Claude Sonnet 3.5 can now search the web with just 15 lines of Python code (step-by-step instructions):
CODE
-
Simplifying Complexity: Retaining Only What Matters
By
–
Totally agree, it's easy to move complexity around. It's harder to actually simplify yet retain only what's crucial.
-
Platform Refactoring for Enhanced Robustness and Maintainability
By
–
We’re in the process of refactoring to make it easier to update and more robist. Stay tuned!
-
Local Gemma: Playing with Open Source AI Model
By
–
I’ve played with this today, it is very cool `local-gemma`
-
alphaXiv enables direct PDF comments for arXiv papers
By
–
In response to popular demand, you can now comment directly on any arXiv PDF through http://
alphaXiv.org. Fewer rendering issues, while still enabling interactive discussion directly on the paper! -
RAG limitations: moving beyond data retrieval to pattern summarization
By
–
Also as some ppl pointed out, this is harder to get right so quality varies across solutions and none working perfectly yet.* People don’t want to just find specific pieces of data, but want summaries and patterns. This is more than basic RAG. *tell me if you find one!
-
Vector Embeddings and RAG Optimization Best Practices
By
–
Upserting data as vector embeddings is important when building a RAG application. There are many factors at play, such as chunk sizes, overlap, vector dimensions, etc. Shoutout to @toi500
, who has been helping to improve our docs and his recent work on the guides for upserting -
GPT-4o vs GPT-4 Turbo: Choosing the Right Model for Code
By
–
Depending on your code language btw, you might by want to still use GPT 4o or GPT 4 Turbo
-
Claude 3.5 Sonnet Tops SEAL Evals in Instruction Following Coding
By
–
We re-ran SEAL evals on the new @AnthropicAI Claude 3.5 Sonnet model. It is now:
– #1 on Instruction Following
– #1 on Coding Congratulations to Anthropic on a great new model! P.S. we’re adding new evals to SEAL, so if you have an idea for an eval, let us know below
