Hacker Newsnew | past | comments | ask | show | jobs | submit | eru's commentslogin

I'm not sure you want heaviness in a laptop?

I use vscode's tunnel from my MacBook Air to my Archlinux desktop a lot.

The MacBook Air has ~16 GiB RAM. The Desktop has 128 GiB, and a lot more processing power and disk space.


> I think a very long time because part of our limit is experiment.

Yes, maybe. But if you are smarter, you can think up better experiments that you can actually do. Or re-use data from earlier experiments in novel and clever ways.


this. could already be useful to narrow down the search space


I suspect at scale (moving either a lot of batches or large batches), you also need to take variance into account more. Some bills might be dirty or have stuff stuck to them, some bills might be damaged and have bits missing? And other things that occur in practice that I can't think of from the comfort of my armchair in 30s.

You should probably split it up: an end-to-end model for great latency (especially for baked in turn taking), but under the hood it can call out to any old text based model to answer more intricate question. You just need to teach the speech model to stall for a bit, while the LLM is busy.

Just use the same tricks humans are using for that.


Huh, the grandfather was suggestion to have the computer think while you speak.

That's different from banning the computer from thinking before they speak, ain't it?


Thinking while I'm speaking means it isn't listening to everything I've said before thinking what to say. If I start my reply with "no, because...", and it's already formulating its response based on the "no" and not what comes after the because, then it's not thinking before it speaks.

The model can have a reasonable good guess of what you are trying to say, and use 'speculative' thinking. Just like CPU's use branch prediction.

In the common case, you say what the model predicted, and thus the model can use its speculative thinking. In the rare case where you deviated from the prediction, the model thinks from scratch.

(You can further cut down on latency, by speculatively thinking about the top two predictions, instead of just the top prediction. Just costs you more parallel compute.)

This is also all very similar to a chess player who thinks about her next turn, on your turn.


See also any public speaking who starts every answer to a question from the audience (or in a verbal interview) with something like 'that is a good question!' or "thank you for asking me that!"

Same strategy but employed by humans.


"You are absolutely right!"

> [...] and no precomputed responses.

You could probably improve your metrics even more with those in the mix again?


You're probably right, at least at scale this could help

> Instinctively, I think morning light is important to our biology for a daily reset and the solar cue of "high noon" is also a real thing.

You know, you can just set your watch to whatever you feel like?

> I'm sure I've read that sleep health experts have historically supported a change to permanent Standard Time, not DST.

What difference does it make? If people want to get up later or especially earlier, they can, no matter what the 'official' time is.

For an example: Spaniards and Poles are officially in the same timezone, but the Spaniards do everything 'late'. At least when you only look at the clocks; not so much when you look at the sun.


They "can" if they don't have jobs that demand they stick to arbitrary hours.

Sure, social coordination is always a thing.

In any case, most people can get up earlier, if they want to.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: