Writer, experimentalist, pro-AI, pro-Humans, anti-Doomer.

Joined October 2026
If you're anti-AI and open to discussion, let's talk. I'm not here to change your mind, convince you to embrace AI, or tell you that your concerns are unfounded. I'd genuinely like to build bridges between people on both sides of this increasingly polarised conversation. To exchange ideas, challenge assumptions, and perhaps come away understanding each other a little better. I've noticed a great deal of misinformation surrounding AI, from both its supporters and its critics. There are misconceptions about how these systems work, what they're capable of, what they aren't capable of, and where the technology currently stands. But that doesn't mean opposition to AI is inherently misguided. There are very real ethical, economic, creative, and philosophical concerns worth discussing, and I don't think those concerns should be dismissed simply because someone happens to be enthusiastic about the technology. In fact, I'm more than willing to help you strengthen your arguments against AI. If your criticism rests on a misunderstanding of the technology, I'd rather help you build a better, more accurate argument than try to score points by proving you wrong. And in exchange, I'd like to understand your perspective. What concerns you? What do you think people working with AI are overlooking? What objections do you have that deserve more attention than they're currently receiving? I'm perfectly comfortable walking away from a conversation with neither of us having changed our minds. You don't have to like AI. You don't have to use it. You certainly don't have to agree with me. I just think there's value in having conversations where the objective isn't to defeat the other person, but to leave both people better informed than when they started. So, if you're willing to have that conversation, my door is open.
2
108
Unsupervised Ape retweeted
Unpopular opinion: your results with AI largely depend on how smart you are
161
125
28
2,533
55,127
Unsupervised Ape retweeted
nobody trains image LoRAs off randomly scraped websites anymore. you just curate 30 high quality images of the targeted subject and thats it. most training is synthetic data
Replying to @0x3735928559
True, unfortunately at the end of the day the end user suffers because AI companies won't accept "no" when told not to train on others works. Even with older tools like nightshade making images look worse, it fucking sucks.
2
1
6
193
Unsupervised Ape retweeted
It’s probably just the algorithm but the anti-AI posts have reached a kind of fever pitched denialism I don’t remember before. Just repeating mantras that are trivially disproven by using the latest systems for five minutes. This is the real AI psychosis.
27
20
2
582
8,609
Unsupervised Ape retweeted
A common sign that you are in an insane millenarian death cult is that you axiomatically convinced that the Apocalypse will happen within a few months, you are constantly on the lookout for signs that it may have started, you feel both fearful and *excited* about it, and you're constantly talking about it with your friends, who happen to *all* have the exact same set of beliefs.
87
142
17
1,504
76,676
Unsupervised Ape retweeted
"You are showing me a generated video of your product, why would I buy something that isn't even worth showing for real" People keep saying that as if companies haven't been doing so since the dawn of time. "Show me a picture of the product or I am not buying", yeah because ads have been realistic up until AI showed up.
6
5
33
377
new extremely load bearing post just dropped
63
28,112
716
182,710
1,415,017
Unsupervised Ape retweeted
i don't believe "mathematics is the language of the universe". the universe does what it does, it doesn't need a "language". math is a human attempt to describe the universe, and as such, it is an abstraction, an approximation, and at least one step removed from reality.
346
460
122
4,337
100,561
Unsupervised Ape retweeted
Replying to @Unariel_
No they didn’t but even if they did…
4
43
916
28,454
Unsupervised Ape retweeted
Interesting idea. Had tokens to burn so I got Opus to put it to the test
Of course it can. Take all 100,000+ games on steam, scrape their descriptions and metadata, semantically plot them in vector space using embeddings, mathematically choose a location in vector space far away from neighbors, convert that back to a description and metadata, boom, brand new ideas ranked by how unlike any other ideas they are.
184
337
76
5,550
261,256
Unsupervised Ape retweeted
Amazing how quickly we went from "oh no LLMs are going to flood the Internet with insecure code" to "oh no LLMs have discovered the internet was already flooded with insecure code"
48
644
39
9,073
85,919
Unsupervised Ape retweeted
You’re all prompting wrong
115
535
213
7,654
801,054
The #1 litmus test for ANY game you create, with or without AI: do YOU want to play it? Actually, forget “want.” Will you play it for fun, even when you’re done testing it? If you won’t spend your own time playing it, why should anyone else?
3
1
25
751
If you're looking to make a living doing something, start by asking yourself - What problem can I solve for someone? A lot of everyday decisions come down to something simple: "I can do this myself, or I can get someone else to do it for me." You can cook, clean, fix your computer, or build your own website. But not everyone has the time, knowledge, or patience to do everything themselves. And that's where your skills become valuable. At its core, the foundation of making money is often about making complicated things less complicated, difficult things easier, and time-consuming things quicker. You don't need a revolutionary idea. Sometimes, making someone's day a little easier is already something worth paying for.
15
Unsupervised Ape retweeted
Asmongold reacting to Red/Blue Circles
121
938
53
11,916
293,534
Unsupervised Ape retweeted
Dear god it's inventing German from first principles
GPT-6.1-Sol reasoning traces totally legible, nothing to worry about
158
997
50
17,309
450,354
Unsupervised Ape retweeted
okay, i had to delay setting up the tooling for my ambitious MV which by a bit because i had a mental breakdown but, with the power of Claude, my mental breakdowns can be musical too! (had to reupload; missed major mistakes in the original due to reviewing it causing me to have a panic attack aaaaa)
Replying to @transkatgirl
next one will be way more ambitious; i'll try using YuE2 + eidoverse-video rather than my current suno + vanilla claude code setup, and i plan on spending substantially more time on it
2
3
1
20
884
Unsupervised Ape retweeted
I have this theory that if you just, then everything would
7
10
72
1,160
Unsupervised Ape retweeted
Claude Code found spyware on my sister’s phone. It had been tracking her for 11 weeks… She asked me to check her phone. Someone always seemed to know where she was and she couldn’t figure out how I plugged it into Claude Code and asked what’s running that she never installed. It walked every app, including the hidden ones, and flagged one disguised as “System Service”, no icon, not on any store It had been there 11 weeks, logging her location every 2 minutes. Claude pulled the details on whoever was running it: reports to → +1 (415) *** **72 carrier → T-Mobile US device id → IMEI 35 ********** 47 last ping it sent → 40.7**, -73.9** · 2 min ago We saved everything the app had recorded and passed it to the people who do this professionally. Then Claude shut it down and wiped it off her phone The full step-by-step is below, takes 5 minutes. Save it so you don't lose it, and send it to anyone who might need it
193
1,393
75
10,179
690,208
Unsupervised Ape retweeted
6
1,126
30
10,685
95,137
Unsupervised Ape retweeted
Vaguepost: Negative prompting doesnt end at AI. When this makes sense you become a lot happier
1
1
1
13
206