Gen AI Video Creative Director & Founder, prev at Sony Pictures and Netflix. Co-host of 5ives podcast. CPP: Hailuo Minimax, OpenArt, Luma, Dreamina, Vidu
Los Angeles, CA
- Tweets 42,090
- Following 5,734
- Followers 14,177
- Likes 9,232
Pinned Tweet
FULL VIDEO: I edited together close to 120 ChatGPT images into video clips made in
@Hailuo_AI
image-to-video to match the Dune trailer frame-by-frame in the style of Moebius
16
6
111
12,712
Give AI your email... what's the worse that could happen?
AI: I've solved everyone's Inbox Zero problem!
1
291
I put Qwen Image 2.1 through its paces. It's not replacing Krea 2 or GPT Image 2.5, but it definitely has its place as an image edit model.
piped.video/watch?v=JA-ThIY5โฆ
2
1
4
738
Had a character reference sheet, popped it into @Hailuo_AI MiniMax H3 and got a 1980s style toy commercial, with a live action toy version.
2
1
5
480
๐๐๐ ๐ค+๐ง retweeted
Friends collect crypto.
Friends want to spend it.
$40,000 worth of prizes.
Vibeathon - build anything, make friends.
55
54
249
47,628
Did someone say chimera research?
An extraordinary @Nature paper has just landed from the lab of @Sergiu_P_Pasca at @Stanford - led by Konstantin Kaganovsky. They have found a way to create "xenocortical mice" which have ~92% of their cortex occupied by a cortical organoid derived from human stem cells. This human-derived cortical graft integrates deeply with the host nervous system, supporting organised neural activity and behaviour.
This study is a milestone in synthetic biology and chimera research. It has the potential to generate multiple medical breakthroughs by providing an enhanced biological model of human brain tissue that allows behavioural as well as neural and genetic assays.
The Stanford team have been exceptionally thorough and proactive in addressing ethical concerns that comes from this frontier work. But their pioneering work nonetheless raises many open questions: are the xenocortical mice conscious? Do they have any human-like properties of consciousness or cognition?
@NitaFarahany and I will be addressing some of these questions in a forthcoming commentary - where we'll also offer an ethically-informed roadmap to guide this important research as it progresses. In this context, "pacing the frontier" really does make sense ๐
Read the Stanford @nature paper here, and buckle up. It's wild. nature.com/articles/s41586-0โฆ
3
4
443
Story concept & art direction I've been playing around with. Video and music using local AI models MiniMax H3 and YuE2.
Trying to get away from the typical anime-derived look of AI animation.
2
2
8
598
I tend to think @Plinz and @ylecun are both incredibly knowledgeable and have fewer conflicts of interest when commenting about the current state of AI.
Anthropic and OpenAI cannot become profitable unless they can reduce the ratio of training cost to inference profits. In the long run, their survival may depend on outlawing competitive open source models. This can only be done under the guise of safety regulation.
1
2
458
I can only imagine the levels of hellscape we'll unleash on some poor digital consciousness if someone uploads a human connectome.
ไธๅชๆ่็่ๅญ๏ผไธบไปไน็็ซๅ
จ็ฝ๏ผ
AIๅคงๆจกๅไธป่ฆๆฏ้ ๆตท้ๆฐๆฎ่ฎญ็ปๅบๆฅ็๏ผไธ้้็ฎใไธ้้่ฎญ็ปๆ่ฝโๅญฆไผโๆ่ฝใ
ไฝ็ฐๅจ๏ผไธๆกๆฐ็ๆๆฏ่ทฏๅพ่ขซ่ฏๅฎไบ๏ผไธ็จๆตท้ๆฐๆฎ่ฎญ็ป๏ผ็ดๆฅๆ็็ฉๅคง่็โ็ฉ็็ต่ทฏๅพโๆฌ่ฟ็ต่๏ผๅฐฑ่ฝ่ชๅจไบง็่กไธบ๏ผ
่ฟๅช่ขซโไธไผ โ็ๆฐๅญๆ่๏ผไป
ไป
ไพ้ ไปฅไธ4ๆ ทไธ่ฅฟ๏ผๅฐฑ่พพๅฐไบ 91% ็่กไธบๅ็กฎ็๏ผ
1. ็ฅ็ปๅ
่ฟๆฅๅพ่ฐฑ๏ผๅฎๆด็็ปๆ็ฝ็ป
2. ่ฟๆฅๆ้๏ผ็ฑ็ช่งฆ่ฟๆฅๆฐ้็ดๆฅๅณๅฎ
3. ็ฅ็ปๅ
ๅฑๆงๅ็ฑป๏ผๆ็กฎๅชไบๆฏๅ
ดๅฅๆงใๅชไบๆฏๆๅถๆง
4. ๆ็ฎ็็ฅ็ปๅ
ๆจกๅ๏ผๆฎ้็โๆผ็งฏๅๆพ็ตโ๏ผLIF๏ผๆจกๅ
ๅฎ่ฏๆไบไธไปถไบ๏ผๅคง่ๆฌ่บซ็ๆๆ็ฝ็ป็ปๆ๏ผๅฐฑ่็ๆบ่ฝไธ่กไธบ็ๅ
จ้จ็ปๆๅฏ็ ใ
ไปๆ่็ๅไธ็บง็ฅ็ปๅ
๏ผๅฐๅฐ้ผ ็ๅไธ็บง๏ผ็ถๅๅฐฑๆฏไบบ่็860ไบฟ็บง๏ผ
โๅ
จ่ไปฟ็โ็็็ฉๆบ่ฝๆถไปฃๆญฃๅผๅผๅฏไบโฆโฆ
1
2
484
Worrying about Big Bad AI is distracting from the more immediate issue, I call the Hackageddon.
We should be hardening all systems with an urgency that would make Y2K pale in comparison.
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
3
1
9
505
Astra is a lot more diligent than Fable. If you tell it to QC something, it will do its best... even if that means burning through 80% of your quota.
3
407
GPT-Image 2.5 may be the first model to correctly generate a run cycle.
Note- the first one was wrong, so I asked ChatGPT to analyze and correct it and this was the result.
1
2
12
463
According to GPT-6 Astra itself, the better options for AI video animatics is ThreeJS, NOT Blender.
1
4
462