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: Condorsay, a decision-making assistant with help from GPT-3

6 pointsby dfrankowover 3 years ago

4 comments

jimmygrapesover 3 years ago
First it makes a chat thing pop up uninvited, taking up 1&#x2F;4 of my mobile screen and covering up my input and the suggestion drop down.<p>Then I get a list of things I don&#x27;t want to filter by.<p>Then I get this:<p>&gt; We&#x27;re glad you&#x27;re here! In order to continue making better decisions, please login with a Google account by clicking the button below. We&#x27;ll take you right back to your decision once you do!<p>Nope nope nope.
评论 #28859431 未加载
superasnover 3 years ago
All I got was this after 15th question:<p><i>Sorry, something unexpected happened. It wasn&#x27;t your fault. But, it may be temporary. Try refreshing this page. If the error persists, contact help@condorsay.com.</i><p>Not cool as I was forced to sign up with Google and wasted almost 10 minutes doing it.
ano88888over 3 years ago
it is quite laborious. Asking me question after question and there is more than 70 questions. I gave up after clicking 10 of them
dfrankowover 3 years ago
Hi HN.<p>I&#x27;m Dan, CTO at Condorsay. We&#x27;ve built a tool that helps you make decisions, alone or with others.<p>* Summary<p>The short version of our tool:<p>- pick a goal (something to decide)<p>- pick factors important to the decision (helped by GPT-3)<p>- pick options (helped by GPT-3)<p>- use pairwise ranking to learn what you or a group think of the options<p>- see the results, including text notes (if you made the decision with others) and dissenters (people who disagree with the group)<p>NOTE: it does require a Google login to get past the &quot;factors&quot; screen. However, you get 5 decisions for free, so you can do everything for free. I read login makes HN cranky, but that is how our tool works. (A decision has to be owned by a user in the DB. Also, we are protecting against someone burning tons of money on GPT-3 calls.) Please don&#x27;t be cranky.<p>* Motivation<p>We believe that decision-making could be improved by a tool that puts structure around it.<p>Some benefits:<p>- clarity: structure and record your decisions, alone or in a group<p>- focus: force hard choices with pairwise comparison<p>- revealed preferences: you actually don&#x27;t always know what you think, but you learn through the simplest possible gut-level calls (pairwise choices). By the end, the results make sense, even if they aren&#x27;t what you thought at first.<p>Further benefits if you’re making a decision in a group:<p>- alignment: get a group of people on the same page, by having the most important discussions quickly (i.e., where people disagree)<p>- independence: express your preferences before you see anyone else’s, to avoid information cascade<p>- asynchronicity: coordinate people in our increasingly remote-work world, mobile-friendly<p>Our scoring is straight-up Analytic Hierarchy Process (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Analytic_hierarchy_process" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Analytic_hierarchy_process</a>). For AHP in Python, we use the lovely <a href="https:&#x2F;&#x2F;github.com&#x2F;PhilipGriffith&#x2F;AHPy" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PhilipGriffith&#x2F;AHPy</a>.<p>Happy to talk about paired-choice decision-making algorithms, AHP, GPT-3, or other TLAs (three-letter acronyms).<p>* Background<p>James, Andrew, and I worked on Barometer, an effort to use Facebook measurement to promote or demote ads to help defeat Trump in 2020. Even in that effort, we picked what to do next in various different ad-hoc ways. James thought, &quot;Why isn&#x27;t there a good tool for this?&quot; and convinced us we should try to build it.<p>I look forward to your feedback and questions. Please don&#x27;t be cranky.
评论 #28858785 未加载