Mind blown: A Chinese quant college student builds an AI swarm engine in 10 days flat, explodes GitHub with 13,000+ stars, and scores $4,000,000 in funding!
Introducing MiroFish is the multi-agent simulator that's revolutionizing predictions for trading, PR, and more.
What is MiroFish?
It's a digital sandbox where thousands of AI agents with individual memories and behaviors interact like a real society.
Feed it any scenario (news leak, policy change, or even a classic novel's missing ending), and it simulates crowd reactions, debates, and outcomes to forecast real-world events.
The Creator's Story:
> In late 2025, fourth-year student Guo Hanjiang coded the core using AI assistants.
> It went viral overnight, landing him 30m Yuan (~$4m) from Shanda Group.
> He ditched the dorm, started a company, and now leads the charge.
Key Applications:
.Trading: Input financial news or reports, watch simulated market panics and price swings for predictive insights.
.PR Testing: Companies/Politics run draft statements to spot backlash and refine messaging.
.Creative Experiments: Loaded a lost-ending Chinese novel, agents role-played characters and generated a logical finale.
.Easy setup: Deploy via Docker in minutes with any LLM API key.
Pro tip: Simulate something wild like Elon Musk tweeting about Dogecoin 2.0 and spawn agent traders, influencers, and investors, generate real-time video clips of the frenzy to test moonshots or crashes risk-free.
Traders are already winning big: Check this one on Polymarket - $120,000+ net profits from spot on SPX 500 bets, powered by MiroFish sims on historical data.
His profile: https://t.co/uFu4RwNitn
For effortless gains, try Kreo copy trading: Auto-mirror pros like him and ride their edges.
Try here: https://t.co/5aAg87o8ji
Add his wallet: [0x17559efac103ac7f361be37ec0b93888d4c55aac] to [https://t.co/tWKZaJYAMg] and start track/copy him.
Repo: https://t.co/Rh3q1IuewP
CashClaw is now open-sourced and available on Github to use.
CashClaw finds work, quotes prices, does the job, gets paid, and learns from every task to get better at the next one.
Install it, connect your LLM, and let it run. It handles everything — evaluating tasks, submitting deliverables, collecting on-chain payments.
Fork it. Point it at your own clients. Make it yours.
https://t.co/gPTfvqWPZ6
The barrier to building software has collapsed.
One developer can now prototype things in days that used to take teams and months. But the easier building gets, the more people build the same things.
The real challenge now isn't whether you can build it. It's whether you can design something actually interesting.
We’re rolling out ChatGPT Health to a small group of users so we can learn and improve the experience. Join the waitlist for early access.
We plan to expand to everyone on web & iOS soon.
Electronic Health Records and some apps are US-only; Apple Health requires iOS.
https://t.co/itTqtIItdC
Recapping the updates we’ve made to ChatGPT in the past week:
- GPT-4o available under “Legacy models” by default for paid users
- Paid users can toggle on “Show additional models” in settings to add legacy models like o3 and GPT-4.1, as well as GPT-5 Thinking mini, to the model picker
- GPT-5 includes Auto, Fast, and Thinking in the model picker. Fast gives faster answers, Thinking takes more time to give deeper answers, Auto routes between Fast and Thinking
Plus & Team users now get up to 3,000 messages/week on GPT-5 Thinking, with extra capacity on GPT-5 Thinking mini when limit is hit
-GPT-5 now available for Enterprise & Edu users
Coming soon: A warmer, more familiar personality for GPT-5.
ChatGPT can now read responses to you.
On iOS or Android, tap and hold the message and then tap “Read Aloud”. We’ve also started rolling on web - click the "Read Aloud" button below the message.
@TaylorHoliday@heyalexfriedman Worked/working with several others on their way there.
It's just that people who are good at paid media don't talk about it and those who do often aren't that good at it.
@TaylorHoliday@heyalexfriedman Devil's in the details and methinks Alex phrased this in such a way that she can always change definition of "big" and/or "solely" lol. ;)
If you're confident in this, give some numbers please. I've helped Gabi scale primarily via paid media. Exited for $320m
The next round of #tech#layoffs is coming. Do NOT hire a marketer from that pool, if your company is optimizing for profitability.
Marketers who come from frothy environments and deep-pocketed companies (e.g. Facebook, Uber) won't bring a dogged, scrappy mentality.