Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- 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?by yellowflash
- Everything it spills out is made up language. Forcing it to respond as what it is (a tool) would mean wasting less tokens but also would be a much tougher sell to people who think AI means it can actually think. This is all just marketing.by keicjwdjwj
- > 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.
by pholden - 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.
- 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.
- I usually leave memory/connections turned off. Remembering/finding out what my name would be is not really something I want to waste context or tokens in, let alone any if the other things it tries to assume I'd like it to remember/find.by zamadatix
- Fair perspective, though I actually prefer this for two reasons: * When it's proposing responses for me to choose between, a description like "I close the PR and you make a followup" is ambiguous - is "I" there "the entity making the proposition (the LLM)" or "the entity making the choice (me)". * I have a line in my `AGENTS.md` specifically instructing it to call me by my name; if it stops doing so, that's a telltale that context-bloat is pushing out other instructions.by scubbo
- 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.
- Totally fair, I meant more in the context of coding agents - should've been specific ; I hate heavily AI-designed presentations too.
- For a completely opposite take: https://yegge.ai/essays/model-welfareby unified101
- Yegge's writing was always ..interesting.. but reading him now just makes me feel sad for him.
- HAHA this is awesome, was a fun read - thanks.
Not sure if I agree with a lot of this, even while spending a lot of time building with LLM, but was interesting nonetheless.
- 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"
by mikaeluman - The article lost me when it implied that verbose drivel is actually intrinsically superior rather than a way to hedge betsby alansaber
- Which people exactly?
The problem we have is a few large and expensive models are trying to be everything to everyone.
by pixl97 - > 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.
by wren6991 - The CoT might "in English", but is it really, or is the CoT just another presentation layer over the actual weights?
What I think the author (and I) are wondering about, is whether instructions like these might influence not _only_ the final output, but also the way it got there.
by pindab0ter - 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.
by firefoxd - I still use the first strategy (with DDG) and it still works great. But for technologies I work often, I just take a bit of time to familiarize with the site's structure and maybe bookmarks a few pages.by skydhash
- I still use the first style with google, it works just fine. Even your example, the first result (after the AI response) is the official docs with examples.by Izkata
- 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.
by Animats - is it lossy though? That didn't make sense to me. You can tell it to use Simplified Technical Language and also still have it give you all the detail. it's just another piece of the prompt that produces the output. it's not like there's "pure" llm output and then "lossy" output guided by a prompt.by efficax
- > Well, what do you expect? LLMs are trained on blithering, mostly from web sites. So you get blithering out.
AI labs can now ask the LLM to translate and filter the data, to create new training data that makes more sense and has better style.
by amelius - I think that was a good enough explanation for gpt3.5 -- these days, labs are extremely capable of post-training phases that eclipse that kind of training phase -- and hence of choosing whatever style or tone they wish.
eg., OpenAI has gone a long way to making reasoning token-efficient by having reasoning piovot off terse langauge -- whereas anthropic appears to be doing the opposite.
by mjburgess - > Well, what do you expect? LLMs are trained on blithering, mostly from web sites. So you get blithering out.
I realize this isn't entirely serious, but I can't resist pointing out that this doesn't seem to be a good explanation for why LLMs write the way they do. When we've experimented with LLM writing style on open-weights models where you can get a base model (pretraining on text only) and an instruction-tuned variant (pretraining + post-training with RLHF and whatever other human-evaluated tasks), it's the instruction-tuned variant that shows the weird writing quirks. That is, the writing style is not because of the training texts, but because of whatever tasks the LLM companies do in instruction tuning. https://arxiv.org/abs/2410.16107
I'd speculate that this is partly impressed human preferences (the human raters unintentionally reward a particular writing style) and partly because of the chosen tasks: they're training the LLM to be good at, say, summarizing text, so it develops a style that's good at being informationally dense.
At any rate I've seen this same phenomenon with Llama and Gemma, and will be trying soon with Qwen. Unfortunately none of the commercial models lets you access the base model, as far as I know.
by capnrefsmmat - 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."
by 7402 - You just saved me a bunch of bickering. TY.by nik282000
- I've been having fun doing the exact opposite. I like to ask the AI to speak to me with a think Australian accent, think Steve Irwin. It chucks in heaps of colloquialisms and slang. I find it much easier to read.
I do ask it not to ask it follow on questions. I find that derails my own train of thought.
by jay_kyburz - Yes, this really ought to be trained in (or at least RLHF'd in) but that would hurt engagement numbers so the opposite is done instead.
These are tools and it would behoove us all to keep that top of mind. Dangerous tools that are not your friend (but are useful as tools nonetheless)
by doctoboggan - +1 it’s a tool
It’s not perfect, it has shortcomings, it sometimes produces bogus outputs. All of that is fine for a tool, it’s not fine when it pretends it’s a conscious being, because errors start to feel like lies and it becomes a bit too personal.
by prymitive