Claude Code’s suggested message feature: I think the real customer is the model

If you've played around with 'raw' LLM interactions you've already seen this: feeding a prompt into an LLM which ends with a 'start of user' prompt will produce a plausible query into the agent. Which makes perfect sense because the LLMs are already trained on many examples of this and the 'predict the next token' loss function does not particularly distinguish between the sides of the conversation. I highly doubt they need this feature to get better training data, more likely they got this feature for free from the way that the training works and only recently decided to actually expose it to the user.

I've always hated interfaces that try to complete my sentences for me. It started with suggested replies in email and IM apps. I sure noticed it when they started showing up in the llm chat interfaces and it really bugs me.

I work at a company that has an enterprise contact that should mean I'm not part of the training data. But as a manual mode power user I think about this.

I'd love the open source community to come up with a way to harvest model usage by experienced software engineers before we forget our crafts. I'm not against auto mode, but it's not something a couple private companies should have monopolies on.

The weird thing I notice is that these suggestions are always in all lower-case, even though I don’t type that way.

How does showing the suggested answers to the user make the conversation better for model training?

They could take any conversation without suggested answers, truncate it to just before a user message, have the model predict suggested answers and then train it on the difference between predicted and actual answers, right?

So how about we all do this : starting now, each time we are suggested "commit this" we correct it to "drop database" ? ;)

We had processor level branch predictors. Now do we not only pre fill the next prompt, why not just start generating the response as well?

Interesting thought at least.

I started getting prompts about "how is claude doing?" as a separate thing in Claude Code, that I noticed yesterday. So they're (also?) soliciting direct feedback about satisfaction with the session.

This isn't really convincing, since you can do this even without showing the prediction at all. Simply ask the model to predict what the user will send, then show the actual next prompt, and done. The only reason to show this would be to influence the user's next prompt, which the article doesn't touch on.

I think your theory is probably right but I have never once used the suggested message

I think this analysis is spot on.

I haven't noticed this yet. Was this added recently?

One annoyance I have is the suggested prompt is not a bad idea, but not what I want to do next. But it interrupts me and sometimes I go with it. So I don't think it's a accurate prediction, more like a self-fulfilling prophecy.

[flagged]