jayson

1.4K posts

jayson banner
jayson

jayson

@jayson

Jayson Hawley. Burned out vain gen-x ronin. Chaotic Neutral writer, producer, tech geek, and loyal pal to dogs. Think of this as a twitterized bio-pic.

Southern California Katılım Nisan 2007
95 Takip Edilen379 Takipçiler
Paul Sims
Paul Sims@SimslearnAi·
An Anthropic engineer literally stopped me at a coffee shop because of what was on my screen. I was sitting at Sightglass running my Polymarket bot. He looked over once. Then again. Then said: “That’s not a normal trading setup.” I told him the whole thing runs on: • Claude Code • 4 open-source repos • $25/month That’s it. He pulled up a chair instantly. “I work on the agent team at Anthropic,” he said. “We stress test Claude for workflows exactly like this.” Then I showed him what the bot was actually doing. 86 MILLION trades analyzed. Every wallet. Every entry. Every exit. Every profitable pattern. One prompt: “Find wallets with 100+ trades and 70%+ win rate. Rank by profit. Export the best ones.” Claude scanned 14,000 wallets in 4 minutes. Returned 47. The top 20 wallets made more money than the other 13,000 combined. He stared at the results and said: “That’s not data analysis. That’s a weapon.” And we were just getting started. Second repo: A Rust CLI scraping 500 live Polymarket markets in minutes. Claude filtered everything automatically: • spread gaps • liquidity depth • timing windows • whale behavior 500 markets became 35. Before I even looked at them. 93% rejected automatically. Then a trade closed live on my screen. +$84. He didn’t even blink. “How does it decide when to enter?” 3 independent AI agents: • arbitrage • convergence • whale-copying No shared memory. 2 agents agree = full position 1 agrees = half size Disagreement = no trade That consensus system alone cut 40% of losing trades. Then he asked the real question: “What about exits?” That’s where it gets stupid. The profitable whales rarely hold to settlement. 91% exit early. So my bot exits BEFORE they do. It takes profit at: • 85% expected move or • unusual volume spikes Basically: It copies smart money… then front-runs their exits. He just sat there staring at the terminal. “How much did you start with?” $200. 27 days ago. Current balance: $14,300. 271 trades. 74% win rate. Sharpe ratio: 2.47. Fully automated. I haven’t touched it in weeks. Before leaving he said: “This is almost identical to the internal scenarios our red team simulates.” Next morning I got an email from him. “Would you be open to speaking with our policy team?” I replied: “The article IS the meeting.” The craziest part? This stack costs less than Netflix. AI is no longer replacing workers. It’s replacing entire hedge funds. Comment “Claude” if you want the framework.
English
1.4K
150
1.3K
255.2K
jayson
jayson@jayson·
I think he made it over the bridge.
jayson tweet media
English
0
0
0
47
jayson
jayson@jayson·
After discovering they're engineered to die in four years, a replicant combat leader and three others fight their way off a doomed off-world colony and toward Earth, not to survive, but to confront the man who made them mortal. - complete, ready to go. #bladerunner #roybatty #tearsinrain #replicants #screenplay
jayson tweet media
English
0
0
0
986
jayson
jayson@jayson·
This is what I get when I try to be too complicated.... the honesty is refreshing.... #Claude
jayson tweet media
English
0
0
0
51
jayson
jayson@jayson·
I backtested my own signal, it had no edge, so I stopped pretending... fixes on the way.
jayson tweet media
English
0
0
0
47
DocSchnag
DocSchnag@DSchnaggel86077·
@jayson wasnt Hermes a trickster like Loki ?
English
1
0
0
8
jayson
jayson@jayson·
Started on openclaw and Gemini Processed through hermes agent and GPT5.4 But, and it's obvious, nothing beats Claude Code. (For now)
jayson tweet media
English
1
0
1
75
jayson
jayson@jayson·
Kinda digging Hermes Agent.
jayson tweet media
English
0
0
1
41
Balaji
Balaji@balajis·
China is physical AI. Robots with nunchucks.
English
217
283
2.3K
558.7K