Post Content
OpenAI released GPT-4.1 family of models. In this video we are going to have a look at everything they said and they didn’t say.
LINK:
https://openai.com/index/gpt-4-1/
https://mmmu-benchmark.github.io/#leaderboardking
https://huggingface.co/spaces/Krisseck/IFEval-Leaderboard
https://huggingface.co/datasets/openai/mrcr
https://aider.chat/docs/leaderboards/
https://scale.com/leaderboard/multichallenge
https://video-mme.github.io/home_page.html
https://www.swebench.com/#verified
https://platform.openai.com/docs/pricing
RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag
Let’s Connect:
Discord: https://discord.com/invite/t4eYQRUcXB
Buy me a Coffee: https://ko-fi.com/promptengineering
|
Patreon: https://www.patreon.com/PromptEngineering
Consulting: https://calendly.com/engineerprompt/consulting-call
Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
Unveiling GPT-4 0.1: What’s New with OpenAI’s Latest Release?
OpenAI has released GPT-4 0.1 in the API, an enhanced model for coding and instruction following with an unprecedented 1 million token context window. The video dives into the features of the three new models—GPT-4.1, 4.1 mini, and 4.1 nano—and compares them with previous OpenAI models and other providers like Gemini and Cloud. Although it comes with significant improvements, the model’s knowledge cutoff remains at June 2024. The video also examines various benchmarks, including SWE and polyglot coding benchmarks, and discusses the potential applications for developers. Key comparisons are also made to multimodal capabilities and pricing considerations. The episode provides insights into long context retrieval reliability and positions these models within the broader AI landscape.
00:00 Introduction to GPT-4 0.1 Release
00:27 Model Variants and Naming Issues
01:14 Benchmarks and Comparisons
03:44 Performance in Coding Tasks
07:46 Instruction Following Improvements
09:57 Long Context Retrieval
14:30 Multimodal Capabilities
15:45 Pricing and Final Thoughts Read More Prompt Engineering
#AI #promptengineering
