Azmat
Watch or Listen on YouTube Liquid AI LFM2 2.6B Exp Review: The “RL First” 2.6B Checkpoint Introduction A lot of model releases are loud in all the predictable ways. Bigger number, bigger chart, bigger promise. Then once in a while a small model lands that forces a more interesting question: what if we are finally … Read more
Watch or Listen on YouTube Next Embedding Prediction (NEPA): Introduction A lot of self-supervised vision feels like an elaborate workaround. Two crops, three heads, four losses, and a decoder you throw away the moment you start fine-tuning. This paper tries something refreshingly blunt. It asks: what if we just did prediction, the way language models … Read more
Watch or Listen on YouTube General Intelligence vs Universal Intelligence Debate Breakdown Introduction People love the idea of a single finish line called “AGI.” One morning you wake up, open your laptop, and the machine on the other side has “arrived,” it writes proofs, plans projects, designs hardware, and stays useful without constant babysitting. That … Read more
Watch or Listen on YouTube MiniMax M2.1 Review: API Access, Local Runs, Pricing, and Benchmarks Introduction Every few months, the internet discovers a new “coding beast” model and immediately does what it always does. Someone posts a chart, someone posts a slick UI demo, and then a thousand developers ask the only questions that matter, … Read more
8 Watch or Listen on YouTube GLM-4.7 Review: Agentic Workflows & Local Roleplay Deep Dive Introduction Sudden benchmark glow-ups always give me the same feeling as a too-clean Git history. Interesting, maybe impressive, but I want to see what got squashed. GLM-4.7 landed with that exact energy, a flagship model claiming big jumps in coding, … Read more
Watch or Listen on YouTube Anthropic Bloom Guide: Automating LLM Red Teaming and Benchmarking Claude guide hub (beginner to pro) Introduction I used to “test” models the way most of us do at first. A dozen prompts, a quick skim, a shrug. It feels responsible. It’s also a lie we tell ourselves because writing good … Read more
Watch or Listen on YouTube T5Gemma 2 Explained: Why Google Is Betting Big On Encoder-Decoders (Again) Introduction Decoder-only models have been winning the popularity contest for a while. They are great at talking. You give them a prompt, they keep the autocomplete train rolling, and suddenly you have code, essays, or a questionable poem about … Read more