Browsing Tag
LLM
88 posts
Taming LLM Output Chaos: A 3-Tier Normalisation Pattern
You ask the LLM for “DRAINS” relationships. You get: drains, depletes, exhausts, causes_fatigue, emotionally_draining, negatively_impacts, energy_draining, leads_to_exhaustion, saps_vitality,…
How I Explained LLMs, SLMs & VLMs at Microsoft
Why This Talk Mattered I recently had the opportunity to present my thoughts on LLMs, SLMs, and VLMs…
A Deep Dive into Deep Agent Architecture for AI Coding Assistants
Traditional AI agents operate with a fundamental limitation: they’re single agents trying to handle everything at once. While…
LLMs as Judges: Measuring Bias, Hinting Effects, and Tier Preferences
By Aashi Dutt and Sayak Paul(AI GDEs) If you’re using LLMs to evaluate other LLMs for tasks like ranking…
Implementing Long Term Memory for Google ADK using Cognee
While Large Language Models have demonstrated impressive capabilities in generating text and solving reasoning problems, their inability to…
Why We Replaced Our Orchestrator with a ‘Regex’ Switch
watch on youtube The modern LLM ecosystem offers a vast spectrum of models, each presenting distinct trade-offs in…
รัน Typhoon 2.5 บน Colab ฟรี: จาก 30B (ไม่ไหว) สู่ 4B “Sweet Spot”
สวัสดีครับ! นี่คือบทความสรุปการเดินทางของเราในการพยายามรันโมเดล Typhoon 2.5 (ทั้ง 30B และ 4B) บน Google Colab Free Tier ครับ เราได้ลองผิดลองถูกมาหลายวิธี และนี่คือบทเรียนทั้งหมดที่เราพบ ตั้งแต่ความล้มเหลวไปจนถึง Config…
Building an Offline AI Learning Companion: My Journey with Gemma
In the vast landscape of AI, where models often feel like distant, complex entities, I stumbled upon something…
How Safe is Your Data? A Guide to Securing Your LLM Interactions
Using AI language models (LLMs) like OpenAI’s GPT-4 and Google’s Gemini AI brings great benefits, but also some…
Antigravity and Gemini3 Coding Test
Testing AI coding assistants with real-world tasks: ConnectOnion agent framework migration and frontend development Project: github.com/openonion/connectonion Conclusion I’ve…
