Robster

📣Wiki Announcement📣 552 days after the debut of the original @MoonsamaNFT Wiki, we're excited to announce that the all-new community wiki is NOW LIVE! 🔥 Read on for a chance to win an EXO! 🏃‍♀️🏆 📘 wiki.moonsama.com

@ivanfioravanti Nope 👎

Claude Desktop is so much better than ChatGPT 😱 It’s night and day!

@thsottiaux Really dislike it, no to this tibo

Do people like this? We don't do this for codex because it exists to help you and it's important that you remain the owner and accountable for your work without AI taking credit. At the same time it does mean that you can't trace how popular codex is among repos.

Anyone can join Dremica this Sunday from 2PM UTC Come give it a spin and let us know what you think. Here is how👇 wiki.dremica.com/Guides/NewPlay…

There are two important changes coming this week. 🚨 - import fees are now zero and all your previously crafted items can be unlocked freely 👇portal.moonsama.com - EXO requirements changing as a result anyone with Moonsama account can play Dremica wiki.dremica.com/en/PatchNotes/…

@SimeonGarratt @ihtesham2005 Thanks for saving me the effort 👌

Looked through the Superpowers repo. Here's my take. It's markdown files telling Claude to please follow a process. TDD is a skill file. Code review is a skill file. The agent reads them and hopefully complies. There's no enforcement. When Claude drifts or hallucinates a passing test, the whole thing falls apart quietly and you won't know until you check. 40k stars because it's easy to install. That's a distribution win not a technical one. The ceiling is the problem. It makes a good LLM slightly more disciplined. It can't make a wrong answer correct

🚨 Holy shit...A developer on GitHub just built a full development methodology for AI coding agents and it has 40.9K stars on GitHub. It's called Superpowers, and it completely changes how your AI agent writes code. Right now, most people fire up Claude Code or Codex and just… let it go. The agent guesses what you want, writes code before understanding the problem, skips tests, and produces spaghetti you have to babysit. Superpowers fixes all of that. Here's what happens when you install it: → Before writing a single line, the agent stops and brainstorms with you. It asks what you're actually trying to build, refines the spec through questions, and shows it to you in chunks short enough to read. → Once you approve the design, it creates an implementation plan so detailed that "an enthusiastic junior engineer with poor taste and no judgement" could follow it. → Then it launches subagent-driven development. Fresh subagents per task. Two-stage code review after each one (spec compliance, then code quality). The agent can run autonomously for hours without deviating from your plan. → It enforces true test-driven development. Write failing test → watch it fail → write minimal code → watch it pass → commit. It literally deletes code written before tests. → When tasks are done, it verifies everything, presents options (merge, PR, keep, discard), and cleans up. The philosophy is brutal: systematic over ad-hoc. Evidence over claims. Complexity reduction. Verify before declaring success. Works with Claude Code (plugin install), Codex, and OpenCode. This isn't a prompt template. It's an entire operating system for how AI agents should build software. 100% Opensource. MIT License.

@sama It's incredible 🫡

The Codex team are hardcore builders and it really comes through in what they create. No surprise all the hardcore builders I know have switched to Codex. Usage of Codex is growing very fast:

@VladGersh @Pranit Why not codex it's fantastic 👌

@Pranit they know none of us are cancelling lol. where else am I going, back to gpt? I'd rather just accept the quiet downgrade and pretend I didn't notice

Anthropic just pulled the oldest trick in SaaS pricing. I pay $200/mo for Claude Max. My limits have been noticeably worse this past week. Now they announce 2x off-peak usage for two weeks. Sounds generous. But here’s what actually happens: limits quietly drop, a temporary 2x makes the reduced limit feel normal, the promo ends, and you’re left at a baseline lower than where you started. You just didn’t notice the downgrade because the 2x absorbed the transition. These AI plans are massively subsidized. The raw compute behind a heavy user costs multiples of the subscription price. Every move like this is the subsidy quietly correcting. Very sneaky, Anthropic.

Dremica updates are out, just in time for tomorrow 2 PM UTC.🕑 - 3 new armour sets from wild mobs - New Bastion Signet rings💍 - Whispers added: click name in chat - Right-click chat menu + major performance optimisations Check the full patch notes 👇 wiki.dremica.com/en/PatchNotes/…

During Carnage players can spend $SAMA to buy buffs or unlock items from previous sessions. These tokens are burnt forever. 🔥Recently these accumulated 6 473 280 tokens were taken out of circulation.👇 etherscan.io/tx/0xc1b894a55…

@kr0der X high mostly 😅

what level of reasoning are you using and finding success with for GPT 5.4? are we still spamming High or is Medium the new meta?

@thsottiaux Thank you - yes it's been a real issue today for a few hours and my limits have nearly all been used up in one day it can't be correct 😔.

Happy Monday, there are reports of codex hanging for some users where it is not responsive after sending a request and the team is investigating.

@Teknium @xdotli Absolutely disagree. Codex is 👑

@xdotli I totally agree

openai is now * way behind claude in terms of single model capability (you can use opus 4.6 for everything, not xxx-codex) * behind claude in terms of coding (am i the only one who are often confused by the output of codex?) * behind google in distribution (gemini is my driver)

@DremicaOfficial Ready to heal the gang 🪄🔥

Dremica updates are out, come and join us tomorrow 2 PM UTC.🕑 - Wand's ability are self-castable with new hotkeys -small gold coins and junk items drop from mobs Check the full patch notes 👇 wiki.dremica.com/en/PatchNotes/…

136 players decided to show up for Carnage which is a new record since Carnage 2.0 started 🔥 We are seeing massive amounts of resources being being consumed by crafting and purchasing items. Check the leaderboard here👇portal.moonsama.com/dremica?tab=le…

@DremicaOfficial 🪄

Healing is coming🪄 Dremica updates are out, just in time for tomorrow 2 PM UTC.🕑 - Elm/Ashen/Moonstone Wands: Rejuvenate (heal over time), Holy Touch (heal), Arcane Beam ( slow) - Bow/Sword ability dmg increased Check the full patch notes 👇 wiki.dremica.com/en/PatchNotes/…

@filippkowalski Nope

I bet that if a Claude Code or Codex sub was $1k/m or $2k/m instead of $200/m most would still pay. The ROI is too good

@Aaronbennett I'm not good with coffee anymore, it's strange because I increase my anxiety and also dislike the acidity of it. Whereas enjoying nootropic teas with some caffeine and adding creatine is this biggest hack right now. Rapid processing, expanded working memory and calm focus 🙏

Been totally off caffeine for over 2 weeks now Have noticed 0 positive benefits Fascinating Does it take longer or is this a scam

@thekitze Absolutely not ha. Codex 👑 and opus is a nice pair assistant along with Gemini.

claude > codex for openclaw, don't @ me