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: PreCog AI – Automatic AI Model Selection for Any Task

61 pointsby ieuanking7 months ago
Hi HN,<p>I&#x27;m one of the co-founders of PreCog AI, a project my friend and I started to make the best AI models more accessible. PreCog AI is a chatbot that automatically picks and answers with the best AI model for whatever task you throw at it.<p>We made PreCog public on Monday and are getting great feedback. Originally built as an internal tool to help our small team reduce costs (paying for various chatbots) and get better AI output, PreCog has helped us so much with our workflow and ideation that we just had to share it.<p>Key Features of PreCog - AI Model Matchmaking: With access to 18 models, PreCog automatically matches your questions with the most fitting AI model based on the task.<p>- Versatile Adaptation: Works with any task, from coding to creative writing, giving you the right tool for the job.<p>-Ongoing Updates: Stay current with AI advancements using the latest LLM leaderboard data (we are constantly adding and changing our leaderboard). See the leaderboard here - <a href="https:&#x2F;&#x2F;precog.ubik.studio&#x2F;leaderboard" rel="nofollow">https:&#x2F;&#x2F;precog.ubik.studio&#x2F;leaderboard</a><p>-Preferred Model Selection: If you have a preferred model, choose it, and PreCog will use that model exclusively to respond.<p>How PreCog Works:<p>PreCog analyzes your query, references the model leaderboard, and then matches your query with the highest-ranked AI for that niche task. Delivering high-quality, task-specific output. PreCog&#x27;s Model Leaderboard ranks AI models through over a million human comparisons, evaluated and presented on an Elo-scale. The dataset used to build the PreCog Leaderboard is from ChatBot Arena by <a href="https:&#x2F;&#x2F;lmarena.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;lmarena.ai&#x2F;</a>. Researchers from UC Berkeley SkyLab and LMSYS developed the battle framework to produce the dataset.<p>I love feedback, questions, and critiques it helps me and my friend develop with the user in mind.<p>You can reach me at anytime at: info@ubik.studio

4 comments

KaoruAoiShiho7 months ago
Do you find that there are a lot of variations and intricacies in deciding which LLM to use? I find it pretty simple to just assume sonnet is best at most coding jobs, o1 best at complicated non-coding tasks, 4o for simple questions that don&#x27;t require planning. and well, tbh that&#x27;s it, no other LLMs are that interesting.
评论 #41938904 未加载
评论 #41939073 未加载
swyx7 months ago
you&#x27;re doing model routing - any thoughts on <a href="https:&#x2F;&#x2F;github.com&#x2F;lm-sys&#x2F;RouteLLM">https:&#x2F;&#x2F;github.com&#x2F;lm-sys&#x2F;RouteLLM</a> and Martian?<p>hope you dont raise funding before you figure out what they haven&#x27;t
评论 #41938286 未加载
dvfjsdhgfv7 months ago
I entered the query but was redirected to a login form. If you are honestly looking for feedback and no leads, unblock the app temporarily for HN. If you are for leads, for sure you will get some if this submission receives enough upvotes, but I wouldn&#x27;t count on many. These days people are not so keen to leaving their data on random websites anymore.
评论 #41938680 未加载
评论 #41938055 未加载
okintheory7 months ago
Ah yes, Minority Report, that story we&#x27;re so eager to repeat.
评论 #41938630 未加载