Most active commenters
  • furyofantares(5)
  • shakna(3)

←back to thread

The case against conversational interfaces

(julian.digital)
279 points nnx | 11 comments | 01 Apr 25 02:14 UTC | HN request time: 0.263s | source | bottom
Show context
ChuckMcM ◴[01 Apr 25 06:35 UTC] No.43543501[source]▶
This clearly elucidated a number of things I've tried to explain to people who are so excited about "conversations" with computers. The example I've used (with varying levels of effectiveness) was to get someone to think about driving their car by only talking to it. Not a self driving car that does the driving for you, but telling it things like: turn, accelerate, stop, slow down, speed up, put on the blinker, turn off the blinker, etc. It would be annoying and painful and you couldn't talk to your passenger while you were "driving" because that might make the car do something weird. My point, and I think it was the author's as well, is that you aren't "conversing" with your computer, you are making it do what you want. There are simpler, faster, and more effective ways to do that then to talk at it with natural language.
replies(11): >>43543657 #>>43543721 #>>43543740 #>>43543791 #>>43543890 #>>43544393 #>>43544444 #>>43545239 #>>43546342 #>>43547161 #>>43551139 #
phyzix5761 ◴[01 Apr 25 07:10 UTC] No.43543740[source]▶
You're onto something. We've learned to make computers and electronic devices feel like extensions of ourselves. We move our bodies and they do what we expect. Having to switch now to using our voice breaks that connection. Its no longer an extension of ourselves but a thing we interact with.
replies(1): >>43543986 #
namaria ◴[01 Apr 25 07:53 UTC] No.43543986[source]▶
Two key things that make computers useful, specificity and exactitude, are thrown out of the window by interposing NLP between the person and the computer.

I don't get it at all.

replies(3): >>43544143 #>>43546069 #>>43546495 #
TeMPOraL ◴[01 Apr 25 08:18 UTC] No.43544143[source]▶

   [imprecise thinking]
         v <--- LLMs do this for you
   [specific and exact commands]
         v
   [computers]
         v
   [specific and exact output]
         v <--- LLMs do this for you
   [contextualized output]
In many cases, you don't want or need that. In some, you do. Use right tool for the job, etc.
replies(2): >>43544577 #>>43551590 #
1. shakna ◴[01 Apr 25 09:19 UTC] No.43544577{4}[source]▶
I don't think they give a specific and exact output, considering how nondeterminism plays a role in most models.
replies(2): >>43545096 #>>43545818 #
2. furyofantares ◴[01 Apr 25 10:31 UTC] No.43545096[source]▶
The diagram you're replying to agrees with this.
replies(1): >>43545198 #
3. walthamstow ◴[01 Apr 25 10:45 UTC] No.43545198[source]▶
Does it? The way I'm reading it, the first step is LLM turning human imprecise thinking into specific and exact commands
replies(1): >>43545359 #
4. furyofantares ◴[01 Apr 25 11:10 UTC] No.43545359{3}[source]▶
That's true, but that is the input section of the diagram, not the output section where [specific and exact output] is labeled, so I believe there was legitimate confusion I was responding to.

To your point, which I think is separate but related, that IS a case where LLMs are good at producing specific and exact commands. The models + the right prompt are pretty reliable at tool calling by themselves, because you give them a list of specific and exact things they can do. And they can be fully specific and exact at inference time with constrained output (although you may still wish it called a different tool.)

replies(1): >>43546984 #
5. TeMPOraL ◴[01 Apr 25 12:13 UTC] No.43545818[source]▶
I'll need to work on the diagram to make it clearer next time.

What it's trying to communicate is, in general, a human operating a computer has to turn their imprecise thinking into "specific and exact commands", and subsequently, understand the "specific and exact output" in whatever terms they're thinking off, prioritizing and filtering out data based on situational context. LLMs enter the picture in two places:

1) In many situations, they can do the "imprecise thinking" -> "specific and exact commands" step for the user;

2) In many situations, they can do the "specific and exact output" -> contextualized output step for the user;

In such scenarios, LLMs are not replacing software, they're being slotted as intermediary between user and classical software, so the user can operate closer to what's natural for them, vs. translating between it and rigid computer language.

This is not applicable everywhere, but then, this is also not the only way LLMs are useful - it's just one broad class of scenarios in which they are.

6. shakna ◴[01 Apr 25 14:09 UTC] No.43546984{4}[source]▶
The tool may not even exist. LLMs are really terrible at admitting where the limits of the training are. They will imagine a tool into being. They will also claim the knowledge is within their realm, when it isn't.
replies(1): >>43548118 #
7. furyofantares ◴[01 Apr 25 15:40 UTC] No.43548118{5}[source]▶
At inference time you can constrain output to a strict json schema that only includes valid tools.
replies(2): >>43548907 #>>43550784 #
8. shakna ◴[01 Apr 25 16:46 UTC] No.43548907{6}[source]▶
That would only be possible, if you could prevent hallucinations from ever occurring. Which you can't. Even if you supply a strict schema, the model will sometimes act outside of it - and infer the existence of "something similar".
replies(1): >>43549754 #
9. furyofantares ◴[01 Apr 25 18:04 UTC] No.43549754{7}[source]▶
That's not true. You say the model will sometimes act outside of the schema, but models don't act at all, they don't hallucinate by themselves, they don't produce text at all, they do all of this in conjunction with your inference engine.

The model's output is a probability for every token. Constrained output is a feature of the inference engine. With a strict schema the inference engine can ignore every token that doesn't adhere to the schema and select the top token that does adhere to the schema.

10. xigoi ◴[01 Apr 25 20:03 UTC] No.43550784{6}[source]▶
Just because the answer adheres to the schema does not mean that it’s correct.
replies(1): >>43551241 #
11. furyofantares ◴[01 Apr 25 20:56 UTC] No.43551241{7}[source]▶
Yes, we've been discussing "specific and exact" output. As I said, you might wish it called at different tool; nothing in this discussion is addressing that.