
Asad Sagheer
1.2K posts

Asad Sagheer
@thecode_envoy
Ideas → Experiments → Projects : Learn & Repeat • Building and learning along the way • Road to 1K • Open to paid gigs • If you code, Let's connect 🤜🤛


15. Model Alignment 16. RLHF (Reinforcement Learning from Human Feedback) 17. SFT (Supervised Fine-Tuning) 18. Prompt Injection

9. Agents / AI Agents (modern meaning) 10. Tool Use / Function Calling 11. Self-Hosted LLM 12. Model Distillation (became mainstream post-2020) 13. Mixture-of-Experts (MoE) (mainstreamed after Switch Transformer 2021) 14. Reasoning Model / Chain-of-Thought Model

9. Agents / AI Agents (modern meaning) 10. Tool Use / Function Calling 11. Self-Hosted LLM 12. Model Distillation (became mainstream post-2020) 13. Mixture-of-Experts (MoE) (mainstreamed after Switch Transformer 2021) 14. Reasoning Model / Chain-of-Thought Model

9. Agents / AI Agents (modern meaning) 10. Tool Use / Function Calling 11. Self-Hosted LLM 12. Model Distillation (became mainstream post-2020) 13. Mixture-of-Experts (MoE) (mainstreamed after Switch Transformer 2021) 14. Reasoning Model / Chain-of-Thought Model

9. Agents / AI Agents (modern meaning) 10. Tool Use / Function Calling 11. Self-Hosted LLM 12. Model Distillation (became mainstream post-2020) 13. Mixture-of-Experts (MoE) (mainstreamed after Switch Transformer 2021) 14. Reasoning Model / Chain-of-Thought Model

9. Agents / AI Agents (modern meaning) 10. Tool Use / Function Calling 11. Self-Hosted LLM 12. Model Distillation (became mainstream post-2020) 13. Mixture-of-Experts (MoE) (mainstreamed after Switch Transformer 2021) 14. Reasoning Model / Chain-of-Thought Model









