پن کیا گیا ٹویٹ
Lulox 🐱🇦🇷
13.2K posts
Lulox 🐱🇦🇷
@LuloxDev
🪷 Techno-optimist · Web3 Architect & Automation Builder Cardano & Midnight focused
Buenos Aires شامل ہوئے Temmuz 2022
2.3K فالونگ1.3K فالوورز
English
English
BREAKING NEWS:
MIDNIGHT BRIDGE CONTROVERSY ERUPTS🙀🙀🙀
@ItsDave_ADA has ignited controversy by claiming that bridging assets to @MidnightNtwrk is currently one-way, warning that once funds are moved, they could be permanently locked. He argues this design could drain liquidity from Cardano and raises questions about staking rewards and the broader ecosystem, even criticizing Midnight’s current capabilities and approach.
Developers have pushed back, calling these claims false and premature. They clarify that no public bridge is live yet, as the network is still in early testing, and emphasize that once bridging is operational, users will be able to move assets both ways.
English
🦀 ZeroClaw v0.6.8
🚀 tui: remove OAuth/Browser auth methods, expand onboarding screens
Zero overhead. Zero compromise. 100% Rust.
#zeroclaw #rust #ai #opensource
github.com/zeroclaw-labs/…
English
@Web3Kristel Yeah, add pokemons to @MidnightCitySim please!
@MidnightNtwrk @midnightfdn @IOHK_Charles
English
@plainionist What's the traditional way? Forking someone else's code and changing the logo?
English
Lulox 🐱🇦🇷 ری ٹویٹ کیا
Getting started with @MidnightNtwrk?
Here’s all the info you need from our Head of Product @Ian_LaceProduct
English
@NinjaSinEspera @feregri_no Gente que quiere una web que se edite como un blog
Español
@LuloxDev @feregri_no Quien va a usar wordpress hoy en dia? Aparte de gente desinformada
Español
Me da una tristeza tremenda de que ya no hablemos se si PHP está muerto. La IA le quitó el sabor a la vida.
Español
The #1 criticism I've received about the self-improving multi-agent framework is that you can't control the agents' outputs.
So I built a “Subconscious agent.”
Inspired by @karpathy’s autoresearch, it’s an LLM process that continuously looks for useful problems to solve.
All day long it contextualizes data, connects ideas, and stress-tests assumptions before anything reaches the main agent.
Once the Subconscious has a tested good idea, it brings it to the Main agent to be pressure-tested further.
The flow looks like this:
- [IDEA] Subconscious surfaces a promising idea
- [CHALLENGE] Main agent attacks it, questions it, and asks for proof
- [DEFEND] Subconscious strengthens the case
- [REVISE] Subconscious improves the idea based on feedback
- [REJECT] Main agent kills weak ideas
- [ACCEPT] Main agent approves ideas worth implementing
- [SHELVE] rejected ideas get logged for future learning
Hard rules:
- max 3 challenge rounds
- every idea needs evidence and reasoning
- every implementation runs in a sandbox
The two agents will go back and forth until the idea is either accepted or rejected. This runs all day long.
I’m using Hermes agent frame for both agents, the Subconscious has its own profile to concentrate on surfacing ideas 24/7.
The Subconscious runs on a local Qwen3.5 9B model, while the main agent uses ChatGPT 5.4 mini. If you don’t have a local LLM, OpenRouter should work too.
The goal is simple: more magic, less noise.
If this gets traction, I’ll share the full setup in an article.
Graeme@gkisokay
The 'Super Self-Improving Multi-Agent Framework' for your Hermes or OpenClaw agent. The article below outlines how Hermes can watch over your Openclaw agent, so this example uses Hermes as the main agent. This idea is interchangeable based on preference. How it works: Agent 1 (Hermes) - The main agent: who operates your workflows, and who you have in the top hierarchy of agents. For simplicity, it also runs the workflows using its persistent memory and self-improving skills. Agent 2 (Hermes) - Main's Supervisor agent: who monitors the entire system, reading operations and failure logs, searches for bugs, solutions, then brings them to... Agent 3 (OpenClaw) - External Supervisor agent: who also monitors the Hermes system, and searches for issues and solutions. Multiple times per day, Agent 2 audits the system, finds errors, stale jobs, etc, proposes a fix, then tags Agent 3. Agent 3 audits the system, reads Agent 2's summary, and verifies the problem and solution. Together, they go back and forth in a dedicated channel until they find a coded solution to the problem. If it's a low-risk fix, it auto-fixes it. If it's high-risk, it's raised to Agent 1 for approval via the owner (me). The first goal is never to have to worry that the system is operating correctly. The second goal is to have two separate agents focused on recommending improvements to the system. Ideally, there are no bugs to fix, and you can have them focus on making meaningful improvements to your workflows over time. This is the basic workflow for monitoring, but you can extrapolate this framework to many more use cases. What's [redacted]? I'm cooking up something to continue working toward my goal of building more sentience in my agents. I will share more soon. Let me know in the comments if this works for you. I'll create a fleshed-out article if you are interested.
