It seems as if Google is trying to fan the hype a little. Recently, the news circulated that Google would now have around 25% of its code written by AI. If the leak below is correct, Google would probably have exaggerated. It seems as if Google is trying to get out of the bad
CODE
-
Separating LLM Orchestration From Information Processing
By
–
I agree, we should separate out when the LLM is used for orchestrating and when it is used for processing information. The more the two are tied together, the harder is it to debug.
-
LangGraph and LangSmith ecosystem benefits for AI development
By
–
Completely agree – one of the benefits of using the LangGraph + LangSmith ecosystem
-
Anthropic Adds Tools Support in Workbench
By
–
Anthropic is working on Tools support in Workbench. Function calling was available in the API but missing in the console.
— 🚨 AI News | TestingCatalog (@testingcatalog) 2 novembre 2024
Some other things that:
– Feedback on model responses
– Admin API Keys pic.twitter.com/Zbm68Hxc0lAnthropic is working on Tools support in Workbench. Function calling was available in the API but missing in the console. Some other things that:
– Feedback on model responses
– Admin API Keys -
Databricks Launches New SQL Editor with AI Integration
By
–
Meet the new SQL editor: streamlined & unified UI for exploratory data analysis & engineering. Key features: multiple statement results, real-time collaboration, enhanced Databricks Assistant integrations, & productivity enhancements. Now in public preview https://t.co/kOoytWl8j9 pic.twitter.com/aWGHvb0dPU
— Databricks (@databricks) 2 novembre 2024Meet the new SQL editor: streamlined & unified UI for exploratory data analysis & engineering. Key features: multiple statement results, real-time collaboration, enhanced Databricks Assistant integrations, & productivity enhancements. Now in public preview https://
dbricks.co/48urOED -
Building Gamified Hex Code Applications with AI Agents
By
–
Building with Agent: Gamifying Hex Codes https://
x.com/i/broadcasts/1
BRJjwylVyVxw
… -
Bonus Material Added: GPT to Llama 3.2 Model Conversion
By
–
Thanks for the kind words, and I am glad you got lots out of it! Btw in case you feel bored, I added a bunch of bonus material to the GitHub repo recently. For example the conversion to a Llama 3.2 model: https://
github.com/rasbt/LLMs-fro
m-scratch/tree/main/ch05/07_gpt_to_llama
… -
CPU and GPU Compatibility: Code Automatically Adapts to Available Hardware
By
–
Interesting question. Not sure this is possible. However, this also shouldn't be necessary for the book. The code works on both CPU and GPU machines (the code is written that it automatically uses a compatible GPU if available)
-
O1 File Upload and Full Access Confirmed by Multiple Sources
By
–
This has now been confirmed by numerous sources:
– file upload for o1 – access to full o1 LFG!