I already addressed the complexity of OAuth client-side programming (version 1 and 2) in a previous post. In that post, I talk about how mybiketraffic uses OAuth to authenticate itself on behalf of its users as clients on the Garmin Connect website, which still uses OAuth v1.0, and the Strava website, which uses OAuth v2.0.… Continue reading OAuth 2.0 Server Side
Samford Family Academy Online Workshop
Had a great time presenting my overview of AI technology and its impacts. I got a bit too carried away with the technical details, so I didn’t quite make it to all the impacts AI is having on society. See the latter slides in the powerpoint below – Many thanks to all who joined in… Continue reading Samford Family Academy Online Workshop
More NUC fun
So my replacement Crucial TForce SSD on my NUC died after about a year and a half of use. Not detected any more internally. In an external enclosure, it is detected but then the formatting process causes a complete lock-up of the formatting program and never finishes. In any case, I bought a replacement for… Continue reading More NUC fun
Samford Homecoming Lecture: What in the world is happening in AI?
I gave a lecture today as part of the homecoming activities on the current impact of AI in both our world and in education. Going to write up more about it later, but it went well! Here are the powerpoint slides: And here is a link to the facebook live video: https://www.facebook.com/brian.toone/videos/1534532750722315 If the Facebook… Continue reading Samford Homecoming Lecture: What in the world is happening in AI?
5th generation programming language?
1st generation programming languages – MACHINE LANGUAGE In the beginning there was machine language – 1s and 0s only, sometimes entered by manually connecting cables into the right spot and setting the correct switches the right way (e.g., ENIAC). This is what is meant as a 1st generation programming language. 2nd gen languages – ASSEMBLY… Continue reading 5th generation programming language?
a tale of complexity
Let me tell you a tale – a tale of magic and power. Ok, maybe there isn’t any real magic to this other than the magic described by Arthur Clarke in this quote: “Any sufficiently advanced technology is indistinguishable from magic.” My reference to power is in the sense of what you as a third… Continue reading a tale of complexity
chatGPT code hallucinations
By this point, many people understand the concept of an AI “hallucination”. This is the term that has come to describe incorrect information stated as facts in the output of a chatGPT prompt. For example, if you ask “Who is Brian Toone?” to chatGPT, you get the response below which has some correct information, but… Continue reading chatGPT code hallucinations
Llama, Llama! (Red Pajama)
This was a fun book we used to read to our kids … but in other exciting news, Meta approved my research request for access to the LLaMA pre-trained large language model. 4/18 5:27pm. I started using the llama download script to download all the data, but the download.sh script doesn’t work by default on… Continue reading Llama, Llama! (Red Pajama)
Win11 officeGPT
Through my efforts to install the Stanford Alpaca system on my M1 mac studio that I dubbed homeGPT, I discovered that some of the required packages are configured to only use CUDA … in other words I need an NVIDIA graphics card. One of my research computers from school is a Windows 11 system with… Continue reading Win11 officeGPT
homeGPT, cont’d
Stanford Alpaca takes the LLaMA pre-trained model released by the Meta AI and “fine-tunes” the model to respond better to natural language questions and prompts (exactly what chatGPT does). Note, the screenshot above is from LLaMA, not from Alpaca. This shows you the value that alpaca adds as the output from the example LLaMA is… Continue reading homeGPT, cont’d