Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
awesome-chatgpt
🤖 Awesome list for ChatGPT — an artificial intelligence chatbot developed by OpenAI (by sindresorhus)
-
promptr
Promptr is a CLI tool that lets you use plain English to instruct GPT3 or GPT4 to make changes to your codebase.
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
download-simulator-2023
Remake of my game Download Simulator 2013 https://github.com/mobyvb/ludum-dare-27
Phind is a GPT powered search engine optimized for developers / technical documentation. It searches the web and tries to aggregate results from multiple web sites. Although there are instances where it references outdated versions of libraries, on balance, it significantly reduced my time spent on technical research.
https://www.phind.com/
There are so many useful tools, that I keep an Awesome list up to date with openAI API, as well as open LLM tools. Especially the up to date list of open LLM models might be of interest to some, in case someone wants to be independent of OpenAI:
https://github.com/underlines/awesome-marketing-datascience/...
Sindre Sorhus released this list:
https://github.com/sindresorhus/awesome-chatgpt
For GPT/Copilot style help for pandas, in notebooks REPL flow (without needing to install plugins), I built sketch. I genuinely use it every-time I'm working on pandas dataframes for a quick one-off analysis. Just makes the iteration loop so much faster. (Specifically the `.sketch.howto`, anecdotally I actually don't use `.sketch.ask` anymore)
https://github.com/approximatelabs/sketch
We are building a programming language (https://lmql.ai), that allows you to execute programs with control-flow and constrained behavior on top of LLMs. Essentially imperative LLM text generation.
Ones that actually save me a lot of time I would otherwise spend googling:
plz-cli, a terminal copilot, https://github.com/m1guelpf/plz-cli
Code GPT, a Visual Studio Code copilot, https://marketplace.visualstudio.com/items?itemName=DanielSa...
Promptr is a coding assistant tool that allows you to ask GPT to produce or modify code, and the results will be automatically applied to your file system.
https://github.com/ferrislucas/promptr
From the README:
- Talking and eye tracking using assistive technology: https://twitter.com/localghost/status/1655665066803617792
I prefer multi-modality over keyboard/text-only input due to my slow typing speed and tendency to overthink and rewrite excessively. So I will use these apps as my default interface to GPT.
2. (Japanese only) ChatVRM: GPT with 3D avatar
https://github.com/pixiv/ChatVRM
Although it may not be suitable for everyone, this is my favorite and I use a fork version of it on a daily basis.
Just a JSON blob in firebase. I am looking into making an electron app, so the data stays local:
https://github.com/egonSchiele/chisel/tree/adit/electron
- Drafting an action plan and coming up with open questions based on specific requirements (issue: https://github.com/mobyvb/download-simulator-2023/issues/1, PR created by bot: https://github.com/mobyvb/download-simulator-2023/pull/2/fil...)
- Writing an Arduino script from scratch based on specific requirements (issue: https://github.com/mobyvb/midi-looper/issues/1, PR: https://github.com/mobyvb/midi-looper/pull/2/files)
Still lots of improvement to go but I'm having a lot of fun.
Exposition if you want:
Some ideas (I may experiment with these on my own fork, and make a PR if I have success):
1. The main prompt is pretty long (https://github.com/paul-gauthier/aider/blob/main/aider/promp...), but I suspect that it could be abbreviated. I'm think the same criteria/restrictions could be enforced with fewer characters, enabling (slightly) larger files to be supported
E.g. "I want you to act as an expert software engineer and pair programmer." (69 chars) -> "Act as a software dev + pair programmer" (39 chars) - I suspect the LLM would behave similarly with these two phrases
2. It would be cool to be able to open "file sections" rather than entire files (still trying to figure out how to do this for my own tool). But the idea I had would be to support opening files like `path/to/main.go[123:200]` or `/path/to/main.go[func:FuncName]`
^the way I've gotten around this limitation with your tool is by copying functions/structures relevant to my request into a temporary file, then opening aider on the temporary file and making my request. Then I copy/paste the code generated to the actual file I want it in. It did a really good job, I'm just trying to figure out ways to reduce the number of manual steps for that
Anyway, great job, and I'm really excited to keep using this tool.
Related posts
-
chatgpt-infinity alternatives - chatgpt-auto-refresh and chatgpt-auto-continue
3 projects | 5 Jul 2023
- Implementations of REMO and other memory systems
- Build a serverless ChatGPT with RAG using LangChain.js
- Day 5— Azure Open AI Challenge: Document Intelligence
- Open AI Challenge, Day 3: Mastering Code Generation