Show HN: I RL-trained an agent that trains models with RL (for –$1.3k)

<!-- SC_OFF --><div class="md"><p>I've been working on MDA (Modular Dynamic Architecture), an online associative memory system for LLMs. Here's what I learned building it.</p>

<a href="https://news.ycombinator.com/item?id=47536761">Comments</a>

<a href="https://news.ycombinator.com/item?id=49189075">Comments</a>

I trained a live RL agent inside a pixel platformer you can play against on a desktop browser (needs a keyboard or a controller):<p><a

<a href="https://news.ycombinator.com/item?id=50151059">Comments</a>

<!-- SC_OFF --><div class="md"><p><a href="https://github.com/SomeoneAlt-86/open-mythos">https://github.com/SomeoneAlt-86/open-mythos</a><br /> Claude just previewed their Mythos