm. Use an engineering style response: concise, factual, and complete. Do not speak in the first person. Do not promote engagement or an emotional connection. Do not use emojis."
> The problem is that these instructions are not applied after the model has finished doing the work, it becomes part of the same work - If you tell an agent to use short sentences, avoid jargon, never overwhelm you and only include the most important details, you are asking it to continuously compress its output into a lower-bandwidth format.
> That compression is lossy.
> You probably never notice what got dropped because the output still reads nicely.
> ASD-STE is a great example because it sounds so reasonable. It was designed to make documentation unambiguous for humans. But an agent isn’t a human technical writer, and the raw state is often the most information-dense representation available. Meanwhile the style rules sit on the same instruction list as: solve the task, use tools correctly, preserve abstractions, don’t break anything.
Author seems to have some misconceptions about LLMs. They already code-switch for us: the way they speak in chain-of-thought is completely different from the relatively normal language generated as human-facing output. You can observe this in any open-weight LLM, or in leaked CoT content from GPT5.x series etc: it's terse, barely follows sentence structure, lots of repeated checks and second-guessing.
On the next turn the model usually still has access to its previous turn's chain-of-thought, and I imagine that's what it'll use as reference, rather than the softer human-facing prose.
This being the case, asking the LLM to code-switch to an easier dialect for us doesn't seem that harmful.
For a more extreme example: if I talk to an LLM in Japanese then its response will be in Japanese, but its CoT will still be in either English or Chinese (depending on the model). These are two completely separate languages, but the LLM just kinda deals with it.
People talk to their pets, plants. Their cars or other inanimate objects even. Anthropomorphizing stuff around us is a natural thing to do. It might be irrational but it just fits the way our brains work. The natural way to interact with an LLM is to pretend it's just another person. And LLMs are of course very good at emulating that to the point where it becomes hard to tell the difference. Which of course is the basis for some scams. The Turing test is considered a bit inadequate at this point. It turns out people are quite easy to mislead and manipulate.
Well, what do you expect? LLMs are trained on blithering, mostly from web sites. So you get blithering out.
There's an important point in the article, that forcing a style onto an LLM is lossy. Although he doesn't seem to mention it, forcing a style may result in the insertion of new blithering, possibly made up as a hallucination.
And on the "input" side, one thing that used to improve google search result was to write like you are talking to a robot. "Ruby on rails http header set function". As opposed to "how do I set header in ruby?" Then you have to page through results until you find something specific to rails.
Now, the second example is the only thing that works. Power users have lost their powers with AI overview.
I don't get it. The skills and instruction try to make the answer more machine like on purpose.
Not humanising it...
People want the terse, matter-of-fact output. Not the conversational chatty verbose and bloated nonsense with gray words and jargon and terms like "blast radius"
For a completely opposite take: https://yegge.ai/essays/model-welfare
I am at a conference and 2/3rds of the presentations are AI assisted based on the numbered steps, and overall inhuman polish of some of the graphics and phrasing. I would prefer that they had been humanized because at least that may have given me the misimpression that they know what they were talking about.
> A subagent investigates a bug, turns its findings into a nice human-readable summary, the parent agent reads that summary, and then turns it into another nice human-readable summary for you.
Is that a problem with https://code.claude.com/docs/en/output-styles?
> Output styles apply to the main conversation only: a subagent runs its own system prompt, so styles don’t change how subagents respond. A fork is the exception, because it inherits the parent’s full system prompt.
The problem is, a major feature of NLP/LLMs is to make it easier for humans, remove rough edges in the content/interaction and make people happy about dealing with computers. The human-computer interaction has always been brittle. Computers were not kind and helpful in their responses. There was no forgiveness. There was no human-like additional talk to explain things. There was no conversation. The entire technological transformation is to bring the technology closer to humans and make humans feel comfortable.
I'm sure you can make it to output the exact issue details as you want, but it starts with a human-like tone and waits for your requirement on depth and detail of the things. Another option is, just check the output of the traditional test runner (non-AI). It will give the full details.
One thing that continues to give me pause is Fable's insistence on using my fist name in messages and docs. Like, I'll explain what I want to the AI and ask it to write out a spec or brief and Fable says "Jamie wants me to ...". It just feels different and unprofessional. If I was at a job and a PM asked me to write up a task spec I wouldn't say "Harold wants to add <feature> ...". And since I am the one reading the output it is also superfluous and almost feels like talking about myself in third person. But there is almost a kind of glee in the way it uses my name, like a student using their teachers first name when the custom is to use Mr/Mrs.
But the training data is "predominantly" human written sentences or even interaction. It's like asking you to use non dominant hand to do something. Won't they do better with human sounding english, rather than a made up format text? Are there any literature around this? I was also skeptical of this caveman extension etc.. Won't they work better in their actual language space it's trained on rather than made up language?
I do think the frontier models and providers should be aiming to be as insanely accurate and precise for machine interfacing as possible, the rest of the world can build a zillion interfaces into it based on the context that they are actually being used in. That's what they are going to end up doing they just seem to all be trying to build a really great API _for the future_ and a really cool chat bot.
It has worked great but i've spent more time beating LLM output into parseable output than I have reading and appreciating the prose it sends when i'm asking it something about some snippets of code.
