Ask ChatGPT to suggest innovative angles or perspectives.
Prompt: "Generate unique angles or strategies for the topic 'How to increase your creative output.' Emphasize innovative ideas."
4. Simulate an expert.
You can get ChatGPT to become an expert in a given subject.
Then, you can engage in conversation or request it to produce content from the perspective of that specific character.
In this example, I turned ChatGPT into a Harvard Marketing graduate:
Prompt: "As a Harvard Marketing graduate and skilled content creator, guide me in crafting social media content that resonates with AI enthusiasts. Emphasize uncommon and expert questions to ask"
5. Train ChatGPT on your email writing style, and respond to emails in your tone.
Super easy to do- yet I still get a ton of questions on how to do it.
Prompt: “Create a table for top AI tools. Include the following columns: Name, Category, and Oneliner. Here are the Tools that I want to summarize: [tools]”
That's a wrap! One last thing- I spent all day curating this, and I need your help.
Please honor the gentlemen's agreement because I will STARVE without engagement dopamine:
1. Follow me @rowancheung for more 2. Like + Retweet the tweet below👇
TODAY'S AI NEWS: Google just dropped Gemini 2.5 Pro, its most intelligent AI model to date.
Plus, more news from OpenAI, Figure, ByteDance, Otter, and Perplexity.
Here's everything you need to know:
Google released Gemini 2.5 Pro Experimental, the first model in its Gemini 2.5 family
—#1 on the LMArena
—SOTA capabilities across benchmarks for coding, math, science, and more
—Visual reasoning
—1M token context window (2M coming soon!)
OpenAI added native image generation within GPT-4o and Sora
—A fully integrated system for creating visuals via ChatGPT
—Excels at menus, diagrams, and infographics
—Edits images with text prompts
—Rolling out to Plus, Pro, Team, and Free users
Tencent released Hunyuan T1, a reasoning AI based on industry's first Transformer-Mamba architecture
—Matches or surpasses DeepSeek R1 and OpenAI’s o1 and GPT 4.5
—2x faster with reduced compute demands
—Priced at $0.14 and $0.55 per million I/O tokens
TODAY'S AI NEWS: Roblox just made 3D content creation as simple as a text command!
Plus, more news from Mistral, xAI, Zoom, Tencent, Perplexity, Baidu, and more.
Here's everything you need to know:
Roblox announced Cube 3D, an open-source AI for generating 3D objects and scenes from text prompts
Trained on native 3D data, Cube uses 3D tokenization to create functional 3D outputs in seconds
Support for image inputs is also on the way!
Mistral AI released Small 3.1, a SOTA multilingual and multimodal LLM
—24B (can run on a laptop)
—128k token context window
—Outperforms Gemma 3 and GPT-4o Mini on most benchmarks
—Inference speed of 150 tokens/sec
—Open-source under Apache 2.0 license