Take a bunch of pictures with different expressions and use those as reference. Have the AI model generate everything but the facial expressions.
@mreflow
-
Fable excellent for coding but often seen as a cloner
By
–
Fable is actually really excellent for coding projects and games. However, most of what I've seen boils down to 'look, Fable has cloned [insert tool or game here]'. Even all my tests have been more or less that, basically. I think this only proves
-
Fable outpaces ChatGPT’s prompt suggestions
By
–
It's funny – I asked ChatGPT for some prompts to test out with Fable and all the prompts were too easy. It didn't suggest anything that 5.5 or 4.8 couldn't already do. Like ChatGPT couldn't comprehend problems hard enough for Fable.
-
Gemini Omni Usage Examples and Video
By
–
Saw someone sharing this video without crediting the creator so giving some love to the original. Awesome examples of using Gemini Omni. https://t.co/rWoVniA6LG
— Matt Wolfe (@mreflow) 27 mai 2026Saw someone sharing this video without crediting the creator so giving some love to the original. Awesome examples of using Gemini Omni.
-
Weekly AI news roundup: New models, agents, and enterprise tools
By
–
Here's all the AI news from the past week: – @thinkymachines unveiled “Interaction Models”
– @OpenAI launched Codex From Anywhere – @AnthropicAI launched Agent View in Claude Code and increased usage limits
– Anthropic also launched Claude for Legal and Claude for Small -
AI capability to analyze environmental source code
By
–
I like this comparison but… cars can’t open up and read the source code of their environment… AI can.
-
Promoting “Python Illustrated” for fun and effective coding skill building
By
–
So not just an iOS issue? Interesting.
-
Packt Publishing AI Agents Live Training Session Announcement
By
–
Great breakdown. I’m loving Codex the most lately but the lack of Codex mobile app has been a real bummer. They nail that and it’s literally got everything I need.
-
Influential Books on Nudge Theory and Behavioral Science by Cialdini and Thaler
By
–
Sharing this so that hopefully it gets pushed to more people, shared further, the right people at Apple see it, and it gets fixed once and for all. Typing on iPhones is so annoying these days!
-
Hands-On Simulation Modeling with Python Book Announcement
By
–
I’m with you. A 12-million token context with 1,000x less compute seems too good to be true out of nowhere. Seems like something big labs would throw billions at to get access to.