Trained an LLM to predict "What will Trump do?"
Hey HN! I RL-tuned an open-source LLM (gpt-oss-120b — 120B MoE, but only 5.1B active params) to predict "What will Trump do?" in any situation, trained on nothing but public news collected automatically from search queries. The trained model beats GPT-5, and both dataset and trained model are open sourced. Data generation: Generated 2,108 binary forecasting questions from just a search query and a date range using the Lightning Rod SDK (https://github.com/lightning-rod-labs/lightningrod-python-sd...). Questions are generated from historic news articles — like "Will Trump…
Trained an LLM to predict "What will Trump do?" launched on February 20, 2026 with 10 votes, #1,046 of 16,627 launches that month and more than 90% of that year's launches.
In plain words
This project fine-tunes an open-source 120-billion-parameter language model to forecast political outcomes, specifically predicting Trump's actions in various scenarios. The model was trained on 2,108 automatically generated forecasting questions derived from historical news articles, with answers determined by what actually occurred. Both the dataset and trained model are publicly available on Hugging Face. The system uses reinforcement learning optimization rather than manual annotation, making the entire pipeline automated from data generation through model training.
written from the facts on this page · September 2026
From the sources
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Starting from nothing but 5 search queries, we used the Lightning Rod SDK to automatically generate 2,108 forecasting questions from news articles, label them using real outcomes, and train this model via RL. No expertise required. No manual labeling. No domain-specific engineering. The result beats GPT-5 on held-out questions. You can do this in any domain — just change the search queries. See how we built the dataset . This repo contains a LoRA adapter for gpt-oss-120b . A standalone merge.py script is included to merge it into a full model. Evaluated on 682 held-out test questions under two conditions: with news context, and without context (question only). The no-context condition…from huggingface.co
In the maker’s words, at launch
Hey HN! I RL-tuned an open-source LLM (gpt-oss-120b — 120B MoE, but only 5.1B active params) to predict "What will Trump do?" in any situation, trained on nothing but public news collected automatically from search queries. The trained model beats GPT-5, and both dataset and trained model are open sourced. Data…
Does a similar job
all alternatives →- WSWeb search using a ChatGPT-like model that can cite its sources2022 · beta.sayhello.so · ▲318
We’ve trained a generative AI model to browse the web and answer questions/retrieve code snippets directly. Unlike ChatGPT, it has access to primary sources and is able to cite them when you hover over an answer (click on the text to go to the source being cited). We also show regular Bing results side-by-side with our AI answer. The model is an 11-billion parameter T5-derivative that has been fine-tuned on feedback given on hundreds of thousands of searches done (anonymously) on our platform. Giving the model web access lessens its burden to need to store a snapshot of human knowledge…
- ALAsk LLMs to predict anything based on news2024 · aipredict.fun · ▲25
Hi HN! We partnered with the Atlas team to build a tool called AI Predict [0] that allows anyone to ask any question about the future and get a thoroughly researched, AI-generated prediction on how likely it is to be true. How it works: Atlas replicated a Berkeley paper [1] that showed LLMs could make predictions as accurate as the crowd. We’re using a mix of models from OpenAI and Anthropic, with information retrieval powered by NewsCatcher [2]. The system is live and fully functional, though it might struggle with hyper-local questions outside of the public domain (e.g., “Will I have…
- ALAI-Less Hacker News2023 · save-buffer.github.io · ▲69
Lately I've felt exhausted due to the deluge of AI/GPT posts on hacker news, and have seen similar grumblings. I threw together this frontend that filters out anything with the phrases AI, LLM, GPT, or LLaMa for use until the hype dies down a bit. Before anyone asks, yes I did try to use ChatGPT to help, and while the code it provided was helpful, it needed some heavy bug-fixing. Edit: One other note I forgot to mention. The favicon is generated by Stable Diffusion, I asked it to generate an "Aritificial Intelligence Favicon", and then I added the red circle with line through it.
Cultivate Conversations - Return of the Trump2015 · cultivatelabs.com · ▲55Discussing prediction markets for the GOP nomination
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com