The best analogy that I‘ve found for AI is that it’s like a calculator for reading and writing.
LLMS
-
LLMs Could Generate Future Religions Through Automation
By
–
Someone will openly use an LLM to generate a religious/C-anon text and it will become a dominant belief system for millennia with fighting, division, and death; we already know that consistency and rationality is not needed.L. Ron Hubbard, you've been automated!
-
Azure OpenAI Service Now Generally Available for Wider Access
By
–
Azure OpenAI Service is now generally available. Very nice milestone in making these models widely accessible:
-
Prompt Engineering Syntax Examples Show Promise
By
–
I've seen examples using this kind of syntax in various prompt engineering forums. Looks promising to me.
-
ChatGPT’s client-side prompt prep now behind API boundary
By
–
It's a good question, because at least initially ChatGPT incorporated client-side preparation of prompts as well. My guess would be that prep now happens behind the API boundary.
-
Multi-prompt Input Testing Not Yet Explored in Depth
By
–
Yeah, I haven't done a lot of multi-prompt input testing yet. Once I have a good reason to, I'm sure I'll get to the bottom of how to make it listen.
-
Internet’s Decline: LLM Output and Training Loop Crisis
By
–
The Internet’s twilight will come when it’s swamped with LLM output and new LLMs are trained on it.
-
LangChain Wolfram Alpha Integration Showcased in New Video
By
–
An awesome video by @JavaFXpert and @dralandthompson highlighting the LangChain Wolfram Alpha integration that @nickscamara_ did last week!
-
Using Caps and Repetition to Improve AI Instruction Following
By
–
We may need to be more forceful in the language telling it to wait. Use of ALL CAPS may work. Or repeating the instruction again at the end… "Remember, WAIT until I say Go! before taking any action." No time to test it right now, but you get the idea
-
AI Technology Limitations and Expected Improvements in 2023
By
–
That is a limitation of the AI tech right now. The best way around it right now is prompting it to continue. Annoying, I know. But as the technology evolves — probably this year even — the number on a lot of those limits may be raised.