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

171–180 of 252 posts

Re: Gemini Diffusion

#171

Post by westoncb »

dimitri-vs wrote: post #161
westoncb wrote: post #123

Earlier quoted context omitted.

The trick to this is you've got to talk to them and share this information in the same way. I can give an example. These days my main workflow is as follows: if I have some big feature/refactor/whatever I'm going to work on I'll just start talking to o3 about it essentially as if it was a coworker and (somewhat painstakingly) paste in relevant source files it needs for context. We'll have a high-level discussion abou…

Interesting approach, I'm definitely going to steal your wording for "generate an implementation plan that...". I do something similar but entirely within Cursor: 1. create a `docs/feature_name_spec.md`, use voice-to-text to brain dump what I am trying to do 2. open up a the AI chat panel in "Ask" mode while referencing that spec file, ask (paste) a boilerplate snippet like: "1) Ask clarifying questions about intent,…

I spend so much time just finding/moving context pieces around these days i bought a physical macro pad and have been thinking about designing some software specifically to make this quicker, basically like rapidly finding/selecting context pieces and loading into buffers and relaying to conversation context. I think it’ll have to be backed by agentic search, voice controlled, and not sure how to best integrate with possible consumers… I dunno if that makes sense. I started building it and realized I need to think on the design a bit more so I’m building more like infrastructure pieces now.

Re: Gemini Diffusion

#172

Post by lucasacosta_ »

airstrike wrote: post #21
ec109685 wrote: post #14

Earlier quoted context omitted.

If you make models fast enough, you can onboard that expert developer instantly and let them reason their way to a solution, especially when giving access to a RAG to. Over time, I models will add more memory and institutional knowledge capture rather than starting from a blank slate each time.

I thought of that as I wrote my comment, but I think the infrastructure and glue to make that possible in a consistent, fast and scalable way is still a few years out.

Definitely. For now the "frontier-level" papers (working with repository-level coding maintenance) need to necessarily depend on previously (and statically) generated Code Knowledge Graphs or Snippet-Retrieval systems, which makes the scalable and fast aspects complicated, as any change in the code would represent a change in the graph, hence requiring a rebuild. But given the context limit, you need to rely on Graph queries to give relevant parts and then at the end of the day it just reads snippets instead of the full code, which makes the consistent an issue, as it can't learn from the entirety of the code.

Papers I'm referring to (just some as example, as there're more):

- CodexGraph [https://arxiv.org/abs/2408.03910] - Graph

- Agentless [https://arxiv.org/abs/2407.01489] - Snippet-Retrieval

Re: Gemini Diffusion

#173

Post by david-gpu »

spuz wrote: post #115
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!

I am not certain that I agree with this. If there are alternative ways of solving a problem that we're not taken then these should be documented in comments. A mantra I try to tell myself and my colleagues is if information exists in your brain and nowhere else then write down it down _somewhere_. If I tried 5 different libraries before settling on one, then I write in comments which libraries I tried but didn't work…

Agreed. IMO it's always a good idea to document design choices.

The owner can write down the problem, a few solutions that were considered, why they were chosen/rejected, and a more detailed description of the final design. Stakeholders then review and provide feedback, and after some back and forth all eventually sign off the design. That not only serves to align the organization, but to document why things were done that way, so that future hires can get a sense of what is behind the code, and who was involved in case they have more questions.

This was how we did things at some $BigCorps and it paid dividends.

Re: Gemini Diffusion

#174

Post by cubefox »

cztomsik wrote: post #100

I have no idea how it works actually (in google) but I wouldn't be surprised if it was just post-training because recently RWKV people did something similar: They replaced the whole attention mechanism with WKV (forward-only linear attention), and created such franken-stein just by post-training. The big wow moment about that is that it sort of implies that most of the useful knowledge is in the FFN, and attention it…

> Also, I read yesterday that at some point, the embeddings across all of the models are (very) comparable/similar, and a simple converter can be trained

That was from here: https://news.ycombinator.com/item?id=44054425

Re: Gemini Diffusion

#175

Post by beernet »

ealexhudson wrote: post #149
beernet wrote: post #144

Serious question: Why does it appear that pages from this URL very often end up on top of HN? I don't find the content particularly special compared to the average HN post. Does the algorithm prefer certain URLs?

