Ask LLMs to predict anything based on news
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…
Ask LLMs to predict anything based on news launched on September 12, 2024 with 25 votes, #714 of 5,281 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
AI Predict is a free tool that generates predictions about future events based on user questions. It uses language models from OpenAI and Anthropic combined with news data retrieval to estimate the likelihood of outcomes. The system was developed in partnership with Atlas and is based on research showing that LLMs can make predictions comparable to crowd forecasting. It handles broad questions about societal trends and specific scenarios, though it may struggle with highly localized or private matters outside public information.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
Humans vs LLMs2025 · aipageready.com · ▲138Hi HN, We just launched [AI Page Ready](https://aipageready.com) — a tool to check if your web pages are discoverable and understandable by AI tools like ChatGPT, Claude, Gemini, and Perplexity. It runs 40+ checks across six areas: Discoverability & Crawlability, Structured Data & Semantics, Content Quality, Answer-Ready Formatting, Accessibility & Rendering, and Deep AI LLM-specific checks. Would love your feedback — especially if you work in eCommerce, SEO, content, SaaS, or are trying to get traffic from AI tools. (Also open to ideas on what else to add to the tool!)
Trained an LLM to predict "What will Trump do?"Feb 2026 · huggingface.co · ▲10Hey 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…
LLM ReadyJan 2026 · llmready.site · ▲3AI systems learn from public explanations across the web. LLM Ready is a diagnostic tool that estimates how consistently AI systems can understand and describe a product based on public information. It does not track live AI responses, rankings, or prompts. It focuses on structural clarity, reference sources, documentation, community discussions, and educational content. I built this after seeing many early products misrepresented by AI due to missing or fragmented explanations. Feedback is very welcome.
How to use LLMs to generate accurate SQL for real-world data2023 · github.com · ▲21Hey HN, We are Zain and Ashish, founders of Vanna AI. We recently embarked on an experiment to see if large language models (specifically LLMs) could help in generating SQL queries for real-world datasets. We initially started this project as a web app but realized that it was most useful and had broadest applicability as a Python package since you can then incorporate it into an existing workflow (Jupyter notebook, Slackbot, etc). We've had some good success with customer datasets but we've generally heard a lot of skepticism so we decided to write a paper about the methodology we're using…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
