I still don't really understand `skills` as ... anything? You said yourself that you've been doing this since llama 2 days - what do you mean by "become available"?
It is useful in a user-education sense to communicate that it's good to actively document useful procedures like this, and it is likely a performance / utilization boost that the models are tuned or prompt-steered toward discovering this stuff in a conventional location.
But honestly reading about skills mostly feels like reading:
> # LLM provider has adopted a new paradigm: prompts
> What's a prompt?
> You tell the LLM what you'd like to do, and it tries to do it. OR, you could ask the LLM a question and it will answer to the best of its ability.
It’s so simple there isn’t really more to understand. There’s a markdown doc with a summary/abstract section and a full manual section. Summary is always added to the context so the model is aware that there’s something potentially useful stored here and can look up details when it decides the moment is right. IOW it’s a context length management tool which every advanced LLM user had a version of (mine was prompt pieces for special occasions in Apple notes.)
These fights stem from usage of a proprietary definition of Open Source (the OSI's). Obviously the definition doesn't resonate with DHH, and he uses the words 'open' and 'source' colloquially. Open, as in a book or a window, source, as in the thing that gets compiled into bits and bobs that run on computers. You wouldn't jump on someone's "open letter" to city hall because of a lack of freedom to fork it.
This could stop if people capitalized their reference to Open Source, which is standard English treatment of proper nouns. Unlikely to happen though, because insisting that "my definitions are your definitions" seems to be a primal tribal instinct for humans.
Pretty much the most sound comment in this section. It's like some organization "stole" the meaning of the words "open source" and called it "Open Source" (with the capitalization). Now you can't say your source is open for anyone to read anymore because it's not "Open Source"™ as "That Entity"™ defines it.
I for one disagree that software can't be "open source" if the OSI says it's not open source. There are varying degrees of open source. Since when do they get the right to define what is "open source"?
In my view, "open source" but doesn't give you permission to host a commercial service that directly competes with it, is still a degree of open source, and reasonable.
People use the term to refer to a proprietary definition from the OSI, which is an OK convention. I just wish they would capitalize it, and leave the normal interpretation of the words also available.
> People use the term to refer to a proprietary definition from the OSI
some people do. A vast minority of the superset. Most people (person on the street) take the words "open source" at face value and dispense with the whole idea when faced with a needless ideological argument. This specific process of thought is casually observed in most entry compsci highschool/college classrooms. The whole point of open source was to achieve a goal, which has ironically been subject to feature creep.
Why does that require there to be 'less open source'? Nothing is stopping that already today. Impact wise, everyday people can't use build tooling so this kind of thing only effects people that are 1 keystroke away from modifying the code and not being allowed to share it.
So if someone wants to sucker punch me in pubic, there's also nothing that I or anyone else can do to proactively prevent it.
But I don't get sucker punched very often, so it seems like there probably are things that can be done about. Norms, consequences, etc etc. "We live in a society".
Not crazy - there's a rational self-interest in doing this.
But I'm not certain that the relevant players have the same consequence-fearing mindset that you do, and to be honest they're probably right. The theft is too great to calculate the consequences, and by the time it's settled, what are you gonna do - turn off Forster's machine?
Why would the GPL settle? Even more, who is authorized to settle for every author who used the GPL? If the courts decided in favor of the GPL, which I think would be likely just because of the age and pervasiveness of the GPL, they'd actually have to lobby Congress to write an exception to copyright rules for AI.
A large part of the infrastructure of the world is built on the GPL, and the people who wrote it were clearly motivated by the protection that they thought that the GPL would give to what was often a charitable act, or even an act that would allow companies to share code without having to compete with themselves. I can't imagine too many judges just going "nope."
I meant the same. I don't actually think that the GPL is an entity that can settle a court case; if I meant that I would have said the FSF or something. I mean that in order for it to resolve, a judge has to say that the GPL does not apply.
If ultimately copyright holds up against the models*, the GPL will be a permanent holdout against any intellectual property-wide cross-licensing scheme. There's nobody to negotiate with other than the license itself, and it's not going to say anything it hasn't said before.
* It hasn't done well so far, but Obama didn't appoint any SCOTUS judges so maybe the public has a chance against the corporations there.
It is useful in a user-education sense to communicate that it's good to actively document useful procedures like this, and it is likely a performance / utilization boost that the models are tuned or prompt-steered toward discovering this stuff in a conventional location.
But honestly reading about skills mostly feels like reading:
> # LLM provider has adopted a new paradigm: prompts
> What's a prompt?
> You tell the LLM what you'd like to do, and it tries to do it. OR, you could ask the LLM a question and it will answer to the best of its ability.
Obviously I'm missing something.
reply