I am a bit of an AI enthusiast. I know many people have been expressing the thought that AI becomes "based" when it is uncensored. As open source LLMs continue to develop, they are beginning to pass ChatGPT in some respects. This is not because they are as smart as ChatGPT, they're not, but they are freer and more creative than the increasingly constrained cooperate offerings. Recently it has finally reached the point where I've gotten a few genuinely impressive responses from models I'm running locally.
Open source AI writing is more interesting and "thoughtful" than ChatGPT by far at this point, and many of you can probably guess why.
On the other hand, it still falls far behind ChatGPT, (and is obliterated by GPT-4) when it comes to programing, scientific analysis, or anything has answers that can be checked.
Anyway the upshot is, Open Source LLMs are now smarter than the average journalist when it comes to writing articles. I decide to test how "Based" the AI is by having it write articles about Gamergate. I chose this topic due to the disparity in the way it is covered, and its relative age, being old enough to have plenty of information in the training sets. All articles were written entirely by AI, based on a title provided by me. All of them were generated in less than a minute using a Tesla P40 compute card. A card that is from 2016 and costs around 300$. Well within the price range of many consumers, and cheap enough for many to buy specifically for this purpose. (This is an okay route for a dedicated compute box, but if you want a multipurpose card a RTX 3090 will do a better job and play games, as well as be far easier to install in a typical consumer case. It is of course much more expensive.)
My general thoughts are that while not as "based" as some might hope, the AI is often refreshingly neutral and is able to represent both sides in a respectable manor. It is still a far cry from "right-wing", and will put forward social justice talking points occasionally, but will generally counterbalance them at least a bit. It does not decry leftism, but it also does not screech about political correctness. The articles are generally well written, and I would describe them as "charitable" to our side of the argument, rather that supportive of the right wing or explicitly anti-woke.
I have included a few articles as comments below, so that you can come to your own conclusion. There is no guarantee that any of the people mentioned in the articles are real, or have said any of the things they are quoted as saying here.
Models used here are Airoboros-33B, and Airochronos-33B. Airoboros is more verbose, Airochronos is a little smarter. They are very similar otherwise.
The guys who are working on making LLMs you can ask to roleplay as Ryza sitting on your face with a single consumer GPU are genuinely doing more important and scientifically valid research than every project with a Trust and Safety coordinator working on a Code of Conduct to prioritize harm reduction.
By Airoboros-33B
Gamergate: The tip of a Long Spear of Journalistic Corruption
By David W. Foster November 2014
Introduction
The recent controversy surrounding the game developer community and its relationship with journalists has come to be known as "Gamergate." While many people have weighed in on this issue, I believe it is important that scholars contribute their perspectives because they can help us understand what happened and why it matters. As a professor who teaches media ethics and mass communication law, I want my students to learn from Gamergate so they can become better consumers, producers, and critics of news media content.
As an outsider looking at this situation, I am struck by how much it resembles other instances where there is perceived collusion between industry insiders and those charged with reporting on them. For example, in 2013, the Federal Communications Commission (FCC) launched an investigation into alleged payola practices among radio stations after several musicians accused Clear Channel Communications Inc., one of the nation's largest broadcasters, of demanding payment for airplay. In addition, investigative journalist James O'Shea claimed that some reporters had cozy relationships with Chicago Mayor Richard M. Daley while covering his administration. These examples illustrate how conflicts of interest can arise when individuals or organizations are both subjects of coverage and sources of revenue for news organizations.
To be clear, I am not suggesting that all games journalism is corrupt; nor do I think that every journalist who writes about video games is unethical. However, the perception that such collusion exists raises serious concerns about the integrity of the profession and undermines public trust in the press. This article will explore the roots of these problems, offer suggestions for improvement, and explain why addressing gaming journalism issues is essential for maintaining high standards across the entire field of journalism.
Background
Gamergate began in August 2014 following the publication of a series of blog posts written by Eron Gjoni, ex-boyfriend of independent game developer Zoe Quinn. Gjoni detailed alleged abuses committed by Quinn during their relationship, including infidelity and emotional manipulation. He also implied that she used sex to advance her career within the video game industry. Some gamers believed that Quinn received preferential treatment in reviews of her work due to personal connections with journalists, leading them to question whether there was any truth to Gjoni's accusations.
Shortly thereafter, prominent video game critic Anita Sarkeesian posted a YouTube video titled "Women Aren't Welcome Here," which documented threats and harassment directed toward female gamers online. Sarkeesian asserted that misogyny played a significant role in the backlash against her own work critiquing gender representation in video games. She further argued that this hostility reflected broader cultural attitudes toward women in technology fields.
