Yeah, the code is open source. Maybe add some credits. 🙂
@skirano
-
Downloading Anthropic Cookbook with Gemini 1.5 Pro API
By
–
Here's an example of downloading the entire Anthropic Cookbook, a whopping 885,958 tokens, and Gemini 1.5 Pro in one shot, returning relevant code using the APIs. Before I added the super prompt to the output.
-
RepoToTextForLLMs: Convert GitHub repos to text for LLMs
By
–
In the era of long-context LLMs, I needed a way to quickly convert a GitHub repo into a text file to feed as a prompt.
— Pietro Schirano (@skirano) 11 mars 2024
Introducing RepoToTextForLLMs 📖
Not only does it return the full repo in one file, but it also appends a super prompt for analysis and understanding 👇 pic.twitter.com/WovzRUpzLeIn the era of long-context LLMs, I needed a way to quickly convert a GitHub repo into a text file to feed as a prompt. Introducing RepoToTextForLLMs Not only does it return the full repo in one file, but it also appends a super prompt for analysis and understanding
-
Model comparison coding capabilities and context analysis
By
–
To me, it's mostly about how much better it is at coding, so of course, given that's what I care about the most, I am a little biased. But overall, it can just do things better than GPT-4, like analysis over large contexts, etc.
-
AI Tools Democratizing Creative Design Beyond Photoshop
By
–
Another step into our vision of making photoshop-like tools unnecessary, unlocking full creative control for all, in your own style and brand!
-
Replace Anything AI Tool Enables Style-Based Image Editing
By
–
Introducing Replace Anything on @everartai ! 🪄
— Pietro Schirano (@skirano) 8 mars 2024
You can now edit any image in your own style just by using words!
I am truly addicted to this feature! pic.twitter.com/Hnr1RTlxf8Introducing Replace Anything on @everartai ! You can now edit any image in your own style just by using words! I am truly addicted to this feature!
-
GPT-4 Benchmark Bias: Circular Evaluation Problem
By
–
I could not agree more, to the point that I have lost trust in most of these benchmarks. Plus, if GPT-4 is used to run the evals, isn't that an inherent bias of the system?
-
Smart AI System Demonstrates Intelligence and Refined Taste
By
–
Not only is it smart, but it also has taste!
-
Was Claude’s AI Protagonist Named After Prometheus Code
By
–
This is actually super interesting because last night I was co-writing a short story with Claude and insisted on calling the protagonist, a sentient AI, Prometheus. I wonder if that was its code name.
-
Claude 3 Outperforms GPT-4 in User Experience
By
–
Interesting results! For me, Claude 3 is so much better than GPT-4, to the point where I stopped using GPT