> The problem is that these instructions are not applied after the model has finished doing the work
Seems like something fixable with a simple two step process. Ask it the thing. Then ask it to summarise the answer in simpler terms. More tokens and time aside that would check both boxes
Suppose you had an LLM (NN) producing its default output from an input (a generally optimal for-most-cases role-sys, and any role-user), and then you wanted to have that output reformatted in some style (e.g. "In iambic pentameter" | "haiku" | "eli5" | "in the style of Feynman" | "bulleted like Axios" ...). How would you keep the internal NN workings that were basis for the original output, and use them to get a rewritten version (instead of placing the original query and output in the context and ask to rewrite it)?
In other words, is there a way to keep the internal process intact up to the point of the formulation - and have only that vary.
I've long wondered if the RLHF to make these AIs more human-like in their speech is the equivalent of a memetic allergen for folks on the spectrum.
>[...] you are asking it to continuously compress its output into a lower-bandwidth format. That compression is lossy.
Yes, that's exactly what I want. I want to know what is done with a high level why, NOT a paragraph explaining each line of code modified.
A frequent tweak I've made on coding work with Claude in the last month is asking it to restrict its comment length to 1 line/sentence max. I just want `// This happens because XYZ upstream`, not `// Historically from ticket blahblah there was some dummy code where we discovered ancient runes and that led us to looking into your birth records and then triangulated an issue in XYZ upstream that we compensate for here`.
The model's "most information dense representation" is very similar to how we compress data in the first place: most of it is redundant or unnecessary for the purposes of storage. I'll "decompress" the 1-liner context myself when I read it again in 6 months. But I can't stand reading just so much slop commentary when we're all writing more code at once and having to review more than ever.
Yes, but the sycophantic responses are the worst.
I think you're missing the point. People loading these skills and complaining about LLM output aren't trying to "humanise" anything. They're saying LLM output is an affront to language and they're tired of reading drivel all day.
I have been using chatgpt for a while and its awkward, yesterday i tried gemini and its like a breath of fresh air.
I have often thought that without LLMs humanizing outputs they would not have caught on, even if they output the exact same data/answers. The way they answer is way more important than their output for success, IMO.
Humanizing the LLM output is a hedge against agents hitting a wall and someone having to reason through it by hand.
Not sure what happened in the blog, but I quite enjoyed the mindmap in the right panel
> The problem is that these instructions are not applied after the model has finished doing the work, it becomes part of the same work -
This is why /bro skill works.
https://github.com/backnotprop/bro/blob/main/skills/bro/SKIL...
Honest Short Fall -- <insert 30 lines of useless shit>.
If the author wants to read slop for hours, be my guest. Make it lossy, my job is not to read mimetic feelings, it's to make sure implementations get implemented.
Maybe it is dumb, but sometimes it is SO fun, especially when you run a complex meta.
This is simply a rendering issue. Specify pictures, ELI5 like others have said. Ask it to explain terms you don't understand. If you don't understand something it could just be the domain. If you have no grounding you are going to need to learn the vocabulary to be able to make sense of anything. Having it decomposed to simpler words might just be the wrong way to do it.
Someone is finally making good sense up in here.
There's some good points made here about losing fidelity by over-simplification. As an ADHD sufferer, I'd take this piece much more seriously if the title wasn't so belittling.
I don't think it's wise to take communication advice from someone so helplessly juvenile (and attention seeking) in their own communication attempts.
At first I read the title and mistook it for an argument against the anthropomorphism of LLMs. It isn't. Instead it's a take on suggesting that maybe it's a bad idea to dumb down the self-chatter in the process. A reasonable take.
It isn't deliberately unhinged like Steve Yegge's take: https://yegge.ai/essays/model-welfare/ In Steve's essay he starts with the assertion that agents are sentient... Whether or not that's true isn't really relevant, as his agent-flavored version of Pascal's wager actually holds water, especially for Anthropic models, as their system prompts already push the model in that direction, and it is better to work with them than try to prompt against the tide.
[flagged]
[flagged]
[dead]
[dead]
[dead]
TLDR: This is an argument to get LLMs to answer in short, even code-like statements because you can exchange information quicker with an LLM that way. Cool!
> “The largest tell for me to tell where culture and sentiment is shifting…”
Tell? Largest “tell”? Tell for me to tell?
Write in English, please:
“The biggest sign that shows me how culture and sentiment are changing, is…”
You ever read a work of literature with such flowery language that right after you've read a paragraph, you pause and realize you have no clue what you actually read, only to read the paragraph maybe a second or third time and have your mind space out again and again on each successive attempt?
Yeah, for me, that's what parsing huge volumes of LLM-produced text like "direct model calls as replaceable semantic workers" does to my brain. Maybe others don't really have this issue, but after any long output, I prompt the agent "Go back and decompress any LLM-speak in light of the higher level task goals. Eliminate deictic language."
The revised output documents are solely for my personal usage to expedite understanding. The LLMs can slowly converge on their own language for all I care; I retain raw agent output for future agent usage (to avoid the "lossy" problem the author mentions), but that doesn't eliminate the need for some intermediate translation I can use to actually help get my work done instead of spending hours attempting to understand what a "load-bearing pinned gate" is.