I have written zero skills, so not sure how normal it is. I counted the words in couple of them and they seem to be around 2k range. So 5 skills would be around 10K. Even at a small LLM context of 128k, that's still around 10%. And for a 1M context window like the big ones, it barely registers.
If there is anything we have learned in decades of Software engineering, it's "A clear outcome" is not easy to describe. In many cases, it's impossible unless people from 4 different domains collaborate. That's why process matters. It allows for software to be built is a "semi-standardized" way that can allow iterations to get us closed towards the expected outcome, that might emerge over time.
Yes, not everything I use LLMs for going to have the same level of ambiguity or complex requirements. Optimizing by choosing to skip over parts of the process is exactly Addy is talking in this article.
Seriously though, why is it a model "card", safety "card"? I had to lookup to learn that it comes from HuggingFace's vague definition of "README" in the model's repo. This is such a specific thing that I don't think anyone except a very small population would know - not the users, not the c-suites.
I don't like Musk or Grok. But not knowing what's a safety card is not a signal of anything IMO.
The "model card" concept actually comes from a pre-LLM Google paper (https://arxiv.org/abs/1810.03993), where the example cards did fit on a single page. The concept quickly became a standard component of AI governance frameworks, and Hugging Face adopted it as a reasonable standard format for a model README. As LLMs emerged and became more capable at broader ranges of tasks, model cards expanded to the sizes we see today.
That makes sense. I recall a “battle card“ (“concise, easy-to-scan document that helps [sales] reps handle competitive conversations, respond to objections, and highlight key differentiators” per HubSpot) as about a half sheet document, which is congruent.
But users don’t need to know you’re 100% right, you shouldn’t need to know this inside baseball (you didn’t pollute & compute & gain the responsibility).
> Seriously though, why is it a model "card", safety "card"?
My assumption is because "card" has a more formal tone than a README, which is more like a quick "how to use the software" guide.
Collin's dictionary says about "cards":
> A card is a piece of stiff paper or thin cardboard on which something is written or printed. (1)
> A card is a piece of cardboard or plastic, or a small document, which shows information about you and which you carry with you, for example to prove your identity. (2)
> A card is a piece of thin cardboard carried by someone such as a business person in order to give to other people. A card shows the name, address, phone number, and other details of the person who carries it. (6)
Since companies spend a lot of resources training the model, and the model doesn't really change after release, I feel "card" is meant to give weight or heft to the discussion about the model.
It's not meant to be updated like a README or other software documents, it's meant to be handed out to others as a firm, unchanging "this is a summary of the model and its specifications", like a business card for models.
Kudos. I set on this exact journey a couple of days back and Pi is what I started reading for inspiration as well. I really can't stand the text boxes and the animations of the mainstream harnesses.
I'm not a teenager anymore but I thoroughly enjoyed it, a lot better than some random dev breathlessly talking about how they haven't written a line of code in 6 months, or an article talking about how LLMs lead to the end of programming/the economy/the world, etc etc.
If you have never used an LSP and don’t need it, you can just turn the LSP off. I do it from the UI (thunderbolt icon on bottom bar I think) for some projects which don’t have LSP typing support. There should also be a setting to turn off permanently.
This is one of those articles that I read and realise how different people and process are.
I fully agree with this method. In fact, my surprise mostly stems from the necessity to write this article. So there are places where comments on PRs are avoided as they are considered “unapproved”? Man oh man.
Check the lsp servers that run when you are editing TS file. I noticed something like 5-6 when editing a TSX file. There was even tailwind thrown in for a good measure (the project has no tailwind). All that buttery smooth 120fps wasted on poor resource management when it comes to LSPs.
100%. A picture is worth a thousand words only when it conveys something. I love to see the pictures from my family even when they are taken with no care to quality or composition but I would look at someone else’s (as in gallery/exhibitions) only when they are stunning and captured beautifully. The medium is only a channel to communicate.
Also, this can’t be real. How many publications did they train this stuff on and why are there no acknowledgment even if to say - we partnered with xyz manga house to make our model smarter at manga? Like what’s wrong with this company?
reply