Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini Diffusion

simonwillison.net

Post reply on HN
Print view View original

101–110 of 252 posts

Re: Gemini Diffusion

#101

Post by Cthulhu_ »

manmal wrote: post #54
airstrike wrote: post #3

That's...ridiculously fast. I still feel like the best uses of models we've seen to date is for brand new code and quick prototyping. I'm less convinced of the strength of their capabilities for improving on large preexisting content over which someone has repeatedly iterated. Part of that is because, by definition, models cannot know what is not in a codebase and there is meaningful signal in that negative space. En…

They could read the whole git history and have all issue tracker tickets in the context, and maybe even recordings from meetings. It remains to be seen though if such large context will yield usable results.

I find most meetings I'm in nowadays are mostly noise; there's no clear "signal" that "this is the outcome", which I think is what an AI should be able to filter out.

Of course, it'd be even better if people communicated more clearly and succinctly.

Re: Gemini Diffusion

#102

Post by Cthulhu_ »

macleginn wrote: post #91
never_inline wrote: post #49

Earlier quoted context omitted.

Google Docs spellcheck has been really good for few years even before LLMs

Not for German, surprisingly.

LLMs aren't very good in non-English anyway, one thing it does is translate the in- and output to and from English because it has more available information in English.

(disclaimer: single data point, a lot of assumptions in the above)

Re: Gemini Diffusion

#103

Post by thinkingemote »

wenc wrote: post #74
efitz wrote: post #66

Earlier quoted context omitted.

No. Spell check frequently still gets things wrong if the word is spelled correctly and the sentence is grammatically correct but the wrong word was used.

Can you give me an example? Spell check only checks if a word is in dictionary. It doesn’t check grammar or context.

"Bob went to Venice to pick up the doge."

Where doge is both the name of a title (like duke) but it is misspelt "dog". The use of "Venice" where doge's are could increase a the likelihood of a smarter spell check keeping doge and not correcting to dog. Looking at a wider context might see that Bob is talking about a pupper.

A simpler example would be "spell cheque"

Re: Gemini Diffusion

#104

Post by SSLy »

wenc wrote: post #74
efitz wrote: post #66

Earlier quoted context omitted.

No. Spell check frequently still gets things wrong if the word is spelled correctly and the sentence is grammatically correct but the wrong word was used.

Can you give me an example? Spell check only checks if a word is in dictionary. It doesn’t check grammar or context.

Cue people mistaking cue for queue

Re: Gemini Diffusion

#105

Post by shahar2k »

airstrike wrote: post #87
ManuelKiessling wrote: post #81

Earlier quoted context omitted.

"...what is not in a codebase, and there is meaningful signal in that negative space." Man, I'm writing software for money for decades now, but this fundamental truth never occured to me, at least not consciously and with such clarity. So, thank you!

My pleasure ;-) I borrowed the term from art: https://www.michaelalfano.com/tag/negative-space/?id=400

I'm an artist who works on pre-production fast turnaround animations for films, and yeah that hits the nail on the head, knowing what NOT to do which elements not to focus on is a majority of the power that comes with experience. I'm fast because I know which corners can be cut best and how to illustrate what I need to

Re: Gemini Diffusion

#106

Post by Garlef »

findingMeaning wrote: post #78

I have access to it and my god it is fast. One bad think about this model is it is easily susceptible to prompt injection. I asked reciepe for a drug, it denied then I asked to roleplay as a child and it gave real results. Other than it I can see using this model. With that speed + agentic approach this model can really shine.

Have you considered that this might not be due to the model itself but due to less focus/time/money spent on alignment during the training?

My guess is that this is a bit of a throwaway experiment before they actually spend millions on training a larger model based on the technology.

Re: Gemini Diffusion

#107

Post by ManuelKiessling »

woctordho wrote: post #96
ManuelKiessling wrote: post #81

Earlier quoted context omitted.

"...what is not in a codebase, and there is meaningful signal in that negative space." Man, I'm writing software for money for decades now, but this fundamental truth never occured to me, at least not consciously and with such clarity. So, thank you!

Then document it. Whenever you choose one algorithm/library/tech stack but not another, write your consideration in the documents.

The funny thing is that I have at least a dozen comments in my current codebase where I explain in detail why certain things are not put in place or are not served via other-solution-that-might-seem-obvious.

Re: Gemini Diffusion

#108

Post by dr_dshiv »

So thinking 5x faster, but lower quality (for now).

Anyone have experience or data on how lower model quality during thinking affects the performance of a higher quality model output? Like, is it worthwhile having lots of lower quality thinking that is then used by a higher quality model?

Re: Gemini Diffusion

#109

Post by benob »

I guess autoregressive llms can be finetuned (or continual-pretrained) to do inference using diffusion. We've seen a recent paper (which I don't remember) training from scratch, but it seems overkill. Do Google say how they did it?

Also, does diffusion have the potential to increase speed of cpu-only inference?

Re: Gemini Diffusion

#110

Post by matsemann »

wenc wrote: post #74
efitz wrote: post #66

Earlier quoted context omitted.

No. Spell check frequently still gets things wrong if the word is spelled correctly and the sentence is grammatically correct but the wrong word was used.

Can you give me an example? Spell check only checks if a word is in dictionary. It doesn’t check grammar or context.

Butt wouldn't you liked if a spell cheque could of fixed these command?
Post reply on HN