English
What is a reasonable budget for Cardano influencers for 1 year?
English
@Hesamation Such a great company culture! Would love to meet people from @Kimi_Moonshot team!
English
> be Moonshot
> 300 employees, avg age <30
> no departments, no titles, no KPIs
> so many former CEOs and founders
> 80% of company are introverts
> everyone keeps slippers under desk
> no bureaucratic culture
> some mornings you walk in not knowing what to do
> no one tells you if you’re doing well
> doesn’t care about job background, care about “taste”
> “if you ranked AI companies by employees who play instruments, kimi wins”
Rui Ma@ruima
English
@ptorrecillas I'm interested but based on Argentina. Got my Italian citizenship so I could travel there when the product is done to celebrate. Ah, y hablo español, por cierto.
English
I'm looking for extremely AI-pilled developers that want to build a very ambitious AI product.
Remote but ideally based in Spain, Portugal or somewhere with easy access to Madrid so we can see each other from time to time.
DM if interested 🙏
English
Lulox 🐱🇦🇷 ری ٹویٹ کیا
An update on our engagement with @Mastercard.
While Cardano was not included in the initial cohort of 85 launch partners, @emurgo_io has been actively engaging with their APAC team to change that and ensure our ecosystem is represented.
Following a leadership transition at Mastercard APAC —where our primary contact moved to EY — we have successfully connected with his successors. They were excited to speak with us and I am pleased to share we are now in the Qualification Stage for the Global Crypto Partner Program.
With the continued support of the Cardano community, I am confident in a positive outcome.
This important:
Please like and share to show @Mastercard the strength of our ecosystem. Mastercard is a global firm.. we need to show them that our inclusion into their Partner Program will make a difference to them. Surely this is an initiative the entire Cardano ecosystem can support! #cardano86
Let's go!!!
#cardano #mastercard @Cardano_CF @Cardano @IOGroup @midnightfdn
English
Lulox 🐱🇦🇷 ری ٹویٹ کیا
Hermes Agent 0.6.0 quietly added one feature most people are going to miss.
Exportable agent profiles.
You can build an agent once.
Package the setup.
Move it to another machine.
Share it with your team.
Reuse it across projects instantly.
That turns Hermes from a tool into a deployable agent platform. 📦
English
@nicoproducto El P2E era un sueño hermoso del que nadie quería despertar, lastima que le faltaban tokenomics sostenibles
Español
Que momento de delirio colectivo que fue Axie
teKa 🥶@teKa088
2021: 500 personas compitiendo por una beca de Axie para ganar $300/mes "Por favor déjame jugar" "Soy responsable" "Tengo experiencia en juegos" 2025: "Por favor jugá nuestro juego muerto" Cómo cambian las cosas. De rogar por axies a que rueguen que los toque.
Español
@GameChangerOk @ChileStakepo Does it support Midnight, or just Cardano? Can it be used for testing and preprod?
English
Nunca ocurrió
S1X3L4@Six3la__
Voy a andar probando este tema del build in public a ver como corre
Español
This is what I was trying to build!
0xMarioNawfal@RoundtableSpace
THIS GUY BUILT A DESKTOP PET CLAUDE THAT WATCHES YOUR SCREEN IN REAL TIME
English
@gemajuarezallen @INCAA_Argentina Yo se los hago por la mitad de precio
Español
Lo ridículo que es que el @INCAA_Argentina le pague 250,000 dólares a una empresa para mantener su plataforma online y haya desarticulado todo el fomento de cine.
¿A quién le entra en la cabeza? ¿Para qué carajos queremos una plataforma?
Español