Zac

@heyblake aviatorledger.com Realistic Career Pilot Simulator

Drop your project URL Let’s drive some traffic

Built a free browser-based airline career simulator and quietly launched it a few weeks ago. 209 airlines. Real pay scales. FAA Part 117 fatigue rules. Charter ops, aircraft ownership, virtual airlines where you can hire real pilots. aviatorledger.com

110 commits in. SkyCareer is ready for beta testers. Airline career sim — FAA fatigue, real pay scales, Iron Man mode, SimBrief, MSFS/XP/FS4 import. No sim required. Want in? DM me. #FlightSim #MSFS #Aviation #IndieGame

@Luis91960935228 @VadimStrizheus Privacy and no api costs

@VadimStrizheus Local models are dumb, right? Is there a real use to local models?

I just got a MacBook Pro M5 Chip > 16” > 24GB > 1 TB of storage What’s the best local model to run on this thing?

@LinusEkenstam data cannot be transmitted to third-party cloud LLM APIs. github.com/zparker68/finc…

@LinusEkenstam Oracle Fusion GL, Blackline reconciliations, HFM variance reporting, and SOX internal controls. The system runs 100% offline. No financial data ever leaves your machine — a critical requirement in regulated industries (gaming, healthcare, financial services) where sensitive GL

Can I see some links of what you’ve built with Claude code? Blow my mind

@sam_kalaliya @kaaaash____ I just bought a 64gb M5 MacBook Pro and it struggles with 70b local models.

@kaaaash____ 32GB is my new minimum with local models + Docker running. 16GB dies too fast now 😭 Dropped a quick 2026 poll here if you want to vote → x.com/sam_kalaliya/s…

as a Programmer, how much RAM is enough for you ?? 1. 8 GB 2. 16 GB 3. 24 GB 4. 32 GB 5. 64 GB 6. 128 GB 7. 256 GB+

Just pure, compliant automation. The future of FinTech is local. ⚡️ #AI #LangGraph #Ollama #Python #BuildInPublic

🗄️ SQLite + ETL layer (Oracle/Blackline simulation) 🛡️ SOX-aware Critic agent for audit trails The pipeline handles everything from user queries to a "Critic" gate that approves or flags entries based on GAAP policies. No data leaves your machine. No API costs.

Financial data + Cloud LLMs = A security nightmare. ❌ Introducing FinClose AI: A production-grade multi-agent system for enterprise financial close automation that runs 100% offline. The stack: 🧠 LangGraph agentic pipeline 🦙 Ollama (Mistral 7B Q4) for local inference

@x_lab_hub @icanvardar Run it through a local LLm like qwen or deepseek ?

@icanvardar Openclaw burns through tokens/money .. You need some serious cash behind

never met a single person irl who uses openclaw

@joseossoriom @vukandric Agreed

@vukandric Imo better M5 Pro 18c with 64GB of RAM and 1TB SSD

Can this run OpenClaw?

@ycocerious Take cert courses

What do you guys do while your claude code is running?

@BentoBoiNFT For real. And for some reason nighttime is the best time to work on my Ai projects.

I’m so addicted to this AI stuff I gotta overload myself with melatonin at night just to sleep 😭

@KevinNaughtonJr I’m going to take your job with Ai

do people still think AI is gonna take their jobs?

@asaio87 💯

Can the Claude max $200/mo plan help you deliver 52 apps in 52 weeks ?

@theindiebuild @BentoBoiNFT Easy

@BentoBoiNFT Lmao can you actually reach limits with this plan?

I’ve upgraded to the $200/mo Max Claude plan Can I become super rich now