Lesson learned from my “hybrid AI” workflow experiment: more agents ≠ better work.
DeepSeek absolutely butchered this animatic 😂 Too many handoffs turned creative direction into boxes, diagrams and technical checklists instead of storytelling. Going back to what worked: Luna
DeepSeek V4.1 Flash vs GPT-6 Astra [Arranged with the same theme]
Flash on the left, Astra on the right. ・Astra is exceptional in terms of construction. - However, if you do the same thing with Astra, the cost will be many times more. ・Look at how far you can be delegated rather than “can you win?”
The AI Large Model Intellectual Disability Competition is here😑 The contestants this time: - gpt-6-luna
Gpt-5.6-luna -grok-4.6 - deepseek-v4-pro - kimi-k3 -gemini-3.1-pro The following are all based on the highest thinking level test of this model. Choose the one you think is the most retarded! !
The installation package of the DeepSeek Harness desktop version was picked up by netizens 🤣 The…
The installation package of the DeepSeek Harness desktop version was picked up by netizens 🤣 The official announcement has not yet been made, and many people have already taken advantage of it (including me).
You have reached the end of the archive
All of deepseek