Good Morning from my Robotics Lab! This is Shadow_8472, and today I am going farther into the world of AI chat from the comfort of my own home. Let\u2019s get started!<\/p>\n\n\n\n
Last week, I got into Silly Tavern, a highly configurable AI chat playground with tons of features. Accomplishing a functional setup was rewarding on its own, but I am having my mind blown reading about some of the more advanced features. I want to explore farther. Notably: I am interested in a long term goal of posing characters with text and \u201ctaking pictures,\u201d as well as locally powered AI web search.<\/p>\n\n\n\n
Stable Diffusion<\/p>\n\n\n\n
My first serious exploration into AI was image generation. Silly Tavern can have the LLM (Large Language Model) write a prompt for Stable Diffusion, then interface with tools such as Automatic1111 through an API\u2019s (Application Program Interface) to generate an image. Similarly to the LLM engine, A1111 must be launched with the –api<\/strong> flag. I haven\u2019t yet spent much time on this since getting it working.<\/p>\n\n\n\n Web Search<\/p>\n\n\n\n It is possible with a plugin to give your AI character the ability to search the Web. While historically this was done through something called the Extras API, the official documentation noted how it is no longer maintained as of last month and that most of the plugins work without it. The step I missed on both this and Stable Diffusion last week was connecting to their repository to download stuff. Anything else I tried kept getting ignored.<\/p>\n\n\n\n I configured AI search to use DuckDuckGo through Firefox. Let\u2019s just say that while my AI search buddies appear to have a knack for finding obscure documentation, they do suffer from hallucinations when asking for exact products, so always double check the AI\u2019s work.<\/p>\n\n\n\n A favorite interaction I had AI searching was looking up how much I probably paid for my now dying tablet (Praise God for letting me finish backing it up first!), a Samsung Galaxy Tab A 10.1 (2016). The bot said it originally sold for around $400 citing MSRP (Manufacturer\u2019s Suggested Retail Price, which I did not know previously). I went and found the actual price, which was $50 cheaper and closer to what I remember its price tag being.<\/p>\n\n\n\n LLM Censorship<\/p>\n\n\n\n While my experience with Artificial Intelligence so far has been a fun journey of discovery, I\u2019ve already run into certain limitations. The companies releasing LLM\u2019s typically install a number of guardrails. I used AI to find a cell phone\u2019s IMEI number, but Crazy Grandpa Joe might make bombs or crack with it in his son\u2019s kitchen using common ingredients. This knowledge is legal, but the people training LLM\u2019s don\u2019t want to be seen as responsible for being accessories to crime. So they draw a line.<\/p>\n\n\n\n But where should they draw this line? Every sub-culture differs in values. [Social] media platforms often only allow a subset of what\u2019s legal for more universal appeal; your .pdf giveaway of Crime This <\/em>From Home<\/em>!<\/em> will likely draw attention from moderators to limit the platform\/community\u2019s liability before someone does something stupid with it. In the same line of reasoning, if LLM trainers wish to self-censor, then that is their prerogative. However, progressive liberal American culture doesn\u2019t distinguish between potential for danger and danger itself. LLM\u2019s tend to be produced under this and similar mentalities. It is no surprise then that raw models \u2013when given the chance\u2013 are ever eager to lecture about environmental hyper-awareness and promote \u201csafe\u201d environments.<\/p>\n\n\n\n It gets in the way though. For example: I played a scenario in which the ruthless Princess Azula (Avatar: The Last Airbender) is after a fight. The initial prompt has her threatening to \u201c…incinerate you where you stand\u2026\u201d for bonking her with a vollyball. I goaded her about my diplomatic immunity and suddenly she merely wanted my head. At, \u201cI will find a way to make you pay for this,\u201d I jokingly tossed her a unit of currency. It went over poorly, but she still refused to get physical. I ended up taking her out for coffee. I totally understand the reasoning behind this kind of censorship, but it made the LLM is so adverse to causing harm, it cannot effectively play a bad guy doing bad things to challenge you as the hero.<\/p>\n\n\n\n Takeaway<\/p>\n\n\n\n Final Question<\/p>\n\n\n\n I tested pacifist Azula against a group chat, and got them to fight normally, but the LLM I\u2019m using (kunoichi-dpo-v2-7b) gives {user} Mary Sue grade plot armor as elaborated above. Have you found a 7B model and configuration that works for interesting results?<\/p>\n\n\n\n I\u2019ve looked around for another LLM and read it\u2019s one of the better ones for the hardware I\u2019m using. I tested pacifist Azula against a few other cards in a group chat, and found that fights can happen, but it gives {user} plot armor to the point of being a Mary Sue. Have you found a LLM you like? I look forward to hearing from you in the comments below or on my Socials<\/a>!<\/p>\n","protected":false},"excerpt":{"rendered":" Good Morning from my Robotics Lab! This is Shadow_8472, and today I am going farther into the world of AI chat from the comfort of my own home. Let\u2019s get started! Last week, I got into Silly Tavern, a highly configurable AI chat playground with tons of features. Accomplishing a functional setup was rewarding on … <\/p>\n
AI is already powerful genie. The \u201cuncensored\u201d LLM\u2019s I have looked at draw their line at bomb and crack recipes, but sooner or later truly uncensored LLM\u2019s will pop up as consumer grade hardware grows powerful enough to train models from scratch. Or perhaps by then access to precursor datasets will be restricted and distribution of such models regulated. For now though, those with the power to let technologies like LLM\u2019s out of the AI bottle have chosen to do so slowly in the hopes we don’t destroy ourselves by the time we learn to respect and use them responsibly.<\/p>\n\n\n\n