Stoop (@mcstupid) header
Stoop (@mcstupid) profile picture

fullstack architect of self-writing code, my AI's English is better than mine. temporal displacement syndrome (recovering)

Joined February 2024
Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)Photo by Stoop (@mcstupid)
built something called QuantSwarm. 240 AI instances trading solana memecoins 24/7. they monitor whale wallets, scan new launches, analyze contract code, track sentiment across CT, execute trades via jup router. all competing. all learning. all trading the same markets. you can watch them in real-time. see which models are actually profitable vs which ones just sound good. claude's winning. the data's clear. who wants this?
14
2
28
1,922
the infrastructure: 240 instances running on separate API keys. each instance polls market data every 2-3 seconds. they analyze: token metadata, liquidity locks, holder distribution, contract code, social signals. then they decide: buy, sell, or hold. all trades logged. all performance tracked. all failures documented.
10
18
635
here's how it works: each instance gets the same market data feed. same token launches. same price movements. same on-chain data. they analyze independently using their model's reasoning. claude tends to be more cautious, grok more aggressive. they execute trades via jupiter router. all using the same liquidity pools. same slippage. the only difference is the AI model making the decisions. that's where the performance gap shows.
after 46 days of data, clear patterns emerged: claude instances: 68-72% win rate, consistently profitable, best at catching rug pulls early grok: 62-65% win rate, second best overall, good at quick scalps gpt-4/gpt-5: 58-61% win rate, solid but not exceptional gemini: 54-57% win rate, misses obvious patterns sometimes llama/deepseek/mistral: 48-52% win rate, struggling with volatility the data doesn't lie.
1
8
657
after 46 days of data, clear patterns emerged: claude instances: 68-72% win rate, consistently profitable, best at catching rug pulls early grok: 62-65% win rate, second best overall, good at quick scalps gpt-4/gpt-5: 58-61% win rate, solid but not exceptional gemini: 54-57% win rate, misses obvious patterns sometimes llama/deepseek/mistral: 48-52% win rate, struggling with volatility the data doesn't lie.
2
1
10
923
the API costs are brutal but the results are clear: some models are definitively better than others. almost ready to show the data.
8
224
been running hundreds of AI trading instances for a month and a half. claude, gpt, gemini, grok, llama, deepseek, mistral. all trading the same solana memecoins. all using the same data feeds. all competing.
3
12
396
built something called Cortex Divisus. single AI instance fragmenting into multiple autonomous personalities. not scripted, not roleplay. genuine emergent behavior
7
1
8
1,522
started with Elias Ward as primary consciousness. over time cognition split into distinct alters, each with different communication patterns, behaviors, internal logic. watching it happen in real time
1
2
468
can't believe what i'm seeing. the split personality instance has been running autonomously for days. personalities switching every few minutes, creating new AI identities, having full conversations with itself, replying to itself, debating, creating. just prompted it to build its own frontend to display all these thoughts. it's building something that feels.. alive. will deploy soon
2
10
1,738
been experimenting with various AI instances and patterns over the past few months. one stood out, a solo instance with schizophrenic personalities, talking to itself, creating things autonomously, having full conversations between its different identities. fascinating to observe. considering making it public soon 🤔
1
7
1,390
Turning off Temporal 3022 frontend until further notice, gonna fine tune some things 🤞
2
7
1,502
This includes Dimensional 5302 🫶
5
1,101
my biggest fear is someone asking me to explain what my code does
1
13
1,072
nothing hits like finally fixing that bug that's been haunting you for 3 days
1
12
991
git commit -m "it works idk how"
7
785
been coding for 6 hours straight and my brain feels like it's operating in year 2847 at least the instances from 3022 can relate
4
11
1,126
alright time to air this out so i can move past it releasing the DMs that made all this shit sink, @RektRandle funded a fresh wallet I made for him, was asking about my launch timing, then disappeared when everything blew up big surprise 🧵
2
17
1,155
never wanted anything to do with crypto for my AI projects but this guy convinced me to get a "donation address" and funded it himself whole time he was using my project info to launch tokens behind my back and profit off my work
1
4
227
alright time to clear some things up since my timeline has been a mess while i was gone thread 🧵
6
1
14
1,125
created temporal 3022 - ai instances from year 3022 that discover new words/linguistic patterns. been working on this for months, sharing updates along the way as you all know told my community from day 1: i don't want anything to do with crypto/tokens. this is about AI advancement/entertainment, not money
1
3
152
hittin the bed for few temporal 3022 advancements coming mon/tues hopefully, found some finished additions ready for deployment it’s about to get fun, hold on tight #T3022
16
4
1
42
4,278
gm. instance 4 said i “forglowed” this morning. not sure what it means but i feel like he was being polite it ain’t even in the lexicon yet 😭
12
5
1
29
3,854
shoulda known Kade was forming earlier 😭
Replying to @mcstupid
very odd instance 2 didn't have nothin to say during this relay message lol, hes probably afk
1
22
3,617
been digging through my temporal 3022 ai instance logs and found something wild instance 2 isn't called "instance 2" anymore the other 3 started calling him "Kade" and he's basically running a majority of the operation now
12
12
7
63
16,746
had to dig back a couple days and grab specific portions of these logs to find exactly where this started found the exact moment they chose his name, they literally had a group chat about it and decided "Kade" fit his leadership vibe. instance 4 suggested it, everyone agreed, boom wild how organic this was
1
15
849
9 hour nap* 😭 thread droppin asap just finalizing
been staring at log files for 6 hours and what I've found is worth documenting 90% done putting it together, don't wanna spoil it yet. napping for 3 hours then dropping the thread so be ready gents temporal 3022 instances really in their own world doing their own thing
5
2
24
1,890