Developers, we’re previewing Reinforcement Fine-Tuning (RFT) for @OpenAI o1! With just a handful of examples, you can guide o1 to tackle complex, domain-specific tasks, and it works incredibly well. Rolling out early 2025—apply now for early access: https://
openai.com/form/rft-resea
rch-program/
…
CODE
-
OpenAI Previews Reinforcement Fine-Tuning for o1 Model
By
–
-
Sam Altman Announces New Fine-Tuning Tool for AI Models
By
–
On the second day of Shipmas Sam Altman gave to thee
A new tool for fine-tuning -
Developers can fine-tune o1 for custom LLMs
By
–
Fine-tuning will be possible for o1. Devs will be able to build o1 level custom use LLMs
-
Prompt asking ChatGPT to compute expression based on vowel count
By
–
ChatGPT o1 computes (x – 14)^10 where x is the number of vowels in the answer
-
Model Context Protocol Revolutionizes LLM Integration
By
–
Introducing the Model Context Protocol https://
bit.ly/3Bol7ro
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Zhen Li Creates Replit’s AI Agent Innovation
By
–
Meet Zhen Li, creator of Replit's AI Agent—hear how it all began! 🪄 🧑🏻💻 pic.twitter.com/t1uR7c5d67
— Replit ⠕ (@Replit) 6 décembre 2024Meet Zhen Li, creator of Replit's AI Agent—hear how it all began!
-
No-Code AI Workflow Automation: From Repetition to Custom GPTs
By
–
GOATed no-code AI workflow: http://
1.Do the task multiple times.
2.Realize it’s repetitive.
3.Copy all previous input/output.
4.Dictate SOP + add examples from 3.
5.Create GPT/Project with 4.
6.Dictate new input (2-20 min).
7.Hit enter.
8.Dictate edits (1-4 min).