Custom Python loop, OpenAI for task generation, Langchain for task execution, Pinecone for storing learnings, running on Replit
CODE
-
Building Programming Languages with English Auto-Complete Features
By
–
Time to build new programming languages that have english auto-complete heavily built in
-
ChatGPT generates Python code with LangChain Pinecone integration
By
–
Not yet. Having ChatGPT write Python code by feeding it documentation from Langchain pinecone openai, etc
-
Plugin Architecture: Routing to Expert Services Instead of LLM
By
–
alors là ça sort de mon scope, mais comme ils sont en train de mettre en place des plugins, pour moi c'est comme ça que ca doit marcher, t'as un 1er niveau de désambiguisation et ensuite tu renvoies au service qui est le plus expert pour y répondre et pas forcement dans le LLM
-
Full-Stack Developer Expectations: Myth vs Reality
By
–
If you're looking for: – JavaScript, PHP, Python
– React, Vue, Svelte
– Node, Django, GraphQL
– Mongo, Firestore, RDS
– Kubernetes, Docker
– AWS, Google Cloud, Azure You're not looking for a full-stack dev, you're looking for an entire IT department. credit: @VittoStack -
Debugging ML Model Training: Shape Mismatch Resolution Success
By
–
About 4 hours and 30 minutes of intense debugging. Finally managed to make it work. Still gotta make considerable architectural changes, and make sure it *converges* But hey! at least it is training and not throwing shape mismatches anymore.
-
GPT-4 Hackathon Updates and Live Coverage
By
–
GPT-4 Hackathon Updates https://
x.com/i/broadcasts/1
zqKVPMDlemJB
… -
Databricks Dolly: Open Source LLM Training in 30 Minutes
By
–
Have 30 minutes to spare? That’s all you’ll need to train your own Dolly – an open source LLM – on Databricks and enjoy #ChatGPT-like capabilities. Check out our latest updates, including our GitHub repo, here https://
databricks.com/blog/2023/03/2
4/hello-dolly-democratizing-magic-chatgpt-open-models.html
… -
GPT-4 Report Lacks Reproducibility Documentation
By
–
While we're looking at source codes, I checked out the source of the GPT-4 Tech Report, and found neurips_checklist.tex (not compiled in their main.tex, I added it back in). Reproducibility answers are DEFINITELY not for this paper https://
arxiv.org/abs/2303.08774 -
No Code Tools: AI Development Without Typing
By
–
You like No Code? How about no typing at all? https://t.co/VmiWDxCURR
— Yohei (@yoheinakajima) 24 mars 2023You like No Code? How about no typing at all?