TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Ask LLMs to predict anything based on news

25 pointsby artembugara8 months ago
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.<p>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].<p>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 chicken for dinner tonight?“). But we’re intentionally NOT stopping it from answering any question, so fire away!<p>What makes it different:<p>- Free to use: Anyone can ask any question about the future that they care about, whether it’s a broad societal trend or a specific personal decision.<p>- Transparent: The tool is based on a proven reasoning model and provides links to all sources. You can see its track record on public predictions [3].<p>- Open-source: We’ve released a simplified open-source version [4] to give people a better sense of how it works.<p>Why we built this: We’re forecasting nerds and loved the idea behind the Berkeley paper. Friends and family kept asking us to make predictions for them, so we figured we’d build a frontend around the system so they could use it themselves. Don’t use it to decide where to buy a house or anything serious. But we think it’s a good starting place when doing research. AI Predict tackles prediction questions using transparent, objective reasoning (mostly Bayesian analysis) and links to all its news sources.<p>We’d love for the HN community to try it out and share feedback (predictions@joinatlas.ai). Let us know what you think!<p>[0] <a href="https:&#x2F;&#x2F;aipredict.fun&#x2F;" rel="nofollow">https:&#x2F;&#x2F;aipredict.fun&#x2F;</a><p>[1] <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2402.18563" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2402.18563</a><p>[2] <a href="https:&#x2F;&#x2F;www.newscatcherapi.com&#x2F;">https:&#x2F;&#x2F;www.newscatcherapi.com&#x2F;</a><p>[3] <a href="https:&#x2F;&#x2F;docs.google.com&#x2F;spreadsheets&#x2F;d&#x2F;1oPvWlst7sxq2URifFaZ0rMBP2mHmXAzxd0gnWr8AgUQ" rel="nofollow">https:&#x2F;&#x2F;docs.google.com&#x2F;spreadsheets&#x2F;d&#x2F;1oPvWlst7sxq2URifFaZ0...</a><p>[4] <a href="https:&#x2F;&#x2F;github.com&#x2F;getdatachimp&#x2F;llm-superforecaster">https:&#x2F;&#x2F;github.com&#x2F;getdatachimp&#x2F;llm-superforecaster</a>

4 comments

user0529198 months ago
Atlas founder here. Happy to answer any questions people have about the tool!
评论 #41523407 未加载
jmartens8 months ago
Can you provide an example of the type of question that comes back with a reasonable prediction? So far, I&#x27;ve tried 3 times, and the answer each time was something along the lines of [prediction will be true] if [they do the thing that makes the prediction true] which is not useful.
评论 #41523195 未加载
niles8 months ago
I was hoping for a tool that would reference &quot;all&quot; news, mainly historical news, and give some reasoning based on past patterns. My query on Kamala does not seem to factor in the news from just before the last Trump win over Hillary and how that time period contributed to a surprise win. It also doesn&#x27;t seem to incorporate Regan, or past high inflation periods and how those news stories influenced the elections of the time.<p>It seems like this is a tool that &quot;if you could read all the news of today, what would your gut tell you&quot;, and that is helpful but not thorough.<p>For example, can you apply the cureent reasoning to news articles from previous time periods and use the prediction on a past result. Would your prediction be accurate? If no, maybe re-reason.<p><a href="https:&#x2F;&#x2F;aipredict.fun&#x2F;prediction&#x2F;1074cf90-c818-44fd-be0b-c0091457957e" rel="nofollow">https:&#x2F;&#x2F;aipredict.fun&#x2F;prediction&#x2F;1074cf90-c818-44fd-be0b-c00...</a>
评论 #41524795 未加载
sturza8 months ago
Hard to launch today with gpt-o1 getting attention.