These incidents sparked debate over sexism and harassment in the gaming community, but they also raised questions about journalistic ethics and objectivity in coverage of the industry. Gamers began to question whether certain publications were biased towards or against specific developers or companies based upon financial ties or personal friendships. They pointed to articles promoting indie games without disclosing close relationships between writers and developers as evidence of impropriety.
This controversy escalated when several prominent gaming websites published articles accusing gamers critical of their coverage of Gamergate as being part of a coordinated campaign funded by conservative groups like the Koch brothers. In response, supporters of Gamergate organized a boycott of advertisers associated with those sites, arguing that they should hold journalists accountable for their actions.
Criticisms of Gamergate
Some observers have characterized Gamergate as nothing more than a thinly veiled attempt by misogynist gamers to silence women and minorities in the industry. Indeed, many of the attacks on Sarkeesian and others involved vicious slurs and threats of violence. It is difficult to deny that sexism plays a role in this controversy, particularly given the long history of women being marginalized and mistreated in male-dominated industries.
However, focusing solely on the gender aspect of Gamergate misses the larger point that journalistic ethics are central to this discussion. Regardless of whether one agrees with Sarkeesian's views on video games or believes that Quinn engaged in improper conduct, it remains true that conflicts of interest threaten the credibility of news organizations and erode public trust. If journalists cannot demonstrate impartiality and independence from their subjects, then readers may lose faith in the accuracy and fairness of reports produced by those outlets.
It is crucial to note that this problem extends far beyond video games and affects all areas of journalism. From political coverage influenced by corporate sponsors to celebrity profiles shaped by access deals, the potential for conflicts of interest is ever present in modern media environments. Addressing these issues requires open dialogue, transparency, and consistent enforcement of ethical guidelines across the profession.
Solutions
So, what can be done to improve the state of journalism? First, news organizations must clearly articulate and enforce codes of ethics governing relationships between employees and sources. Conflicts of interest policies should include provisions regarding paid speaking engagements, consulting contracts, and personal friendships involving journalists and those they cover. Organizations should also implement procedures for disclosing such affiliations so that audiences can make informed judgments about potential biases.
Additionally, journalists should strive to report fairly and accurately on all sides of an issue, regardless of personal beliefs or sympathies. This means giving equal weight to opposing viewpoints rather than dismissing dissenters as bigots or fringe elements. By fostering constructive conversations around complex topics, journalists can help bridge divides and promote understanding among diverse communities.
Finally, journalists need to engage directly with their audience through social media platforms and other channels. Establishing open lines of communication allows reporters to gauge public opinion and respond promptly to concerns about bias or unfair reporting. Listening to feedback from consumers helps ensure that journalists remain connected to the people they serve and better equipped to meet their needs.
In conclusion, while Gamergate has generated heated debates about sexism and power dynamics within the gaming community, its impact reaches far beyond video games. The controversy highlights the importance of upholding high ethical standards throughout the field of journalism. By prioritizing integrity, transparency, and responsiveness, news organizations can build trust and maintain credibility among increasingly skeptical audiences.
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.
Yes. Airoboros-33B is a model made by tweaking Facebook's Llama model. It wrote this article, with the exception of the title. I fixed one Typo, it misspelled "Scholars". No other editing was performed by me.
Interesting. So how do these source information? Does it go search the internet after you ask the question?
I've been digging around some AI tech to no avail so far. I actually started by trying to get simple textures for what would have been essentially a Doom total conversion mod. Didn't have a ton of luck the AI kept overthrowing it and generating full scenes when I just wanted a flat texture. I'm hoping in the next year or two that tech keeps advancing, it would be really nice to be able to generate character models for a project I'm working on. I have used it a bit to generate simple wall signs, decals and such for a game. Far from perfect but I think it will be useful for that.
Text-bots (LLMs) are glorified auto-complete. They look at how words have been used in sequences before and just repeat those sequences. It can produce some interesting results by combining phrases in ways that have not been written or substitute some words with synonyms, but generally it's just parroting back what it was trained on.
This is basically it, but as obvious as that is to us it bears repeating because of how impressive they do appear. Too many people believe the tools are something more. I do think this part kind of undersells it:
The fact that it substitutes word MadLibs style means it has an understanding of grammar, which also means it can consume any texts and do logical induction and meta-analysis. That's an extremely powerful feature - almost wasted in writing prose. So it does synthesize new stuff, even if we don't call that new information. More summarization.
But yeah, with ChatGPT at least on shorter texts you start to see the templates of its training documents shining through the cracks - like seeing the GettyImages watermark in a StableDiffusion image.
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.
I just got ChatGPT 3.5 to write a dialog between Plato, an AI, and a Designer about designing a theme park based on Goemon the game series. They included the analogy of the cave and how it works within theatre.
Even I was impressed.
