DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

Think Fu

Show HN: Think Fu – Metacognition as a service

50 AI Score
Show_hn other Added Mar 30, 2026

Details

Sector
other
Total Funding
$0
Last Round
$0

About

Hi HN!<p>I&#x27;ve been very unimpressed with how LLMs think when it comes to anything creative. It&#x27;s no surprise - they&#x27;ve been lobotomized by RLHF to be helpful, predictable and consistent - all of these things are counterproductive in a more creative setting.<p>So I&#x27;ve built a little something to help LLMs be less creatively bland and dumb. It&#x27;s called ThinkFu (because I believe creative thinking, when practiced well, is a martial art).<p>Anyway, you can watch a 3-min video demo here: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=x-LQvX105SI" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=x-LQvX105SI</a><p>Or you can just add it to your claude code like this:<p>&#x2F;plugin marketplace add move38studios&#x2F;thinkfu<p>&#x2F;plugin install thinkfu@move38studios-thinkfu<p>You can also explore what&#x27;s happening in the code here: <a href="https:&#x2F;&#x2F;github.com&#x2F;move38studios&#x2F;thinkfu" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;move38studios&#x2F;thinkfu</a><p>The TL;DR is:<p>1. I&#x27;ve collected 200+ &quot;thinking moves&quot; from things like oblique strategies, triz, systems thinking, design thinking etc. and adapted them for LLMs<p>2. I&#x27;ve added a little randomness with variables, so that the total number of moves that you can get is somewhere around 500 billion. Because in creative thinking randomness is a feature not a bug.<p>3. There is a vector search and a tiny LLM router (behind an MCP) that tries to get you the right &quot;thinking move&quot; for whatever your problem may be.<p>Everything runs on cloudflare (still love you guys, despite all the recent issues).<p>Oh, also on first use you can opt in or out of sending the anonymized ratings back to my endpoint. The idea is that the LLM (or user) can rate whether a certain move was productive or not in a certain context.<p>If I collect enough ratings, I&#x27;ll finetune a custom LLM for the router and I think routing will get better as a result.<p>Hope y&#x27;all find it interesting!<p>I&#x27;d be happy to answer questions and get bug reports and PR requests and what not. It&#x27;s a tiny experiment - but if it works it could be fun to scale with the community.

AI Score Reasoning

Think Fu is an innovative 'metacognition' tool addressing the creative limitations of RLHF-trained LLMs, leveraging timely tech like the Model Context Protocol (MCP). While the conceptual approach is clever and developer-friendly, it currently functions more as a niche utility with low barriers to entry and significant platform dependency on the Anthropic ecosystem.

Source

Show_hn — View original →