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

Show HN: Steerling-8B, a language model that can explain any token it generates

guidelabs.ai

Post reply on HN
Print view View original

51–60 of 104 posts

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#51

Post by potato-peeler »

adebayoj wrote: post #43
potato-peeler wrote: post #38

Looks very interesting. Is there a published paper/article on your algorithm? Would like to take a dab at implementing this on my own. I could find this [0], but not sure if that represents the entire system? (Apologies, I am not that well versed in ML) [0] - https://www.guidelabs.ai/post/scaling-interpretable-models-8...

Yes, that is the post that has the most up to date details of the model architecture. Take a look at this: https://github.com/guidelabs/steerling . It has the scaffolding for what you need :)

Got it. Thank you so much.

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#54

Post by adebayoj »

deepdarkforest wrote: post #50

Just wanted to say i think most interpretability research it's just a smoke show nowadays but this is actually the first one that i think has a very serious potential. I love that the SAE is actually constrained and not just slapped unsupervised posthoc. How granular can you get the source data attribution? Down to individual let's say Wikipedia topics? Probably not urls? Would be interested to see this scale to 30/7…

Down to the very exact text chunk in a document! Check this out for an idea of what smaller versions of this style of model can do: https://www.guidelabs.ai/post/prism/. We'll have more to say soon about it. We can trace any generation to 11B chunks (not documents, but actual chunks in the training data).

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#55

Post by theMMaI »

crimsonnoodle58 wrote: post #53

So maybe one day we'll see coding agents like Claude Code create and update an ATTRIBUTION.md, citing all the open source projects and their licenses used to generate code in your project?

Only if there's a commercial incentive to do so methinks. Just one of the things where I expect a legal catch-up is needed to get companies to do the right thing.

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#56

Post by adebayoj »

crimsonnoodle58 wrote: post #53

So maybe one day we'll see coding agents like Claude Code create and update an ATTRIBUTION.md, citing all the open source projects and their licenses used to generate code in your project?

You got it exactly right :) And you can update the attribution.md to have it NOT rely on opensource projects that have been compromised. Imagine asking claude code to write a package/function in the style of a codebase that you care about or force it to ALWAYS rely on some internal packages that you care about. The possibilities are endless when you insert such knobs into models.

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#57

Post by pu_pe »

Looks neat and original, congrats!

I don't quite grasp how to interpret the training data attribution process. For example, it seems to say that for a given sentence like "They argued that humans tend to weigh losses more heavily than gains, leading to risk aversion", 24% is attributed to Wikipedia and 23% to Arxiv.

Does that mean that the concepts used in this sentence are also found in those datasets, and that's what's getting compared here? Or does it mean that you can track down which parts of the training data were interpolated to create that sentence?

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#58

Post by Grimblewald »

gchamonlive wrote: post #49
Grimblewald wrote: post #45

Earlier quoted context omitted.

What I am reading here is that when the model is wrong, it still (at least sometimes) confidently attributes the answer to some knwoledge base, is that correct? If that is the case, how is this different to simply predicting the vibe of a given corpus and assinging provenance to it? Much less impressive imo and something most models can do without explicit training. All precision no recall as it were.

I think this was answered before, with the constraints of the architecture of the model. You can't expect something fundamentally different from an LLM, because that's how they work. It's different from other models because they were not designed for this. Maybe you were expecting more, but that's not OP's fault or demerit.

What you're saying fits my understanding/expectations. However the post and the user I am replying to seem to imply different. This makes me wonder, is my understanding incomplete or is this post marketing hype dressed up as insight? So I am asking for transparency.

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#59

Post by adebayoj »

pu_pe wrote: post #57

Looks neat and original, congrats! I don't quite grasp how to interpret the training data attribution process. For example, it seems to say that for a given sentence like "They argued that humans tend to weigh losses more heavily than gains, leading to risk aversion", 24% is attributed to Wikipedia and 23% to Arxiv. Does that mean that the concepts used in this sentence are also found in those datasets, and that's wh…

Great questions. We weren't quite explicit about the training data attribution process. We'll discuss this in more detail in future work. We can track down which parts of the training data were interpolated to create that sentence. For those training data sentences, we then compare the concepts between generated and training.

We can attribute to exact sentences and chunks in the training data. For the first release, we are sharing only concept similarities. Over the coming weeks, we'll share and discuss how you can actually map to the exact training sentence and chunk with the model.

For a technical overview of how some of these models work, check this link out: https://www.guidelabs.ai/post/prism/

Re: Show HN: Steerling-8B, a language model that can explain any token it generates

#60

Post by adebayoj »

aziis98 wrote: post #48

Does anybody know if I can try this online?

Take a look at the link in the blogposts. Here is a github link as well: https://github.com/guidelabs/steerling. The model weights are on huggingface, so you can play with it.
Post reply on HN