#llm on Video

LectureAI: I Let Whisper and Gemma Attend Class for Me

Aman Kumar

The king of vibe coding says people are sleeping on swarms. Here's what else Steve Yegge is saying.

Codacy

Human vs. automated evals: who should judge your AI agent?

Nicolai Bohn

What They Missed In The HuggingFace Incident Senate Hearing

Tera Tokomi

How LLMs Work: A Journey Through One Sentence

Filipe Martins

Human-in-the-loop knowledge base for AI agents

Deian

Stop Paying Full Price For Every LLM Call

Decodo

I Built a Semantic Cache for RAG. The Hard Part Was Knowing When NOT to Cache.

Yatin Annam

What Happens When an AI Remembers You Overruled It?

sreekarvvns

Do Not prompt the Arch Intelligent ! ! !

Peter Vivo

The Bell of Greystone

Peter Vivo

Anthropic’s CEO Wants to Slow Down AI, Ban Open Source

Dragos Roua

Inside BitRun v0.2: How I Engineered a Terminal Cockpit for 1-Bit LLMs with Live Power Telemetry

Abhishek Khanra

This Post Is Being Written Through a Browser Perception Layer

Alechko

Fine-Tune, Deploy and Use LLM As AI Agent

Blessed Josiah

Why more context makes your AI answers worse

VLAD

Jev did not make Claude Code cheaper. Its own benchmark says so.

AI Dive

How to Fine-Tune an LLM Locally with Unsloth Studio

Blessed Josiah

Does an LSP help a coding agent?

Scott Raisbeck

Fable 5.1 cut cache reads by 75%. Cost per task went up 20% anyway.

AI Dive

Three models, one live Duolingo lesson: hot-swapping the LLM mid-task in a real browser session

Alechko

The token compressor that made my bill go up — and the proof it had to

Gaurav Gupte

What I Learned Cutting Claude Code's Token Bill by 77%

rguiu

Can we play a game on pixelden? Made my pixel art game portal playable inside Claude via MCP

Tomas Grasl