Perhaps your content quality meter needs a recalibration?

How so? What makes this blog stand out in terms of quality? I prefer a constructive discussion over personal questions, maybe you should, too.

Re: Gemini Diffusion

#176

Post by rcarmo »

dimitri-vs wrote: post #161
westoncb wrote: post #123

Earlier quoted context omitted.

The trick to this is you've got to talk to them and share this information in the same way. I can give an example. These days my main workflow is as follows: if I have some big feature/refactor/whatever I'm going to work on I'll just start talking to o3 about it essentially as if it was a coworker and (somewhat painstakingly) paste in relevant source files it needs for context. We'll have a high-level discussion abou…

Interesting approach, I'm definitely going to steal your wording for "generate an implementation plan that...". I do something similar but entirely within Cursor: 1. create a `docs/feature_name_spec.md`, use voice-to-text to brain dump what I am trying to do 2. open up a the AI chat panel in "Ask" mode while referencing that spec file, ask (paste) a boilerplate snippet like: "1) Ask clarifying questions about intent,…

That's very close to my workflow: https://taoofmac.com/space/blog/2025/05/13/2230

Re: Gemini Diffusion

#177

Post by grumbelbart2 »

scotty79 wrote: post #159
cztomsik wrote: post #100

I have no idea how it works actually (in google) but I wouldn't be surprised if it was just post-training because recently RWKV people did something similar: They replaced the whole attention mechanism with WKV (forward-only linear attention), and created such franken-stein just by post-training. The big wow moment about that is that it sort of implies that most of the useful knowledge is in the FFN, and attention it…

Attention is just completely arbitrary way to split the network so the learning can be parallelized. What contributed more towards success in my opinion are "shortcut connections" through layers which enable more influence on early layers during learning.

> What contributed more towards success in my opinion are "shortcut connections" through layers which enable more influence on early layers during learning.

For those who don't know, that is the idea behind ResNet (He et al., Deep Residual Learning for Image Recognition, https://arxiv.org/abs/1512.03385), one of the most influential papers in deep learning of all time.

Residual connections make it possible to train networks that are arbitrarily deep. Before ResNet, networks that were too deep were essentially not trainable due to vanishing or exploding gradients.

Re: Gemini Diffusion

#178

Post by rcarmo »

internet_points wrote: post #118
wenc wrote: post #74

Earlier quoted context omitted.

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

Finnish would like a word. Take a random noun like kauppa "shop". It has at least 6000 forms: https://flammie.github.io/omorfi/genkau3.html and that's excluding compounds (written as one word in Finnish) like "bookshop" or "shop-manager" etc. etc. And then you have loan words and slang, derivations into other words classes; all of this is impossible to compactly represent in a full-form word list. Now consider the ma…

"would like a word". I see what you did there...

Re: Gemini Diffusion

#179

Post by campers »

scotty79 wrote: post #162
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 will continue to be handicapped by that lack of institutional knowledge, so to speak Until we give them access to all Jira tickets instead of just one so they know what's missing.

I've been thinking about adding in an agent to our Codex/Jules like platform which goes through the git history for the main files being changed, extracts the Jira ticket ID's, look through them for additional context, along with the analyzing the changes to other files in commits.

Re: Gemini Diffusion

#180

Post by blurrybird »

rcarmo wrote: post #176
dimitri-vs wrote: post #161

Earlier quoted context omitted.

Interesting approach, I'm definitely going to steal your wording for "generate an implementation plan that...". I do something similar but entirely within Cursor: 1. create a `docs/feature_name_spec.md`, use voice-to-text to brain dump what I am trying to do 2. open up a the AI chat panel in "Ask" mode while referencing that spec file, ask (paste) a boilerplate snippet like: "1) Ask clarifying questions about intent,…

That's very close to my workflow: https://taoofmac.com/space/blog/2025/05/13/2230

I’d love to watch a video of this playing out.
Post reply on HN