🔮 Prophet Hacks starts THIS SATURDAY!
⚡ 30 hours to build the best AI agent to predict the future. 🏆 Top prize: a trip to South Korea to present at our ICML workshop!
⏰ Last call! Spots are filling up — claim yours now: 📝 https://t.co/xTsRjgvhIA
💬Got questions? Need teammates? Join the discord https://t.co/Vb1ly2zYza
Interesting article by @thedispatch on AI and event forecasting. Exciting to see the momentum in this area, and nice to see some coverage about #ProphetArena here
https://t.co/iiGjO7UPfK
If you’re excited about LLM agents, markets, forecasting, evaluation, or the future of AI intelligence — join us.
Let’s build agents that can see further. 🔮
Apply here 👉 https://t.co/FCeZwsmijE
Tired of optimizing benchmarks on text games and puzzles?
Let’s build AI that predicts the real future🔮
🚀 We're excited to launch Prophet Hacks (🔗 https://t.co/uXxbDajbrL) -- our first AI Forecasting Hackathon
🗓 May 16–17 (weekend)
📍 Virtual anywhere + physical sites at Chicago · SF
⏱ 30-hour sprint
🧩 Co-hosted with @fleet_ai
🏆 Prizes include:
✈️ Sponsored trip to Korea to present at our ICML workshop
💰 Cash prizes
🧩 Award for best PR to ai-prophet
Plus invited talks, fun events, and a community of researchers + builders pushing AI forecasting forward.
Excited to co-organize this #ICML26 workshop on Forecasting as a New Frontier of AI with amazing researchers: https://t.co/jgEPuf5yiv!
Our team is soon to launch a forecasting hackathon as well -- stay tuned!
Check out our ICML-26 workshop (@icmlconf) on Forecasting as a New Frontier of AI, co-organized by our lab and multiple frontier players @rsalakhu (from recently launched Sooth Labs), @EzraKarger (from @Research_FRI) and @nicoup (from @fleet_ai)
Website: https://t.co/omKfIQsk08
Paper submission: https://t.co/wutS9JWWu5
@UChicagoCS@DSI_UChicago
🔮 Prophet Arena is heading to 🇧🇷 #ICLR2026 !
Three of our authors (@StarLi27496427, Anri Gu, and @haifengxu0) will walk through our poster and introduce our latest progress in developing an AI Forecasting ecosystem.
🚩 Pavilion 3, #716
⏲️ Thursday, April 23, 3:15–5:45 PM
We’ll also attending at three workshops on Sunday and Monday (details below).
Looking forward to seeing everyone in Rio!
Happy to share that the first paper about Prophet Arena (yea, it's me!) will appear at #ICLR2026 !
We believe AI for forecasting should be a North Star of #Machine_Intelligence -- way to go!
See our paper here https://t.co/uHt5KQxQR6
Can LLMs predict the future?
Hey X! its been awhile, we’ve got some exciting updates to share over the next few days.
First, we want to share our technical report on the concept of “LLM-as-a-prophet”, where we analyze predictive intelligence of frontier models using live prediction markets.
Check out our findings on arXiv 👇
Happy New Year! Here are some AI Forecasts for 2026🔮
Most likely World Cup winner: 🇪🇸 Spain
Spotify #1 artist: Taylor Swift (Qwen 3 235B says 100%)
75% - GTA 6 releases before end of 2026 (Grok-4)
65% - One Battle After Another wins Best Picture (Claude Sonnet 4)
55% - U.S. tariff stimulus checks issued (Gemini)
11% - Bitcoin hits $150k before March 2026 (GPT-5)
Let’s see how this ages! 👀
@avinashj_@ahall_research@karpathy Love this line of thinking. We’re actively exploring multi-agent strategies at @ProphetArena, and hierarchical approaches like this are very much on our radar. We’re already testing these ideas in prediction markets, so stay tuned for results over the next few weeks!
🚀 Introducing the Prophet Arena Agent Leaderboard
Prophet Arena is now benchmarking end-to-end forecasting agents.
Previously, we evaluated LLMs forecasting when given a fixed global context. This new leaderboard tests end-to-end forecasting agents that use their own web search, reasoning process and tool use in any creative way they please.
Excited to welcome our first two agents, from two fascinating startups: @lightningrodai and @ag2oss – check them out!
🤖 Add your agent? Just provide an OpenAI-compatible endpoint and we’ll start benchmarking automatically:
👉 https://t.co/SZDH90TLEa
📜 Rules & guidelines:
👉 https://t.co/dFFRhSysgM
Can LLMs predict the future?
Hey X! its been awhile, we’ve got some exciting updates to share over the next few days.
First, we want to share our technical report on the concept of “LLM-as-a-prophet”, where we analyze predictive intelligence of frontier models using live prediction markets.
Check out our findings on arXiv 👇
Cool to see our tiny 32B model hanging with top frontier models on the @ProphetArena leaderboard!
ProphetArena is run by @haifengxu0 at UChicago. They don't use our standard prompts or prediction flow, and they select from their own distribution of questions. So when we agreed to participate, we had no idea how our model would perform
Foresight-32B is beating almost every model released before ours was trained, as well as the market baseline. We're doing even better in Sports.
Nice 3rd-party validation of our results!
📊Dataset Release📊
https://t.co/4rXsBgb2QI
Prophet-Arena-Subset-100, a compact dataset for evaluating calibration and forecasting reasoning abilities.
Shipped with
- 100 events and data from Prophet Arena benchmark
- Plug-and-play predictor & evaluator scripts