ethan /entropy

A $100/mo subscription to ikigai that just might change your life forever this lil guy’s become the connective tissue for many great things lately

@pwnies 🥵

A bunch of people were asking how I made the effect for the "renderaissance" style page I made previously. Here's a full walkthrough of creating that depth / dynamic lighting effect for the web. Interactive version: html.non.io/tarot/

So glad I touched copious amounts of grass this past weekend, cause it’s gonna be a long week of building 🧱

@pwnies @MeshyAI send me a invite, i got raccoon skins to gen up

What we built over the July 4th weekend with Fable: PromptKnight. A battle royale game where instead of buying skins, you prompt them. If you win the match, you keep your skin, otherwise it gets added to the random skin pool. Uses @MeshyAI to create the characters.

@jordanrstout @theo also had this issue, hand rolling all the subwork out in another session ugh

I just asked mid session in /btw if I can instruct sub agent use to be fable on high effort instead of main thread since it was on xhigh and it said there’s no effort changing when calling sub agents. I hope that’s not true bc that’s whack lol. Was hoping to let main agent be xhigh and ensure all work is delegated to lower ones and ensure sub agents responses are small.

I've been getting a TON done with Fable today and I'm not hitting rate limits. Wanted to share some tips on how I'm doing that 1. I only use Fable on "high" effort for now. xhigh is token hungry. max/extra is a furnace with worse outputs than lower options imo 2. I taught Claude Code how to use Codex as a fallback for lots of implementation tasks. GPT-5.5 is incredibly steerable, and Fable can learn how to steer it 3. I wrote up a big section in my CLAUDE[.]md on how to prioritize different models for different work when orchestrating workflows and subagents 4. Things that are unnecessarily token hungry (computer use, codebase analysis, etc), I do with other models and report results back to Fable

@douglasfugazi @claudeai completely 👍

@entropy_eq @claudeai is it free?

Upgrading your @claudeai with an auto-learning brain has never been easier 🧠 Drop this link in a session and enjoy never having to re-explain yourself again github.com/entropyeq/karp…

Serendipity ✨

My track record of good timing with Fable-related usage resets is bonkers Guess I’m not touching grass after all 🌱

@mattpocockuk It’s mind-blowing to see the loops compound and the friction decrease progressively 🙌 If you have your system take a look at mine, I’ll bet there are some good nuggets to pull in for hardening and tightening the rails.

Can confirm that this is the best decision for my business I've made in a long time Being able to plan courses in collaboration with an agent that understands my entire business context feels ridiculous I can just say things like: - "pull up what my students think about autocompact" - "Is this section missing any major talking points" - "What problems did people have with this section during the last cohort" - "What are people excited to learn right now" Nucking futs

Fable 5 is back.

@joseph_mugen facts, everyone needs to ask themselves if they spent more personal effort actually building or just framing for that post before they hit send

@entropy_eq you don't have to be loud to be knowledgeable

Very very few people who are vocal about their AI use are actually knowledgable enough to be speaking on it Productivity engagement farming theater out here Dunning-Kruger effect go brrr

@NotionHQ Ok sick, very into this as my default Claude artifact format has been html lately

New block in Notion: HTML. Build interactive HTML right on your Notion page. Ask AI to turn your content into interactive explainers, prototypes, or diagrams. Share with your team to use and tinker together.

goodbye & good riddance to the Chat tab in Claude, excellent update 🤌

@OpenSoftwareCo July just doesn’t have the same ring, good work. plus can you imagine the rebrand lift ooooof

@entropy_eq the marketer cut it quite close on this one, we almost had to change our name

Meet June, private AI on your Mac. June bundles it all in one: - An agent + chat - Voice dictation into any app - Automated meeting notes - Private OSS & anonymized frontier models Files, context, and data stay yours. Open source. MIT. Try it: opensoftware.co/june

By the skin of my teeth

Hermes stop, you flatter me too much 🪽🥲 Figured out a rail for Hermes to safely interact with my wiki, despite not being able to bootstrap the same way I do Claude Want my brain system? It's free because we all deserve better process, agents included. github.com/entropyeq/karp…