I’m done with ChatGPT for a while. It’s sucked the joy out of prompt writing for me. Default writing quality is easy to achieve but hard to improve; opaque front-end and high temperature prevent the sort of casual analysis and experimentation that made fall in love with GPT-3.
TOOLS
-

AI Skills Gap: Data Analytics Tools and Talent Recruitment Strategy
By
–
Mind #AI #Skills Gap! New #research https://
bit.ly/AIUKResearch @SASsoftware 1) Consolidate #data & #Analytics tools
2) Invest in #culture #networks
3) Widen outreach for #DataScience talent! #SAS @SASsoftwareUKI #womenintech @Shi4Tech #ML #HR @baski_LA @mikeflache @DrKeil #IoT -
Running Stable Diffusion on Vultr VPS with Multiple GPUs
By
–
Can I use Stable Diffusion for ex on a Vultr VPS with multiple GPUs? Or do I then need to have multiple VPS instances with 1 GPU per VPS? I prefer to just do one VPS w/ multiple GPUs cause I'm used to running a VPS thx
-

From Inaccessible to Mainstream: AI Models Now Available to Everyone
By
–
How it started vs How it's going I knew how to recognize exponentials in 2018, but also didn't believe that this was accessible to the median technologist. That is the biggest thing changing with @StabilityAI
; today, hobbyists can run these things on iPhones and CPUs -
API Limitations Restricting Image Generation Dimensions
By
–
API is limiting tech too, eg I want to gen diff dimensions like 512×1024 and it ain't happening
-
Learning AI fundamentals through Replicate platform
By
–
Replicate is super cheap yes, but good for me to figure out how this stuff works in the core
-

Debugging Micromamba Issues: Developer’s Technical Challenge
By
–
already stuck due to some micromamba shit, but let's drink 3rd coffee and figure this out
-
LangChain v0.0.35 Release: Documentation Improvements and New Features
By
–
LangChain v0.0.35 Doc improvements @HunterGerlach Fix typing of parameters, flagged by @fcampeot
Expose more parameters for the q&a chains, suggest by @johnjnay Add a `.clear()` method for memory, @shobith and @andrewgleave Support -1 for max_tokens, @BruceHammer