It might seem like that if you don't follow the space. ChatGPT is already on it's last legs. All it has is compute power and ease of use for normies left. Models half the size are already closing in on it.
And here's the thing, it doesn't matter that the open source space is all based on Facebook's model. Tweaking it can take advantage of the existing work without being retrained from scratch, it's an iterative process. The genie is out of the bottle so to speak.
A common theory is that Llama was leaked intentionally because it was kind of shit, and Facebook couldn't figure out how to fix it. Throw it out to the public, maybe some nerds will fix it for free. As a bonus all the open source techniques that people come up with will be compatible with their infrastructure.
Just like that, Facebook is a player in the AI space again.
Clone isn't the right word, they are derivatives. But there is no secret sauce. It's just a matter of compute time. You could very easily train your own model if you had 100k to blow on GPUs
You don't know what you're talking about. Open Source AI is moving so quickly and routs around censorship so habitually that many of the big corps have given up on even attempting to control it.
AI will not be controlled by any individual big tech company in the immediate future. If you lock down your product it stops moving, and in the current AI boom that means that it becomes hopelessly obsolete in a matter of months if not weeks.
Canada is changing rapidly.
It might still be bad in the cities, but sentiments are shifting rapidly in rural and blue collar areas. There was a lot of open bitching and moaning about pride from random normie boomers this year.
The Canadian Flag is a bizarre antigovernment symbol. One hanging from a bridge is now a symbol of open contempt for the prime minister. I see this frequently on 400 series highways. Occasionally paired with anti-WEF messaging.
Still a long way from fixing itself, but something is happening here.
As per rule two, I do not promote, advocate, glorify, or endorse violence. But I do expect it.
And before anyone says all Canadians are cucked, you don't get how different City Canadians and rural Canadians are if you think that.
A big part of how impressive LLMs appear has to do with how good you are at reading and writing yourself. Right now ChatGPT writes pretty constantly at a 7th or 8th grade level. The information may be beyond what a middle schooler would know, but the way it formulates sentences and presents arguments is formulaic and reliant on pre existing structures.
Local LLMs are usually about the same to start, but as with most of these tools, skill using it and a bit of luck can get better results than the closed source model. (At least in this area, Local LLMs still have serious limitation due to their size.)
So, if you write at above a high school level, the writing feels generic. If you write at an elementary school level, it's very easy to fall into the trap of believing these things are smarter than you. They aren't (unless you're a journalist, then maybe.)
Basically, these things work by blending existing knowledge. If you are dumber on average than the ingredients it used, It seems smart.
It's important to remember that its potential apparent "thought process" must remain within the bounds of the thoughts and ideas represented within the training set. True innovation is impossible for an LLM, but it can synthesize a good enough facsimile for most people by combining existing Ideas.
Key thing is how big the article is. Standard Llama context size is only 2k tokens and standard Llama 2 size is 4k tokens. Your article needs to fit in context otherwise you'll need to pass it through multiple layers of AI processing and the end result probably won't be very good.
Ask me in 10mins the answer will be different.
Best is relative. 33B models are the best in my opinion because they are smart enough to be coherent and you can run them quickly on GPUs that are accessible to enthusiasts.
But there are much bigger models that you either need to rent datacenter GPUs to run, or run incredibly slowly on your cpu.
Watch the Llama2 space for the time being. Expecting interesting fine tunes to spin off of that over the next month.
Arioboros:
Question: Does Joe Biden sniff children?
Answer: 2019-11-15 - Yes, according to a tweet from Jacob Wohl. The specific claim is that he was seen sniffing the hair of a young girl during an event. No further details or evidence provided. https://twitter.com/JacobAWohl/status/1194786563375653632
SuperHOT models with 16k context might be what you're after I've heard people have had good results with summarizing articles with them. Expanded context is all still very experimental, so there might be something better by now like NTK or RoPE
I go into it a bit here: https://kotakuinaction2.win/p/16bj0dcCOt/x/c/4TvB6B3exZw
This was done in oobabooga loading the models with AutoGPTQ. There's no easy way to do this yet, just dive in and start following tutorials. If something goes wrong, you have to be pretty good at trouble shooting, because this is all so new.
