Code generation, programming assistants

Github copilot
Codeium
Amazon CodeWhisperer
Incoming
References

A cousin to neural automata: writing machines to code for us. We might also want to write code to speak for us, which ends up involving similar technology, i.e. large language models.

I am vaguely concerned about how much of the world is uploading their source code for everything to these code servers. The potential for abuse is huge.

Github copilot

GitHub Copilot uses suggestions from OpenAI Codex to suggest code completion.

Pro tip. behind a firewall, requires at least the following whitelist exceptions:

vscode-auth.github.com
api.github.com
copilot-proxy.githubusercontent.com

See Networked VS Code for some more whitelest rules we need for VS Code generally.

Codeium

Codeium has been developed by the team at Exafunction to build on the industry-wide momentum on foundational models. We realized that the combination of recent advances in generative models and our world-class optimized deep learning serving software could provide users with top quality AI-based products at the lowest possible costs (or ideally, free!).

Amazon CodeWhisperer

AI Code Generator - Amazon CodeWhisperer - AWS

Available as part of the AWS Toolkit for Visual Studio (VS) Code and JetBrains, CodeWhisperer currently supports Python, Java, JavaScript, TypeScript, C#, Go, Rust, PHP, Ruby, Kotlin, C, C++, Shell scripting, SQL and Scala. In addition to VS Code and the JetBrains family of IDEs—including IntelliJ, PyCharm, GoLand, CLion, PhpStorm, RubyMine, Rider, WebStorm, and DataGrip—CodeWhisperer is also available for AWS Cloud9, AWS Lambda console, JupyterLab and Amazon SageMaker Studio.

Free for individual use.

Incoming

AI self-play for algorithm design
Software²: A new generation of AIs that become increasingly general by producing their own training data
openai/openai-cookbook: Examples and guides for using the OpenAI API
LMQL: Programming Large Language Models: “LMQL is a programming language for language model interaction.”
LMQL generalizes natural language prompting, making it more expressive while remaining accessible. For this, LMQL builds on top of Python, allowing users to express natural language prompts that also contain code. The resulting queries can be directly executed on language models like OpenAI's GPT models Fixed answer templates and intermediate instructions allow the user to steer the LLM's reasoning process.
This is how you code now
AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code
Using GPT-3 to explain how code works
A Datasette tutorial written by GPT-3
Mitchell Hashimoto on the mysterious ease of ChatGPT plugins

Querying Glean:

Glean is a system for working with facts about source code. It is designed for collecting and storing detailed information about code structure, and providing access to the data to power tools and experiences from online IDE features to offline code analysis.
For example, Glean could answer all the questions you’d expect your IDE to answer, accurately and efficiently on a large-scale codebase. Things like:
Where is the definition of this method?
Where are all the callers of this function?
Who inherits from this class?
What are all the declarations in this file?

References

Beurer-Kellner, Luca, Marc Fischer, and Martin Vechev. 2022. “Prompting Is Programming: A Query Language For Large Language Models.” arXiv.

Bubeck, Sébastien, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, et al. 2023. “Sparks of Artificial General Intelligence: Early Experiments with GPT-4.” arXiv.

Din, Alexander Yom, Taelin Karidi, Leshem Choshen, and Mor Geva. 2023. “Jump to Conclusions: Short-Cutting Transformers With Linear Transformations.”

Suzgun, Mirac, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, et al. 2022. “Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.” arXiv.

Wang, Xuezhi, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. “Self-Consistency Improves Chain of Thought Reasoning in Language Models.” arXiv.