“The paper is on the arXiv” would be like “the code is on the GitHub”
CODE
-
Claude Instant v1.2 Powers Poe with Enhanced Reasoning
By
–
New: Claude-instant and Claude-instant-100k on Poe are now powered by @AnthropicAI
's Claude Instant v1.2. This model represents a substantial improvement over the previous iteration across multiple domains, particularly in reasoning and code. -
Hugging Face Tools for AI Model Prototyping and Deployment
By
–
Very cool! Let us know if you get to a good prototype. You can probably use https://
github.com/huggingface/hu
ggingface_hub
… to retrieve model & https://
huggingface.co/spaces to host/share the demo -
Google DeepMind AI Podcast: Generative Models for Developers
By
–
Watch the full AI Podcast with @dymanicwebpaige, Product Lead for Generative Models at Google DeepMind, in conversation with Replit’s @pirroh and @CeciliaZin
. Check out how devs can use tools like Bard + Replit to streamline your workflow. -
Free AI Workshop and Demonstration August 22
By
–
Join us for our workshop and demonstration and learn how to make AI that builds a real-world applied AI. FREE.
Aug 22, 9-11 am PST Seats are limited. RSVP here: -
LangSmith: Debugging, Testing, and Monitoring Tools for LangChain
By
–
Lots of fun stuff in LangSmith – debugging, testing, evaluation, monitoring And you can use it all even if you aren’t using LangChain! Great new guide
-
Data-Centric Prompt Engineering: Iterative Model Error Refinement
By
–
3/ We then began data-centric prompt engineering, iteratively identifying model error modes and addressing them in the prompt where possible, either with added detail in the prompt or adding in-context examples (~68 F1).
-
DistilBERT Fine-Tuning Achieves 84 F1 With Programmatic Labeling
By
–
4/ For maximum quality, we finished with fine-tuning, using Snorkel Flow to programmatically label data in areas where the model was still underperforming. Our best model (~84 F1) is fine-tuned DistilBERT, a model 10,000x smaller than GPT-4.
-
PyTorch Summary in One Slide Overview
By
–
I had a few minutes to quickly summarize PyTorch in one slide and this is roughly it.
-
Replit Launches Expandable Storage for Developer Projects
By
–
This is the first of many improvements towards a more powerful Replit. We can’t wait to see the expansion of ideas built with Expandable Storage. Be sure to tag us when you ship. For more read here. https://
blog.replit.com/expandable-sto
rage
…