Mix of both. I've had quite a few ChatGPT outputs that were good to go on the first try.
LLMS
-
Training Your Own AI Model Without ChatGPT
By
–
That's a whole different ball game. If you want the same model, then I would train my own (not on ChatGPT).
-
Blueprint to Cut LLM Costs by 88 Percent
By
–
Our blueprint to cut LLM costs by 88%: https://
decodingml.substack.com/p/our-blueprin
t-to-cut-llm-costs-by
… The advanced RAG course (use code paul_15 for 15% off): -
Fine-tuned GPT-4o Mini cuts costs by 88 percent monthly
By
–
This fine-tuned GPT-4o Mini runs at just ~$180/month—saving us $1,320 monthly- and has comparable results to the original model. Want to dive deeper? Rerad the full article and check out the “From Beginner to Advanced LLM Developer Course” with 50+ hours of content—and grab a
-
Cost-Effective Fine-Tuning of GPT-4o Mini Models
By
–
2. Fine-Tuning a Cost-Effective Model: Instead of deploying a full-scale GPT-4o (costing ~$1,500/month handling 10k queries monthly), we fine-tuned a smaller, more efficient GPT-4o Mini. By using OpenAI’s managed fine-tuning on a curated dataset of 100 Q&A pairs (with 30 for
-
Fine-tuned GPT-4o Mini cuts costs by 88%
By
–
This fine-tuned GPT-4o Mini runs at just ~$180/month—saving us $1,320 monthly- and has comparable results to the original model. Want to dive deeper? Rerad the full article and check out the “From Beginner to Advanced LLM Developer Course” with 50+ hours of content—and grab a
-
Natural Language Simplifies Complex Data Transformation Workflows
By
–
transpose anything to anything is nothing new, but the fact that 3 days ago it took complicated workflows, and now it’s a single line of natural language.
-
Apple Invests $1B in Nvidia Servers for In-House GenAI
By
–
Apple entre dans la course aux datacenters 1 milliard de dollars investis dans les serveurs Nvidia NVL72. Partenariats avec Dell et Supermicro pour bâtir un cluster GenAI maison et un futur LLM ? Pas encore de modèle maison, mais la base est posée. Siri est largué, Apple
-
Google Launches Gemini 2.5 Pro with Advanced Reasoning Capabilities
By
–
Google passe à la vitesse supérieure avec Gemini 2.5 Pro.
Le modèle domine les benchmarks sur le raisonnement, les maths, la science et le code. Son architecture intègre un contexte long, une meilleure capacité à structurer les réponses, et une finesse dans les tâches