hstream
ChatDev
| hstream | ChatDev | |
|---|---|---|
| 1 | 10 | |
| 691 | 23,203 | |
| 0.7% | 10.5% | |
| 9.5 | 9.5 | |
| 2 days ago | 12 days ago | |
| Haskell | Shell | |
| BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hstream
ChatDev
-
AutoGen: Enable Next-Gen Large Language Model Applications
Check https://github.com/OpenBMB/ChatDev out, they simulate personas in a company and build products by simulating the interactions.
-
[task] Looking for someone with experience in chatgpt
Hey I have being playing with Chatdev for a long time now, and I am looking for customization on the company config file, I am pretty busy so I can't do that on my own time I have already customized for two tasks but I am looking to do that for more than one task. I can pay 5-20$ depending on the customization length and how much time it takes you to do so
-
I will pay you to customize ChatDev for me
Hey I have being playing with Chatdevfor a long time now,
-
AI hype is built on high test scores. Those tests are flawed
Exactly and things are actually getting crazy now. For some reason this hasn't reached the frontpage on HN yet: https://github.com/OpenBMB/ChatDev
Making your own "internal family system" of AI's is a making this exponential (and frightening), like an ensemble on top of the ensemble, with specific "mindsets", that with shared memory can build and do stuff continuously.
I remember a couple of comments here on HN when the hype began about how some dude had figured out how to actually make an AGI - can't find it now, but it was something about having multiple AIS, discoursing with a shared memory - and now it seems to be happening.
-
[D] Are there examples of AI-written projects actively maintained/worked on by humans?
I've seen a rising trend in these "ChatDev"-like projects (https://arxiv.org/abs/2307.07924, their github is https://github.com/OpenBMB/ChatDev) that can "assemble a team of AIs" to build a complete project, such as a snake game. The possible projects it can build are rather limited, and the "team" is really a chat dialogue. But it does in fact generate runnable code with some underlying system design philosophy.
- FLaNK Stack Weekly 2 October 2023
- Show HN: ChatDev – Simulating a software company with LLMs
- Communicative Agents for Software Development
-
FLaNK Stack Weekly for 12 September 2023
https://github.com/OpenBMB/ChatDev?
What are some alternatives?
hasqly-mysql - composable SQL generation for haskell
FLaNK-HuggingFace-BLOOM-LLM - https://huggingface.co/bigscience/bloom into NiFi
crdt
minum - A minimalist Java web framework built from scratch
haskelldb-connect-hdbc-catchio-mtl - Bracketed HDBC session for HaskellDB
LLM-Finetuning-Hub - Toolkit for fine-tuning, ablating and unit-testing open-source LLMs. [Moved to: https://github.com/georgian-io/LLM-Finetuning-Toolkit]
machine_learning_games - Set of games and simulations designed to experiment with QLearning, Neuroevolution, and PoseNet.
RecipeUI - Discover, test, and share APIs in seconds
FastMJPG - FastMJPG is a command line tool for capturing, sending, receiving, rendering, piping, and recording MJPG video with extremely low latency. It is optimized for running on constrained hardware and battery powered devices.
kafkaflow - Apache Kafka .NET Framework to create applications simple to use and extend.
Judy Graph DB - A graph database with cypher like queries using judy arrays
initializr - A quickstart generator for Spring projects