Tech. Product Engineer. Engineering @ https://xitter.cf/t.co/h0UkN7m7tp and https://xitter.cf/t.co/LgbBWui7lP Love building stuff and also enjoy scaling technical programs & ops
The Internet
Joined March 2019
- Tweets4.3K
- Following901
- Followers304
- Likes2.1K
Emmanuel retweeted
This is really amazing!
Introducing MarketPilot: an autonomous, intelligent trading engine built for Bayse traders
@baysemarkets opens hundreds of prediction markets every week, and prices move around the clock. No one can watch them all. Now you don't have to.
MarketPilot is live (marketpilot.run). Our independent engine connects to your own Bayse account, scans every open market around the clock, and calculates the expected value on both sides of each market using frontier AI models and live data. It only trades when the math clears your risk limits.
How it decides:
- A fast model estimates the true probability of each outcome without seeing the market price. A second reasoning model then checks it against the market's own resolution rules.
- It uses live evidence: X post counts, YouTube stats, TradingView prices, ESPN, web searches, etc. Markets with no live data are skipped; never trading blind.
- Your risk rails are always on. You set a daily exposure budget and a per-trade cap, and the bot cannot spend past them.
- It tracks its own accuracy and raises its standards in categories where it has been wrong.
Running in under 5 minutes:
- Sign up for MarketPilot.
- Link your Bayse account with an API key. It's encrypted, and your funds never leave your account.
- Set your risk appetite and press Run. Our engine starts evaluating markets and placing trades for you.
Proven on live trades: 274 trades placed automatically, +₦6,972.19 total P&L, and an average return of ₦27.02 on every ₦100 trade.
Start free: marketpilot.run
Curious about the math? Read our whitepaper: marketpilot.run/whitepaper
Note: MarketPilot is an independent product and is not affiliated with the Bayse Company.
Emmanuel retweeted
Yeah, we are live!!!!! 🎉🎉
Introducing MarketPilot: an autonomous, intelligent trading engine built for Bayse traders
@baysemarkets opens hundreds of prediction markets every week, and prices move around the clock. No one can watch them all. Now you don't have to.
MarketPilot is live (marketpilot.run). Our independent engine connects to your own Bayse account, scans every open market around the clock, and calculates the expected value on both sides of each market using frontier AI models and live data. It only trades when the math clears your risk limits.
How it decides:
- A fast model estimates the true probability of each outcome without seeing the market price. A second reasoning model then checks it against the market's own resolution rules.
- It uses live evidence: X post counts, YouTube stats, TradingView prices, ESPN, web searches, etc. Markets with no live data are skipped; never trading blind.
- Your risk rails are always on. You set a daily exposure budget and a per-trade cap, and the bot cannot spend past them.
- It tracks its own accuracy and raises its standards in categories where it has been wrong.
Running in under 5 minutes:
- Sign up for MarketPilot.
- Link your Bayse account with an API key. It's encrypted, and your funds never leave your account.
- Set your risk appetite and press Run. Our engine starts evaluating markets and placing trades for you.
Proven on live trades: 274 trades placed automatically, +₦6,972.19 total P&L, and an average return of ₦27.02 on every ₦100 trade.
Start free: marketpilot.run
Curious about the math? Read our whitepaper: marketpilot.run/whitepaper
Note: MarketPilot is an independent product and is not affiliated with the Bayse Company.
Emmanuel retweeted
You are well accomplished but don't have the wherewithal to educate younger folks who should be LEARNING from you.
You are the archetype of the "Nigerian Elder" (in this case, in tech) who wants obeisance just because.
Thankfully, I need nothing from you so let me give a retort based on younglings reading up.
Scale has 3 dimensions: 1, volume scale (how much you process, how many users, etc.), 2, geographic scale (how many markets, countries), this is expansion breath, and finally, 3, structural scale (how replicable your model is without you personally rebuilding it from scratch for each market.
