Here is a conversation between me and LLama3:70b-instruct on Wikisimple Article “Artificial Intelligence”. Tyler: Please write me some deductive syllogisms from the following Wikisimple article: AI: Here are some deductive syllogisms based on the provided article: Syllogism 1 Syllogism 2 Syllogism 3 Syllogism 4 Syllogism 5 Tyler: Can you fallacy check your arguments?AI: Let’s go […]
List of Large Language Models on My Machines
The following are Language Models that I have been playing around with on my dev workstation. NAME Size codegemma:7b-instruct-fp16 17 GB codellama:34b 19 GB codellama:34b-instruct 19 GB command-r:35b 20 GB command-r-plus:104b 59 GB dolphin-mixtral:8x7b-v2.7-fp16 93 GB dolphin-mixtral:latest 26 GB llama2:13b 17 GB llama2-uncensored:70b-chat-q6_K 7.4 GB llama3:70b-instruct 56 GB llama3:8b-instruct-q8_0 39 GB llama3:latest 8.5 GB llava:34b […]
Folding Stage 2
Taking step 2 into folding today! Created a program that exports Wikia one article at a time and uses the new LLM Models to create deductive and inductive arguments for all my datasets. Worth mentioning I have the following datasets imported into MySQL.
If I Had $100,000 Family Server Builds
As you already know. I have created an application called _AugmentedIntelligence! Which is entirely a big data Emergent Build that is mean to calm people down about privacy and computers and technology in general. Current Small Scale Experiment At the time of this writing, we have a total of four servers and one NAS. The […]
_AugmentedIntelligence Development YouTube Stream
As you may or may not know, I am streaming my journey through the development of _AugmentedIntelligence and other AI programs I am working on. https://www.youtube.com/@tylercrockett5354/streams
Mutually Assured Destruction (MAD) LLM
The interviewees discuss the concept of “mutually assured destruction” (MAD) as a deterrent against nuclear war,but acknowledge its limitations and potential flaws. They argue that the idea of MAD is based on a flawed premise,as it assumes that both sides would be destroyed equally in the event of a nuclear conflict, which is unlikely tohappen. […]
Building a Powerful AI-Ready Server: Combining LLM, Whisper, and Linux
Introduction As AI technology continues to advance at a rapid pace, building a powerful server capable of handling demanding AIworkloads is becoming increasingly important. In this post, I’ll walk you through my journey of creating anartificial intelligence (LLM) and Whisper dedicated server using an old Windows 2016 license and Ubuntu. Thissetup will provide a robust […]
CodeLLama: Engineering Problem
Tyler: I am programming an application, it is an intelligene suite which I call _AugmentdIntelligence. The application should be GPU and CPU intensive. I am curious to ask if I should invest in clients on the spot or have most of the resource demanding tasks run on my server rack with a shared GPU? Codellama: […]
Meta.ai LLama3:8b-instruct Climate Change
Tyler: What is wrong with the following paragraph?: Many people argue that climate change is an urgent issue that needs immediate action. However, these arguments often come from scientists and researchers, many of whom live in urban areas and rarely experience nature firsthand. How can we trust their judgment about the environment when they spend […]
TranscriptionClient
I wrote a program inspired by my mom. The app records from the microphone, saves to a .wav, uploads it to one of my servers, then sends the transcription back to the client and displays it for the user.