Happy to help spread some advanced techniques with AI, Alex.
AI
-
Email sequences adapted from tweet thread prompts
By
–
Sweet, Joe. I think email has a lot to gain from these techniques. Someone in my course even adapted one of my prompts to write email sequences instead of tweet thread ideas. Very cool stuff.
-
AI Tools: Potential for Time Loss and Valuable Lessons Learned
By
–
There is huge potential to lose yourself in this. And I've burned hundreds of hours experimenting with ChatGPT, and hundreds more making images with the various art AI tools. Hopefully my loss can at least be someone else's gain.
-
AI Course: No Coverage on Proprietary Data Protection
By
–
Protecting your proprietary data when using the AI isn't something I cover in the course. I give away all my best prompts inside, and many others in the course community are already sharing their work as well. For advice on this specifically, you may need to look elsewhere
-
GPT capabilities vary by topic, expected improvements ahead
By
–
For some topics, it seems to have more knowledge. Others, you sometimes have a harder time getting it to act more uniquely. But I do agree, it should get better over time. If OpenAi's GPT-3 is any indication, it'll see huge upgrades multiple times a year.
-
Testing GraphViz Reformatting Outside AI Training Data
By
–
(*SPOILERS for Glass Onion – I needed a movie that was outside the training window*) @elzr pointed out Riley's GraphViz experiments (
https://
x.com/goodside/statu
s/1561549768987496449?s=20
…) as a reformatting, and I wanted to doublecheck it doesn't only regurgitate from things it knows (for useful generality) -
AI Output Eloquence vs. Reasoning: The ‘Nonsense Conclusion’ Effect
By
–
Agreed — but it's also somewhat independent. E.g., think of ChatGPT outputs that eloquently reach a nonsense conclusion by confidently asserting things that don't follow. There's a "Hey, wait a minute…" effect when style exceeds reasoning.
-
Three Tech Predictions: Transformers, ROS2, and Indoor Farming
By
–
“I never make predictions. I never have and I never will.” Tony Blair(?). Me neither, except: Transformers, ROS2, and Indoor Farming.
-
Stanford Buffalo Universities Advance Language Modeling State Space Models
By
–
Stanford & Buffalo U Advance Language Modelling with State Space Models https://
syncedreview.com/2023/01/03/sta
nford-buffalo-u-advance-language-modelling-with-state-space-models/
… -
AI Dungeon’s Role in the Birth of LLM Prompt Engineering
By
–
LLM prompt engineering was born in academia, but AI Dungeon was its cradle. Many people, including me, used GPT-3 for the first time via this game. Many useful prompting techniques were discovered by players who abused it for independent, informal research.