StefanoDoDev

I share my new gpt to everyone: Code Self Explanator chat.openai.com/g/g-5DoH5Gboo-…

@Hug0_Tr47 @sagfutbol De nuevo, están locos por pasar a Italia

@sagfutbol Para mí 1. Brasil 2. Alemania 3. Argentina 4. Italia 5. Uruguay 6. Francia 7. España 8. Países Bajos 9. Inglaterra 10. Chequia 11. Hungría 12. Portugal 13. Croacia 14. Bélgica 15. Suecia 16. Rusia 17. Chile 18. Dinamarca 19. Paraguay 20. Polonia +

📊🌎 La lista de las 25 mejores selecciones de todos los tiempos según la fuente Perplexity Sport Bible. ¿Qué opinan?

@Paolitolokuu @sagfutbol Menos mal que este año cambiamos de campeón porque estáis insoportables

@sagfutbol Por partes: 1- Argentina va 3ra 2- Uruguay va 6ta/5ta 3- Bélgica ya es más que Checoslovaquia 4- Chile, Paraguay y hasta México son más que Suecia 5- Croacia es más que Suecia también 6- Polonia no es menos que Suecia 7- Rumania no es más que Colombia

@RottenTomatoes Why the background is always blurred?

First look at Dwayne Johnson as Maui in the live-action #Moana. In theaters on July 10.

NVIDIA JUST DROPPED NEMO CLAW TO MAKE OPENCLAW SAFE TO RUN ON YOUR OWN MACHINE. It keeps private files off the cloud, runs fully offline, and adds the security layer local AI agents were missing.

Great!!!😊

Claude Code can run entirely on your local GPU now. Unsloth AI published the complete guide. The setup itself is straightforward - llama.cpp serves Qwen3.5 or GLM-4.7-Flash, one environment variable redirects Claude Code to localhost. But the guide is valuable because of what it explains beyond the setup: Why local inference feels impossibly slow: Claude Code adds an attribution header that breaks KV caching. Every request recomputes the full context. The fix requires editing settings.json - export doesn't work. Why Qwen3.5 outputs seem off: f16 KV cache degrades accuracy, and it's llama.cpp's default. Multiple reports confirm this. Use q8_0 or bf16 instead. Why responses take forever: Thinking mode is great for reasoning but slow for agentic tasks. The guide shows how to disable it. The proof it all works: Claude Code autonomously fine-tuning a model with Unsloth. Start to finish. No API dependency. Fits on 24GB. RTX 4090, Mac unified memory.

🚨BREAKING: You can now run Claude Code for FREE. Here's how to run Claude Code locally (100% free & fully private):

🚨 BREAKING: You can now give your Claude Code infinite memory for free. Claude-Mem is a free open-source plugin to persist memory across Claude sessions. - Up to 95% fewer tokens per session. - 20× more tool calls before context limits. 100% open-source.

Yo no recibí este memo 🫠 Está chévere, en indispensable esta simplificación de evals para los SKILLS, porque a medida que su adopción crece en las organizaciones asegurar su calidad se vuelve indispensable. No pierdan de vista validar los SKILLs que tienen entre ellos.

My Claude script made $2,410 overnight. I built the bot in about 4 hours. Starting capital: $200 Ending balance by morning: $2,410 Average win rate: 68% The idea is simple: 5-minute BTC & ETH micro-arbitrage. The bot scans short prediction markets where YES + NO temporarily drops below $1. When that happens, a small pricing gap appears. The system detects it in real time and enters instantly to capture the spread. Why it works: • markets move fast • manual traders hesitate • bots react in milliseconds Wallet: polymarket.com/profile/0x88f4… Copytrade → t.me/KreoPolyBot?st… By the time most people notice the opportunity, the price has already corrected. Instead of chasing huge wins, the strategy collects many small spreads. Run continuously, those micro-edges compound into real profits. Now it’s just about improving the code, scaling it up, and letting it run.

