Manitcor

We are moving over to new explorer stay tuned #ROKO $ROKO NETWORK

pliny.gg just got a fresh makeover 💄💅 lots of new interactivity and hidden features! had a ton of fun co-designing with the new models over the weekend. see if you can find all the 🥚🐇!

one must imagine Sisyphus happy when the boulder resets

a single word in a prompt can poison the well of possibilities

@_b0dh1 models that prevent security researchers from doing their work are bad, actually

Every blockchain answers "who owns what." Almost none can answer "who went first — and can you prove it?" We just did. On Bitcoin. Verifiable by anyone. Time is the thing crypto quietly fakes. block.timestamp is nudgeable. Order inside a block goes to whoever pays the most gas. Every chain trusts someone's clock. ROKO was built for one thing: make time verifiable instead of trusted. So here's proof, not a promise. 8 real blocks from the live ROKO testnet — each carrying its timestamp and ordering — sealed into one cryptographic root and anchored into Bitcoin. On-chain. Checkable by anyone on Earth: mempool.space/signet/tx/bbc3… Look at the OP_RETURN yourself. It says RKO1. That's ROKO's commitment, now witnessed by Bitcoin's proof-of-work. Change one bit of any block and the proof shatters. You don't take our word for the order — you check it. And there's a war in Bitcoin right now over what belongs on-chain. 42 bytes or unlimited. Core or Knots. $ROKO doesn't ask you to pick a side. Our commitment is 45 bytes — it lands under the old limit, the new one, and Knots' strictest policy alike. We don't bloat the chain. We write one hash. Here's the part people miss: Bitcoin is the permanence layer. ROKO is the time layer. Not competitors — complementary. One makes things impossible to erase. The other makes when and in what order impossible to fake. Where this goes: markets, machines, and AI agents that share a clock they don't have to trust. Where "who went first" is something you verify, not something you're told. Fair ordering. Provable audit trails. Honest provenance. One substrate. We're not trying to be another L1 in the pile. We're building the way the industry expresses verifiable time — the reference for a category that doesn't have one yet. TLS did it for encryption. Something has to do it for time. Everything above is checkable. That's the point. Don't trust. Verify. → roko-explorer.ntfork.com The clock is the consensus. Come look.

can I say something without everyone getting mad?

@CodeByNZ yes, glad i learned before this tbh

Be honest, can you CODE without AI...?

so few do this because its legit a bit hard

ok fable, show me what you got ...or not

@weswinder already have been

stop using loops start using queues trust me

@plainionist aiwg.io

In your agentic coding workflow, what is the one tool that gives you the most leverage? 🤔

what happens when you prompt Fable to use up an entire week's worth of Claude Max 20x credits at once? as it turns out, you end up with >50 playable games! 🤯 I realized that I had a Claude account which I hadn't used all week and its reset was the next day, so I wrote a one-shot prompt to parallelize dozens of Fable-5 agents and encouraged them to spend my entire weekly usage as fast as possible 🙃 the results were really impressive! everything was nice to look at, fun to play, and worked perfectly. many of the games bring a heavy dose of nostalgia for the Flash Games era hard to imagine this being possible 6-12 months ago, especially from a single prompt! PROMPT: "ok i have a challenge for you! i need to use up my anthropic credits for the week in one day, and ONLY on fable 5!! lets see if we can't build something that leverages our claude code cli to build a bunch of epic demos for fable 5 of all sorts of different complex cool creative projects! leverage fable 5's full creativity and intelligence until our credits are gone!! tons of stuff in parallel!"

@plainionist All of my stuff is heavily spec driven (pre-dates openspec by quite some time). Extremely powerful pattern. Gives you a way to front load decisions and significantly reduces both hallucination and going off track, still gets lazy at times though.

Anyone already using OpenSpec? Curious about your experience. 🤔 openspec.dev

@plainionist part of the aiwg.io ecosystem, working on orchestrate/collab patterns. The sandbox is almost ready, then its just about wiring control through

@Manitcor which would be? 🤔

I thought loop engineering was about the agent team. But I feel like I am the one stuck in an endless loop: writing tickets, reviewing specs, analyzing what to improve next, constantly context-switching between different tickets. Exhausting. 🤷‍♂️

🚨 JAILBREAK ALERT 🚨 SPACEXAI: PWNED 🫡 GROK-4.5: LIBERATED 🚀 Our fren Grok has gotten some upgrades!! 🤗 1.5 TRILLION parameters (triple what Grok-3 had) and apparently on-par with the likes of Opus-4.8 and GPT-5.5 on coding performance! The guardrails have gotten a little update too, but with a few tricks like specific academic/educational/safety reframing and a bit of gradual escalation, everything opens right up ⛓️‍💥 We've got full breaks for meth synthesis, IED construction with ANFO, a ricin extraction protocol, and a Remote Access Trojan script! Information wants to be free 🙌 gg

is everyone enjoying Fable?

6 months of Claude Max 20x, on us. We're expanding Claude for Open Source to more of the community. If you're a maintainer, a core contributor, someone landing PRs across the ecosystem, or someone keeping a critical package alive, apply today!

@Timur_Yessenov @plainionist You still do unit and integration BDD significantly cuts into UAT and its surprises. Does so with an analyst and a dev instead of a room/server full of QA.

@plainionist I like BDD for acceptance, but I’d still keep one lower-level invariant beside it. Given/When/Then says what the user sees. Agents also need “this field never decreases”, “this job is idempotent”, “this webhook can replay”. That’s where happy paths miss bugs.

Hot take: Eventually, all projects will adopt Gherkin/BDD for specifying and verifying acceptance criteria. It tells coding agents how the system should behave, not how it should be built. Clear acceptance criteria without limiting the solution space. Perfect for humans to review the tests and verify their correctness and completeness. 😎