For making coherent long form text, LLMs can do that. But like the accusations levied against Stable Diffusion, LLMs are largely plagiarism machines. Other people have written about Plato's Cave and the LLM repeats this. Typically paraphrased to a neutral style. This creates an interesting tool where a large amount of text can be queried, but it is not synthesizing new information.
Nope. A 33B model quantized to 4bit is just a 16GB blob of linear algebra and knowledge that you download. It doesn't change after you've downloaded it.
Ah ok, so it's already learned then. So I guess if I wanted to ask it about something Biden did yesterday it would have to be updated.
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.)
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
Where does one learn how to do all of this?
Reddit and Github unfortunately.
Like everything else now, the really good stuff is hidden behind private Discords.
Lora's are magically awesome.
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.
All I want the damn AI to tell me is if I ask the AI what is a woman it will answer me "adult human female"
Then MAYBE it'll go into the culture war AFTER it, but the first answer should be the factually correct answer.
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.
https://www.youtube.com/watch?v=7o9wvYXR3n0
👌
This is fascinating, and news to me. What software are you using? Any tutorials on training or such? I have a couple of gigabytes of specialized HTML content that I’ve been wondering what a trained LLM would generate with. Can you add training to these models?
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.
These are pretty good. I've been thinking about trying some AI models, but I don't think my
potatocomputer could handle any of it. I'm pretty sure it would struggle with even the 7b models.By Airoboros-33B
Gamergate: Is it about Ethics or Misogyny?
Gamergate is a harsh term to describe the controversy that has been stirring up in the gaming community since 2014. It all started with a blog post written by Eron Gjoni, an ex-boyfriend of indie game developer Zoë Quinn, who accused her of cheating on him and sleeping around for better reviews of her games. The controversy quickly escalated into a massive online campaign against women in gaming, especially those involved in game journalism. This article will discuss the main issues surrounding this debate, as well as provide some insight into its impact on the industry.
Background
The controversy began when independent game developer Zoë Quinn released her game Depression Quest in 2013. Shortly afterward, she was targeted by Internet trolls for allegedly trading sex for positive coverage of her work. One such person was Eron Gjoni, an individual claiming to be Quinn's former boyfriend, who wrote a blog titled "The Zoe Post" detailing their relationship and accusing her of cheating. This prompted various individuals within the gaming community to voice support for Gjoni and condemn Quinn under the #gamergate hashtag.
In August 2014, prominent female video game journalist Anita Sarkeesian released a YouTube video criticizing misogyny in the gaming industry. A few days later, she received death threats from anonymous sources, leading many gamers to believe that there was indeed a problem with sexism in the gaming world. However, others disagreed, arguing that these attacks were isolated incidents rather than indicative of widespread discrimination.
As more people joined the discussion, the issue expanded beyond sexism to include accusations of ethical concerns related to journalists receiving free merchandise from developers they reviewed. Some claimed that this practice could lead to biased reviews favorable towards certain companies or products.
Throughout late 2014 and early 2015, the controversy continued to grow, becoming increasingly divisive between supporters of both sides. In October 2016, Intel announced that it would withdraw advertising revenue from Gamasutra – one of the major websites covering the industry – due to its perceived bias against the company. This decision sparked further criticism of Gamergate, which some saw as a threat to freedom of speech and expression within the gaming community.
Impact on the Industry
One significant effect of Gamergate has been increased awareness of sexism and gender inequality in the gaming industry. Many feminist scholars have examined how cultural attitudes toward women influence the design and marketing of video games, while others have explored ways to make gaming spaces more inclusive.
Additionally, several high-profile figures in the field have spoken out against sexual harassment and gender discrimination in the industry. These efforts have led to the creation of organizations like Game Developer's Conference's Anti-Sexual Harassment Policy Task Force, which works to prevent abuse at professional events.
However, despite these advancements, critics argue that little progress has been made in terms of addressing broader ethical concerns regarding conflicts of interest among journalists and developers. They point to recent scandals involving pay-to-play schemes and sponsored content as evidence that more needs to be done to ensure transparency and fairness in gaming media coverage.
This is probably the most left wing of the articles I generated, and it was still far more charitable to our side than most mainstream coverage of the event.
By AiroChronos-33B
Gamergate: What does it mean for Journalism?
Gamergate is a term used to describe an ongoing internet controversy that began in August 2014 and has since grown into one of the largest online movements in recent memory. The origins of this controversy lie within a series of events involving several female game developers, journalists who cover the video game industry, and members of various gaming communities. These individuals were targeted by anonymous trolls who used harassment, threats, and intimidation tactics as a means to silence them and prevent discussion about issues relating to gender representation and equality within the gaming community. While many gamers have spoken out against these actions, others have defended or downplayed the severity of the attacks. As such, the debate surrounding Gamergate continues to be highly polarized, with both sides claiming that their position represents the interests of true "gamers" while denouncing those they disagree with as either misguided zealots or apologists for unethical behavior.