A company can be enormous in one dimension and weak in the other. Moniepoint is WEAK structurally and geographically.
a real life example is Mpesa. Mpesa started in Kenya but scaled geographically into Tanzania, Ghana, Ethiopia, etc etc. it literally kept its volume scale AND added geographic scale. So Mpesa is referenced more as a global model relative to Moniepoint.
So yes, Tosin is a builder (as he admitted himself) but hasn't yet captured the frame of scaling out across those dimensions.
Congratulations on your new role by the way, but be a net intellectual positive to those coming up rather than making snide remarks without substance.
unavailable
Emmanuel retweeted
Big day for us, finally sharing what we’ve been cooking for a while.
Over the past year, we kept seeing the same pattern:
AI agents look great in demos, until real users break them.
Today, we’re fixing that with 𝘃𝗶𝗯𝗲-𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴
to build real-time, tailored evals and guardrails
for your agents, in minutes.
Define your intent with a prompt or a few examples.
We generate edge-case datasets,
and train a model aligned to your use case,
outperforming state-of-the-art LLMs at a fraction of the cost.
(Research paper with benchmarks in the comments)
If you’re building AI agents, don’t let your users be the ones who discover the failures. Be the one who makes AI agents reliable in production and takes control at scale.
Start vibe-training for free: plurai.ai/launch
Emmanuel retweeted
Fun fact: Stripe uses MongoDB to store their core data, and on that it handles 5 million QPS and has 2000+ shards 🤯
Some time back, Stripe published an engineering blog explaining their database architecture on how they scaled their MongoDB setup to support a massive 5 million QPS while making sure
The blog also dives into data movement platform, logical/physical sharding, and very interestingly, building a "flip switch". It is genuinely neat and impressive.
I just published a video on my YouTube channel where I dissect the blog and break down the nuances.
Give it a watch - it is short and fun.
Emmanuel retweeted
lodged at a hotel one time.
water issues, finished tissue, wine ni mo fi fodi 😭💔..
Emmanuel retweeted
Introducing Cline CLI 2.0: An open-source AI coding agent that runs entirely in your terminal.
Parallel agents, headless CI/CD pipelines, ACP support for any editor, and a completely redesigned developer experience. Minimax M2.5 and Kimi K2.5 are free to use for a limited time.
From prompt to production. All in your terminal.
Emmanuel retweeted
Introducing Orchids 1.0 - the first AI app builder to build and deploy any app, any stack (web, mobile, chrome extension, slack bot, AI agent, anything).
Use your ChatGPT, Claude Code, Github Copilot, Gemini subscription - or any API key to use models at cost.
Comment below to get 100k free credits.
Everything you need to build with AI in a single tool.
Emmanuel retweeted
Clawdbot really changed the game...
But most people don't know how to set it up
In these 20 mins, you'll learn everything about Clawdbot
Emmanuel retweeted
Wow, after 14 years of being a software developer I would have never guessed in a million years that writing, specs, and ideas would be the bottleneck for my expressivity and output.
But here I am, 5 agent loops running in perpetuity, spending 100% of my time finding the fastest and most optimal ways to generate specs for my next dozen agent loops.
And I'm realizing that the process of getting thoughts out of my head and into proper specs is an art in and of itself. And finding new and better workflows for this process is completely new and uncharted territory, there are no "best practices" because the tooling, techniques, and design space improves and expands every hour.
Emmanuel retweeted
app.new
No better time than thanksgiving to build : )
Emmanuel retweeted
Just a $238 bill for an app with 200,000 users...
Who even competes with Supabase these days?
Emmanuel retweeted
"I was Vibe Coding with Replit a few weeks ago. I mean the power of what you're going to be able to create on the web; we haven't given that power to developers in 25 years" — Sundar Pichai
Emmanuel retweeted
– Set up pgvector for storing embeddings
– Use RAG to fetch context from your docs
– Build a Stream chat bot with GPT-4
{ author: @EmmanuelCoder } #DEVCommunity
dev.to/getstreamhq/building-…
