Activity
Mon
Wed
Fri
Sun
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Memberships

AI Money Lab

73.6k members • Free

KI Automation Akademie

88 members • Free

n8n, KI & Automation

2k members • Free

KI Klarheitsclub 50+

77 members • Free

AI Profit Boardroom

3k members • $59/m

2 contributions to AI Money Lab
Common AI Mistakes
What’s the biggest mistake people make when using AI?
Common AI Mistakes
4 likes • 1d
Using AI to create before knowing the real pain point of your niche. AI doesn’t make you smarter, it makes you faster. And if you’re fast in the wrong direction, that’s worse than being slow.
48 hours later — I have 7 agents running my SEO agency on autopilot.
The full stack, the breakdowns, and the 3 things I wish someone had told me before I started 👇 Tuesday, 9 PM. I open the terminal to set up Hermes Agent (an open-source agentic framework by Nous Research). By 3 AM, I had: → Spent 2 hours just fixing my broken terminal config before I could even start (broken $PATH, no brew, basic Unix commands missing — the works) → Watched Hermes take 10+ minutes to respond to a single "who are you?" — and then time out → My ANTHROPIC_API_KEY was sitting unused in .env while Hermes kept silently calling a different account I'd already burned through→ A growing suspicion that "agentic AI is here" was a marketing line I closed the laptop. Slept badly. Thursday, 7 PM. Here's what's running for BVMBY SEO without my hands on the keyboard: 🇩🇪 German writer #1 — 1 article/day at 5 AM UTC 🇫🇷 French writer — 1 article/day at 6 AM 🇩🇪 German writer #2 — 1 article/day at 7 AM 🔍 Keyword researcher (FR+DE) — every Monday 8 AM 📊 GEO citation monitor — every Wednesday 9 AM (Perplexity API) ✉️ Cold email drafter — Mon→Thu, 5 drafts/day for manual review 📈 Weekly digest — every Monday 8 AM, dropped in my inbox Total: 7 agents · ~$22/month in API · roughly 5 hours/week of my time saved. The 3 things that unblocked me 1. Don't run agents on a "local" model that isn't built for agents. Hermes Agent loads 89 skills + 28 tools into the system prompt. The default local model (hermes3:8b) physically can't process that — it spends 10+ minutes thinking about a single "hi". Switch the runtime to Claude / GPT / Gemini. "100% local" stays a fantasy until inference gets cheaper. 2. Kill the OAuth cache. Hermes caches Claude Code OAuth in ~/.hermes/auth.json and silently overrides your API key from .env. You'll watch your Claude Max quota evaporate while wondering why your API key budget isn't moving. Just delete the file. 3. Don't pick the newest Claude model.claude-sonnet-4-6 has 1M context and requires a paid "long context" tier opt-in (which, surprise, you don't have on a fresh API account). Switch to claude-sonnet-4-5-20250929 (200K context). Same quality, no opt-in.
48 hours later — I have 7 agents running my SEO agency on autopilot.
7 likes • 5d
@Peter Velinov haha you'd have laughed at my first generated article 😅 Yes — German C1, French native, my agency targets DACH so quality matters. First batch was rough: agents writing "ue" instead of "ü" (the lazy keyboard workaround 🙄), weird Genitiv-Dativ confusions, that "I learned German from a 1997 textbook" tone you can smell from a mile. The advantage of agents (vs one-shot Claude translation) is they learn fast when you bake rules into a SKILL.md. Added umlaut handling, formal Sie register for Steuerberater audience, no Anglicisms — next batch was 10x cleaner. Quality stack: I review every German piece before it ships, Grammarly catches grammar in real time, and rules update in the SKILL.md every time I spot a recurring error. Your Bulgarian story is exactly the lesson though — Claude can produce text but you need a native in the loop for the tonal stuff that doesn't show up as "errors". Otherwise you publish garbage with full confidence 😂
7 likes • 5d
@Peter Velinov actually here's one that shipped this week 👇
1-2 of 2
Bamby Ndiaye
3
11points to level up
@abdoulaye-ndiaye-5668
student want to learn more about AI

Active 7h ago
Joined May 5, 2026
Berlin
Powered by