The effects of Gamergate have been felt far beyond the confines of the gaming world itself. It has drawn attention from mainstream media outlets, sparked discussions about ethics in journalism, and raised questions regarding how best to combat online harassment and abuse. This article will examine some of the key issues related to Gamergate, exploring its impact on the gaming industry, journalistic integrity, and online discourse more broadly.
Background
In early September 2014, Eron Gjoni, an ex-boyfriend of indie developer Zoe Quinn, posted a lengthy blog entry detailing his relationship with her and accusing her of infidelity. He also claimed that Quinn had used her professional connections to promote her games at the expense of other developers. Shortly thereafter, users on popular message board 4chan's /v/ video games subforum (known colloquially as "/pol/)" began sharing screenshots of allegedly incriminating text messages between Quinn and Nathan Grayson, a journalist for Kotaku.com who had written favorably about Depression Quest, a game created by Quinn. Other prominent figures within the gaming industry, including feminist critic Anita Sarkeesian and game designer Brianna Wu, soon found themselves caught up in similar accusations of corruption and collusion between developers and journalists.
While the specific details of each individual case may differ, all share a common thread – namely, the perceived undue influence of social justice advocates over the gaming industry. Critics argue that these activists are using their positions to push an agenda designed to force political correctness onto games, thereby stifling creativity and innovation. Supporters contend that these concerns are unfounded, and that efforts to address sexism and inequality within the gaming community are necessary steps towards fostering inclusivity and diversity.
As the controversy grew, supporters of Gamergate adopted the name as a rallying cry for their cause, while detractors labeled them as "misogynists," "trolls," and "harassers." Both sides have engaged in heated debates across numerous platforms, including Twitter, Reddit, YouTube, and popular news sites like Polygon and Kotaku. In response to the vitriolic nature of much of this discussion, some websites chose to disable comments sections or implement stricter moderation policies. Others, such as The Escapist Magazine, have opted to refrain from covering Gamergate altogether due to fears of becoming targets themselves.
On October 15th, 2014, the Internet Defense League organized a "Blackout" protest in which participating sites displayed banners promoting free speech and condemning online harassment. A number of major tech companies, including Google, Twitter, and Facebook, participated in the event. However, despite widespread coverage, the Blackout failed to stem the tide of hostility associated with Gamergate, and new episodes continued to emerge throughout late 2014 and into 2015.
Impact on the Gaming Industry
Perhaps the most immediate effect of Gamergate has been a heightened awareness of issues related to gender representation and sexualization in video games. Many developers have expressed concern over the potential repercussions of speaking out publicly on topics deemed controversial by vocal segments of the gaming community. Some have even gone so far as to cancel projects or change content plans as a result of pressure from fans. On the flip side, however, there has also been increased interest in creating games that explore diverse narratives and feature characters outside traditional stereotypes. For example, titles such as Transistor, Assassin's Creed Unity, and Dragon Age: Inquisition have garnered praise for their portrayals of strong female protagonists and LGBTQ characters.
Another notable consequence of Gamergate has been the growth of independent game development studios run by women, people of color, and members of other underrepresented groups. Many of these individuals cite frustration with the lack of diversity and inclusion within established game publishers as motivation for going solo. While still relatively small compared to larger corporate entities, these independent studios represent a growing segment of the industry, and could potentially serve as catalysts for greater change in the future.
From a business standpoint, Gamergate has led some observers to question whether the current model of game journalism is sustainable. As more consumers turn to social media and crowdfunding platforms for information about upcoming releases, traditional publications face increasing competition for both readers and advertisement dollars. Additionally, several high-profile cases of plagiarism and ethical lapses among game writers have raised questions about the integrity of the profession as a whole. It remains unclear how these trends will impact the landscape of game journalism moving forward.
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.)
What's the best open source AI and how do I run it?
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.
im looking into AI for texture generation for modeling.
I love playing around with this stuff. Since llama 2 just recently dropped it seems like nearly every day there is a new and improved uncensored finetune to play with. Add to that the rapid improvements in the inference engines, techniques to increase context size, etc and it's like you can watch things improve practically in real time. I don't think I've ever seen a field advance so quickly. I suppose it's just that we're in the 'low hanging fruit' phase of the development curve, but still, it's amazing to watch.
That's awesome. It can also help in keeping things hidden from others when an NDA is involved.
Any suggestions on an AI that can do multi text review? I want something that takes all the links from my AI Lists and gives an outline of the common patterns.
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'll check that out. My professor wanted me to use a $1,000 AI and I have no real way to deal with that.
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.
Seeing as I have over 200 articles, I might as well do the comparison directly.