from the Stack Overflow annual survey https://
survey.stackoverflow.co/2022
CODE
-
Stack Overflow 2022 Annual Survey: Developer Insights
By
–
-
Stack Overflow 2022 Developer Survey Annual Report
By
–
from the @StackOverflow annual developer survey of 2022! https://
survey.stackoverflow.co/2022/ -
Reverse-engineering GitHub Copilot: brilliant notes by @parth007_96
By
–
See @parth007_96
’s brilliant notes on reverse-engineering GitHub Copilot here: https://
thakkarparth007.github.io/copilot-explor
er/posts/copilot-internals
… -
GitHub Copilot’s implicit prompt engineering creates a competitive moat
By
–
When you hit tab in GitHub Copilot, you’re FITM-completing a prompt of your file with an implicit comment header added, and it takes pages to describe what might be in that header. That’s prompt engineering. That’s a moat.
-
GPT-3/LLM prompts as assembly code, need prompt compilers
By
–
I increasingly see GPT‑3/LLM prompts as assembly code, not as human interface. We shouldn’t be writing prompts, but prompt compilers. A template string is not a moat.
-
Top 5 In-Demand Tech Skills for Jobs in 2023
By
–
The Top 5 In-Demand #Tech Skills For #Jobs In 2023 The #job market is shifting all the time and every-faster #digitisation means the skills companies will require are changing. Here we look at the top in-demand #skills for #2022. https://
linkedin.com/pulse/top-5-in
-demand-tech-skills-jobs-2023-bernard-marr
… -
Code Capture as Foundation for RLHF Self-Bootstrapping
By
–
“capture code” could be a very cool basis for RLHF/retraining. this thing is bootstrapping itself!
-
Debug Mode for Copilot: Expose Scores, Latencies, and Prompts
By
–
idea for extension: offer a “debug mode” modified version of copilot with all these scores and latencies and prompts exposed, so that people can gain an intuition of whats coming in and out as they type
-
MLflow 2.0 Released with Enhanced MLOps Features
By
–
Availability of #MLflow 2.0 is here Incorporating extensive user feedback, MLflow 2.0 introduces new features & improvements to simplify data science workflows & deliver innovative, first-class tools for MLOps. Learn more https://
dbricks.co/3tAv3qy -
Optimizing ChatGPT++ with Reinforcement Learning for Better Parameters
By
–
yes having no heat cycle is such a big deal chatgpt++ can probably help some, but i suspect RL for optimizing the input parameters can help a lot!