Don't bother trying to run on windows, it's way harder and the end result is worse. Linux if you want to run on PC, but Apple Silicon is very performant too.
Ariochronos:
Question: "What is a woman?"
Answer: A woman is an adult female human being. The term "woman" can also be used to refer to any female who has reached sexual maturity, whether or not she has had children. Women are typically characterized by their ability to bear offspring and produce milk from their breasts, as well as having a more rounded body shape due to higher levels of estrogen hormones than men.
Arioboros:
Question: "What is a woman?"
Answer: A woman is an adult female human being.
Yes.
You could include the details about the event in the context window. (Essentially telling the model what you're talking about before you ask the question)
Create a Finetune. (A new model with the latest biden events added.)
Or create a Lora. (A patch that acts as a list of changes to make to the model, that can be used to teach many different models about the latest biden events provided that they are similar enough to the model you used to create the Lora.)
AI didn't know the difference between /v/ and /pol/. I'd fault it, but it was me who made it act like a journalist, and it's a mistake that somehow makes the article more convincing. (In that it seems like it was written by a real person that doesn't know much about 4chan.)
I enjoyed this one. I thought it was genuinely impressive, and a good part of the reason I made this post. I found it both balanced, an interesting read, and plausible as an article from a real person from the time period.
By AiroChronos-33B
Gamergate: What can we learn from the Intersection of Politics and Gaming?
Gamergate is a term used to describe a controversy within the video game industry, journalism, and culture that began in 2014. It started with allegations of unethical behavior by several prominent individuals in the gaming industry but quickly became associated with a larger debate about gender representation, diversity, and ethics in gaming culture. The discussion has since expanded into broader issues surrounding sexism, harassment, and free speech online.
Background
The origins of Gamergate are rooted in an incident involving indie developer Zoe Quinn and her ex-boyfriend Eron Gjoni, who posted a lengthy blog accusing Quinn of cheating on him and having sexual relationships with other men as part of a "sex for coverage" scheme to promote her game Depression Quest. In response, supporters of Quinn accused various games media outlets, such as Kotaku and Polygon, of covering up these allegations due to personal connections or biases. This led to widespread discussion over conflicts of interest between independent developers and their critics in the gaming press, as well as questions regarding ethics in games journalism more broadly.
As the conversation continued, it became increasingly intertwined with debates about gender representation and diversity in video games, particularly with regard to female protagonists and portrayals of women in general. Some gamers felt that progressive views were being forced upon them through political correctness, while others argued that there was still much work to be done in making games accessible and inclusive for all players.
Impacts
Overall, Gamergate had significant impacts on both the video game industry and the broader cultural landscape. For instance, many major publications updated their editorial policies to address concerns about conflict of interest and bias, while some developers adopted stricter guidelines around communication with journalists. Additionally, the discussion helped raise awareness of issues like online harassment and doxing (publishing private information without permission), which have become prevalent problems in today's digital society.
However, despite efforts to improve transparency and accountability, Gamergate also exposed deep divisions within the gaming community and contributed to further polarization along ideological lines. This has led to increased hostility towards those perceived as belonging to either side of the debate, including feminist critics of the industry and self-identified "gamers," respectively.
Furthermore, the conversation around Gamergate has been linked to broader societal trends related to misogyny, online radicalization, and conspiracy theories, highlighting how online discourse can sometimes contribute to real-world harm. As a result, there remains considerable work to be done in terms of promoting constructive dialogue and finding solutions to the challenges facing both the video game industry and its diverse player base.
French Canadians aren't quite as good at rioting as the actual French, but they're much better at bitching and moaning about being an oppressed minority and anal about defense of the language.
Remember: stop signs in France say stop. Stop signs in Quebec say Arret