Physics, AI and technology.
Joined May 2025
- Tweets 550
- Following 982
- Followers 58
- Likes 9,774
62 Photos and videos
26 Oct 2025
Another Veo 3.1 experiment - I showed it physics textbooks & prompted
"Continue the scene in a funny and surprising way."
(I also asked for a Scottish accent audio narrator, which I think explains the Scottie dogs π π€·)
Physics comprehension ββοΈ
Trolling π―β
25 Oct 2025
I like to poke at where gen AI models make interesting mistakes (interesting to me at least).
... but today, I was impressed at how Veo 3.1 accurately read text in a photo I took (last year) and quoted it in audio narration. Other examples confirm text reading & comprehension.
1
212
25 Oct 2025
I like to poke at where gen AI models make interesting mistakes (interesting to me at least).
... but today, I was impressed at how Veo 3.1 accurately read text in a photo I took (last year) and quoted it in audio narration. Other examples confirm text reading & comprehension.
1
279
21 Oct 2025
With Veo 3.1, I noticed that rowing boats travel the wrong way.
People moving in the direction they face is so universal that a strong prior forms that's hard to unlearn in this exceptional case.
I animated more photos I took of other cities to verify π§
x.com/AnthonyPPhysics/statusβ¦
20 Oct 2025
I tried out Veo 3.1 to animate a photo I took of Cambridge earlier this year.
Locals can tell it's AI because of several problems with the boat π£
Veo has learnt such a strong rule that people move in the direction of facing that it hasn't also learnt this one weird exception π€
1
91
20 Oct 2025
I tried out Veo 3.1 to animate a photo I took of Cambridge earlier this year.
Locals can tell it's AI because of several problems with the boat π£
Veo has learnt such a strong rule that people move in the direction of facing that it hasn't also learnt this one weird exception π€
1
137
6 Sep 2025
I saw a claim that AI video models can't generate finger clicking.
I tried Veo3 - it sticks middle fingers upπ±π
.
The sound of clicking is correct, so it's within the training set π€.
My guess is that it's akin to the bias against left-handed writing - unbalanced dataset effect?
1
3
156
2 Aug 2025
You've had "pizza quattro formaggi". You may even have had an 8-cheese pizza -
but have you had a 16-cheese pizza (with bacon and mushrooms)?
The world record is 1001 cheeses, but I say we can beat that with a 1024-cheese pizza if we invest more in fundamental R&D ππ.
2
3
264
27 Jul 2025
Many UK X users say that political posts are censored now that the Online Safety Bill has taken effect. I'm not political, so the censoring I see is bizarre π₯΄.
Now I will never know why I shouldn't incorporate in Delaware π
Reminder of how we got here:
windowscentral.com/british-gβ¦
1
154
25 Jul 2025
I was challenged to make a cool AI video about my PhD (years ago), because I'm uncool without AI π
Script by Gemini, video by Veo3 πͺ
Equations in the video are garbage, the script needs work-
but back then, this video was inconceivable. AI moved like lightning this ~10 yearsπ.
1
110
22 Jul 2025
First attempt at an AI-generated "documentary" π
.
"Standard Model Particle Discoveries"
Script by Grok, video by Veo3 (audio narrated).
*Minimum* editing by me, e.g. where Veo3 refuses to accept names in prompts (and "Cambridge" - π€·).
Limited compute budget, so "imperfect" π€£
1
157
21 Jul 2025
Let's see if Veo3 can generate reversed length scale hierarchies.
Ordinarily:
Bacterium < raindrop < chest < castle < forest < ocean < planet < star < galaxy.
How much nested scale reversion can we get? Examples here.
With good prompts, it can do a little, but doesn't enjoy it π
1
110
19 Jul 2025
Utopian visions from Grok, rendered by Veo3
Today: habitats high in Earth's atmosphere.
1. Scientific Research Outpost
2. Cultural and Educational Retreat
3. Disaster-Resilient Community
4. Eco-Tourism and Wellness Haven
I'm not convinced, but it's a hard challenge.
Better ideas?
81
18 Jul 2025
Next up in *positive* future worlds made by Veo3 from Grok descriptions is... VR.
1. Skills training
2. Remote collaboration
3. Technical assist HUD
4. Emergency simulation
Whatever happened to the Metaverse?
What is an optimistic alternative to Snowcrash, Ready Player One?
116
16 Jul 2025
After getting Grok & Veo3 to create positive visual depictions of life underwater and on Mars, I turned to life underground. What's a positive vision of humans prospering in underground cities? What would make people positively choose it instead of the status quo?
1
2
85
15 Jul 2025
Suppose we're going to Mars π. Suppose we have to π±. What's your vision of how we're going to live π±? I asked Grok to suggest some habitats, and passed the descriptions to Veo3.
1. Lava tube
2. Inflatable
3. Ice cavern
4. Crater rim
Any better ideas? π§
105
14 Jul 2025
Oceans cover ~71% of the Earth's surface, but most people rarely think of them. We cultivate the land, but act as hunter-gatherers at sea. Humanity adapts to new environments, and is looking to new planets. What is your vision for humanity's future technology in the ocean?
51
14 Jul 2025
There's a short supply of welders - the lack of young people becoming welders has forced the older welders out of retirement to stop the world ending π§.
I asked Gemini to suggest some robots for general purpose mobile welding π¦Ύ.
"How hard can it be?" π
ππ (very, of course)
73
11 Jul 2025
I've been feeding "fake word" prompts to Veo3 x.com/AnthonyPPhysics/statusβ¦.
- Try "ej republast ish pluncidelst diffechindic" 4x.
The two speaking ones are interesting (audio)
1) Error corrects to "we republicans pledge to defend"
2) Says the fake words
Varied but not unconstrained π€
9 Jul 2025
Previously x.com/AnthonyPPhysics/statusβ¦,
I gave "fake words" to Veo3 and got random videos back.
What about the same fake words again?
The original three in order, plus the 1st again as a bonus.
- No similarity on re-runs?
- Implies no consistent meaning inferred?
- How much freedom?
166
11 Jul 2025
I'm puzzled when I see people on X imagine that LLM models are self-knowledgeable enough to answer questions about themselves not in public documentation π. Humans aren't born with innate knowledge of their neurobiology, and AI models only "know" what is in their training data.
1
50
9 Jul 2025
Previously x.com/AnthonyPPhysics/statusβ¦,
I gave "fake words" to Veo3 and got random videos back.
What about the same fake words again?
The original three in order, plus the 1st again as a bonus.
- No similarity on re-runs?
- Implies no consistent meaning inferred?
- How much freedom?
8 Jul 2025
I've seen posts prompting Veo 3 with camera-filename-like prompts to get talking heads back πΈ.
Talking heads seem to be a common default for many random word prompts.
How about 5 random "fake" words π? randomwordgenerator.com/fakeβ¦
Here's what happened... fairly random videos π π€·.
243
9 Jul 2025
A common AI flex is "faster than Moore's law" growthπ¦Ύ
Often, this refers to
- Model size
- Compute
These mean that effort spent outpaces the underlying technology. This is a looming problem, not a flex. It requires Moore's law to speed up or ML methods to get smarter to sustain.
36