Mischa M. Runsink retweeted
An Anthropic engineer paid for my espresso at Sightglass when he saw my screen
I was running my Polymarket bot from the counter. He was next in line. Looked over my shoulder. Stopped scrolling.
"That's not a normal trading app. What's it actually running on"
I told him. Claude Code. Four repos. $25 a month.
He sat down without asking.
"I'm on the agent team. We stress test Claude for exactly this. You're letting it find its own edges"
Not just edges. Wallets.
86 million trades. Every wallet. Every entry. Every exit.
"You're feeding Claude raw wallet data and letting it identify who consistently wins. Then cloning them"
He said it slowly. Like he was writing the threat model in his head.
One prompt. Find every wallet with 100 plus trades and win rate above 70%. Rank by profit. Export top 50.
Claude scanned 14,000 wallets in 4 minutes. Returned 47.
The top 20 made more than the bottom 13,000 combined.
"That's not a stat. That's a hit list"
Exactly.
"And you didn't write the scoring function"
Claude did. I just wired it into an if-statement.
Then I showed him the second repo.
Official Rust CLI. No API key for reads. 500 markets, Claude scores them in minutes.
Gap. Depth. Resolution window.
487 markets become 35 before a dollar moves.
93% killed before I even see them.
A green fill landed on the screen. +$84.
He watched it hit.
"How does it decide to actually enter"
Three agents. Shared wallet. No shared memory. Arbitrage, convergence, whale copy. 2 agree, full size. 1 alone, half. Disagree, no trade.
Consensus filter alone killed 40% of losing trades.
"And the exits?"
The 47 whales never hold to settlement. 91% exit early. 73% of max profit captured. Redeploy immediately.
My bot cuts at 85% of expected move or on a 3x volume spike.
"You built a whale copy bot that exits before the whales"
Yeah.
He put his espresso down.
"How often does it trade"
10 a day on average. Most of them skipped before I look up from my coffee.
My setup:
Claude API - $20/mo
VPS in Germany - $5/mo
poly_data - free
polymarket-cli - free
Polymarket/agents - free
$200 seed. 27 days ago. $14,300 now.
Copytrade here: t.me/KreoPolyBot?st…
271 trades. 74% win rate. Sharpe 2.47.
I haven't touched it in 27 days.
He stared at the screen for a long time.
"This is literally what our red team simulates. Except you actually shipped it"
He emailed me the next morning.
"Any chance you'd take a call with our policy lead"
I told him the article is the call. Read it twice.
Too late to gatekeep.
You only need Claude + laptop + 1 hour/day.
Giving This Free for 24 hours. To get it:
1. Comment the word 'Claude'
2. Like and Retweet this post
3. Follow me
@ZayvenKnox
Dat moment dat je het opgeeft omdat je van @ZiggoWebcare weer een mail krijgt met een rekening voor je moeder die al in 2019 is overleden. Zou beter zijn als jullie je account veranderen in ZiggoWeCare en dit oplossen…
Een heerlijk ontspannen ochtendwandeling met Tommie. Genietend van de natuur en een fijn luisterboek op @storytel.nl van @hans.peter.roel #lovelife #tommie #ki #morningwalk instagram.com/p/CH94VJNJ9AGT…
Mischa M. Runsink retweeted
Celebrating the 151st birth anniversary of a great leader. Have a safe and happy #GandhiJayanti.
Mischa M. Runsink retweeted
Brokers and insurers still struggle with information siloes and the massive amounts of unstructured data generated.
Learn why enterprise-wide data digitisation is the solution to tackling unstructured data and thriving in a competitive market. bit.ly/2SaHpTp #insurtech
Mischa M. Runsink retweeted
Property and #casualty insurers are reluctant to change – but rising customer demand is spurring automation adoption to lower costs and drive growth.
From process improvement to auto-populating forms, here are the best automation opportunities using #RPA. bit.ly/2HEPKge
Mischa M. Runsink retweeted
The average profit per mortgage loan in 2018 was just US$367, nearly half the previous year (US$711).
To tackle the shrinking profits that continue to plague lenders in 2020, they must remain competitive and manage increasing customer expectations.
Mischa M. Runsink retweeted
78% of banks have already implemented automation solutions or are in the process of digitising their #TradeFinance operations.
Learn how #CognitiveMachineReading can help you use more of your data to become a strategic resource for banks worldwide. bit.ly/3jgPy4Q
Mischa M. Runsink retweeted
Learn how with @CNAHardy’s Ingrid Woodward, and AntWorks’ @mike_hobday and Ben Platts at our webinar 16th September, 9 am EST. Register now. bit.ly/32xPd7H
#Insurance #InsuranceIndustry #Claims #Digitization #SSOW2020 @ssoweek
Mischa M. Runsink retweeted
CASE STUDY: Discover how AntWorks enables this global #BPO to reduce bill of lading processing time by 63%. bit.ly/2RlJVFY #BusinessProcess #Outsourcing
Mischa M. Runsink retweeted
How do you transform traditional claims operating models to meet increasing customer demands in challenging times?
The answer is the digitisation of ALL data, including unstructured data, to generate rich claims insights at the core of your digital transformation strategy.
Mischa M. Runsink retweeted
We’re spilling the beans – AntWorks' Robin P. will provide the low-down on #CognitiveMachineReading and how you can scale your #RPA projects better. (Hint: it involves data)
Check out the sneak peek podcast collab with @WYWM_Academy. youtu.be/ejcQzpGenlQ
Mischa M. Runsink retweeted
BOT downtime is a MAJOR challenge that traditional #RPA struggles to address.
QueenBOT RPA solves it by creating smarter BOTs that can deal with unknown exceptions and are intelligent enough to start again.
Mischa M. Runsink retweeted
Learn how QueenBOT #RPA can ensure business continuity and deliver failover management with our free trial today: bit.ly/3idCYT3
#StraightThroughProcessing #RoboticProcessAutomation
Mischa M. Runsink retweeted
Commercial underwriting is slowed by the inability to automatically handle unstructured data such as broker submissions, underwriter notes, and contracts.
Incorporate these 5 must-haves to improve your #underwriting process. bit.ly/31RKpcW #Insurance #InsuranceIndustry
Mischa M. Runsink retweeted
80% of data is unstructured and cannot be digitised using #OCR and #RPA, slowing the underwriting process and diminishing the customer experience.
Learn how you can transform ALL your data and speed up your #Underwriting process with #CMR. bit.ly/2Ekec4O #Insurance
Mischa M. Runsink retweeted
Digitise all your data, regardless of format, and transform your intelligent automation programme with our Digital Disruption brochure. Download your copy today: bit.ly/3j8qmgb
#Government #Digitization #PublicService
Mischa M. Runsink retweeted
Solving these challenges starts with clean, digitised data. Download our eBook and learn how you can win the race for data with Cognitive Machine Reading: bit.ly/3jwPz4a
#Insurance #InsurTech #InsuranceIndustry #Digitization
Mischa M. Runsink retweeted
Enabled by automation, the future of underwriting will not take days – but minutes.
Transform your underwriting process with our AI and ML-powered Cognitive Machine Reading solution. bit.ly/3j99KVJ
#Underwriting #Insurance #InsuranceIndustry #CMR