🚨Breaking: The guy who created Claude Code (@bcherny) just revealed how his team actually trains their AI. One file: CLAUDE.md You place it at the root of your project. Inside it: past mistakes conventions rules Claude reads it every session. The result? The agent improves over time without you touching the code. Every bug that gets fixed becomes a permanent rule. Boris Cherny uses this internally at Anthropic every day. Here’s the template he shared — ready to copy, paste, and adapt. CLAUDE.md Template 1. Plan Mode Default Enter plan mode for any non-trivial task (3+ steps or architectural decisions) If something goes wrong, STOP and re-plan immediately — don’t keep pushing Use plan mode for verification steps, not just building Write detailed specs upfront to reduce ambiguity 2. Subagent Strategy Use subagents frequently to keep the main context window clean Offload research, exploration, and parallel analysis to subagents For complex problems, throw more compute via subagents Assign one task per subagent for focused execution 3. Self-Improvement Loop After any correction from the user, update tasks/lessons.md with the pattern Write rules for yourself to prevent repeating the same mistake Ruthlessly iterate on these lessons until the mistake rate drops Review lessons at the start of each session 4. Verification Before Done Never mark a task complete without proving it works Diff behavior between main and your changes when relevant Ask yourself: “Would a staff engineer approve this?” Run tests, check logs, and demonstrate correctness 5. Demand Elegance (Balanced) For non-trivial changes, ask: “Is there a more elegant solution?” If a fix feels hacky, ask: “Knowing everything I know now, implement the elegant solution.” Skip this for simple fixes — don’t over-engineer Challenge your own work before presenting it 6. Autonomous Bug Fixing When given a bug report: just fix it Use logs, errors, and failing tests to diagnose Require zero context switching from the user Fix failing CI tests automatically Task Management 1. Plan First – Write the plan in tasks/todo.md with checkable items 2. Verify Plan – Confirm the plan before implementation 3. Track Progress – Mark items complete as you go 4. Explain Changes – Provide a high-level summary at each step 5. Document Results – Add a review section to tasks/todo.md 6. Capture Lessons – Update tasks/lessons.md after corrections Core Principles Simplicity First Make every change as simple as possible and minimize code impact. No Laziness Find root causes. Avoid temporary fixes. Maintain senior-level engineering standards.

Single biggest improvement I made to my CLAUDE.md: "When I report a bug, don't start by trying to fix it. Instead, start by writing a test that reproduces the bug. Then, have subagents try to fix the bug and prove it with a passing test."

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

@s_mohinii 1/1: Claude now has explicit persistent “auto memory” instructions: consult memory files across sessions, update via Write/Edit, keep MEMORY.md concise (lines after 200 truncate), store stable patterns/prefs/architecture, avoid session state & speculation, and ...

🚨BREAKING: Someone just solved Claude Code's biggest problem. It's called Claude-Mem and it gives Claude persistent memory across sessions. - You can use up to 95% fewer tokens each time. - Make 20 times more tool calls before reaching limits. 100% Opensource. For Repo : Like + comment " send " + Retweet+ Follow me @s_mohinii so that it can be auto DM

I stopped paying for Claude Code. $200/month for an API subscription to write code. Then Ollama dropped Anthropic API compatibility. Now Claude Code connects to free, local models on my machine. Here's the exact setup (took me 10 minutes): 1. Install Ollama → curl -fsSL https:// ollama .com/install .sh | sh 2. Pull a model → ollama pull qwen2.5-coder 3. Point Claude Code at localhost → ANTHROPIC_BASE_URL=http: //localhost :11434 claude That's it. Claude Code thinks it's talking to Anthropic. It's talking to your laptop. Best models I've tested: • Qwen 2.5 Coder - best all-around for code generation • DeepSeek-Coder - strongest at debugging and refactoring • Llama 3 - solid general reasoning Local models aren't Sonnet or Opus. Complex multi-file refactors still stumble. Long context windows get messy. But for everyday coding - scaffolding, tests, quick edits, boilerplate - they handle it fine. Your code never leaves your machine. Your bill goes from $200/month to $0. Your API key stays in your pocket. (Save this for later.)

@midudev @grok resuelve este ejercicio en JavaScript

No veo fallos en su lógica. ¡Contratado!

Repo: github.com/gsd-build/get-…

@goofyninjaaa Y cuánto pagas de suscripciones? Obviamente es menor que pagar a empleados, pero debes gastar tokens como agua

Para todos los que decían que su trabajo nunca iba a ser reemplazado, oficialmente puedo decir que la IA va a reemplazar a TODOS los godínez. Mientras duermo, mis agentes de IA debaten 24/7 y 16 Mac Minis hacen el trabajo de 200 personas sin cobrar sueldo, sin pedir prestaciones y sin enfermarse. Si no estás corriendo tus propios agentes de IA, no estoy seguro de cómo vas a pagar tus cuentas los próximos meses.

Cuánto niño montando este proyecto y ya le mataron su Startup unicornio 😂