Browsing Tag
LLM
126 posts
Exploring AI workflow Orchestration: Comparing Weft, Python & Alternative Pipeline Approaches
A few weeks ago I started exploring something that made me rethink how we build AI workflows. Most…
로컬 LLM 셋업 가이드 (v18)
Local LLM Setup Guide (v18) 1. Overview & Prerequisites Running LLMs locally requires minimal hardware but careful resource…
Request-Boundary AI Spend Control in 2026: A Practical Diagnostic for Gateway and FinOps Teams
TL;DR AI invoice shock is usually created at request granularity, not account granularity. Current 2026 gateway docs from…
Built an open-source picker that recommends the right self-hosted LLM for your hardware
Built this because every “which LLM should I self-host on my [hardware]” thread ends with “depends” without anyone…
I tracked 332 AI releases this week. 85% were noise.
332 items. That’s how many AI releases, papers, repos, and tool launches we ingested last week into the…
Did My LoRA Learn Tenacious Style—or Just Memorize Augmented Patterns?
In Week 11 Tenacious-Bench, we trained a LoRA adapter on Tenacious-style B2B sales emails using Supervised Fine-Tuning (SFT).…
The creation of Power Bar in Astrocot (an astrology system).
I created a command bar (Power Bar) to control the system (Sky Chart) using readable text instead of…
SearchWala: I Built a Blazing-Fast Meta-Search Engine in Rust That Queries 90+ Engines Simultaneously
Hey devs! I want to share a project I have been working on called SearchWala (Swift-Search-RS). What is…
Serve and Inference Gemma 4 on TPU
Introduction Earlier in April 2026, Google released Gemma 4, the latest family of open multimodal models, and momentum…
The Fatal Flaw of AI Hallucination: When LLMs Confidently Tell Lies
A journalist recently called out DeepSeek for its “serious lying problem” — the model can write a beautifully…