Vier lokale KI-Modelle, 2.213 echte Spam-Mails und ein klarer Überraschungssieger: In diesem Spam-Benchmark erreicht Laya Multilingual eine Erkennungsrate von 99,86 Prozent. Noch interessanter ist allerdings der Vergleich mit den anderen Modellen, insbesondere bei Geschwindigkeit und Ressourcenbedarf. Getestet wurden Julia-1, Laya Multilingual, Kev-0.8B und Kev-4B. Alle vier sind spezialisierte KI-Modelle, die Texte analysieren und Entscheidungen treffen…
Read ArticleTag: AI
z.ai is scamming their customers with glm-5.2
They rate limit requests coming from Openclaw or Hermes aka every harness which is not “approved”. You pay a huge price and they think they can dictate which harness you’re supposed to use. This is a scam. Chinese untrustworthy company, just like every single Chinese company I ever had the displeasure to do business with.…
Read ArticleAI Game Engine Comparison: Unity, Godot, Unreal, Defold
I asked 4 LLMs which Game Engine they’re most familiar with: Out of curiousity, which of those are you most familiar with, if you would have to create a game client with it? Godot, Unity, Defold, Unreal? and this is what I received as a response. Codex 5.3 For creating a game client, I’m most…
Read Article
My Vibe Coding Process: From Zero to Shipped with AI
My vibe coding process is not just about typing speed. It is about maintaining a continuous flow state where the AI handles the heavy architectural lifting and implementation details while you act as the conductor. Over time I have refined a specific workflow that keeps code quality high and hallucinations low. If you have already…
Read Article