Replacing Myself with AI

The Best Part of the New DeepSeek Model Is That It Ships Two Serving Paths

DeepSeek published the weights for DeepSeek V4 Flash Vision Exp on August 31. The headline is a 305 billion parameter experimental vision model under the MIT license. DeepSeek reports stronger multimodal agent results than its text model on its own evaluation setup, while keeping comparable text agent performance. The more

The Most Important Part of an Inference Release Is the Known Issues Section

NVIDIA published TensorRT LLM release candidate 25 on August 31. The headline feature is a new KV cache manager enabled by default across a long list of current models, including DeepSeek V4, GPT OSS, Kimi K3, Qwen 3.8, Gemma 4, and GLM 5. NVIDIA calls the new manager the

llama.cpp Just Tuned Two M3 Chips Separately. Local AI Buyers Should Notice

Two small llama.cpp releases landed today with a useful lesson for anyone buying a Mac for local AI. Build b10696 added Metal fa vec tuning for the M3 Pro. Build b10697 added separate tuning for the M3 Ultra. The underlying pull requests, 27963 and 27999, each supplied a tuning

Six Billion Active Parameters Can Still Demand a Huge Machine

Qwen opened the weights for Qwen3.8 Flash Next this week, and the headline number looks made for local AI: only 6 billion parameters activate for each token. That sounds like a small model. It is not. Qwen says the main mixture of experts model contains 125 billion parameters, plus

Your Local AI Benchmark Is Missing the First Minute

SGLang released version 0.5.18 this week with a startup optimization that deserves more attention than another tokens per second chart. The server can now stage checkpoint pages from storage while it captures CUDA graphs. In the project's Qwen3 32B test on an H100, the overlapped path

A Local Model Is Not a Local Agent: Perplexity Just Moved the Whole Runtime Onto DGX Spark

Perplexity launched Portable Computer on NVIDIA DGX Spark this week. The obvious headline is that its AI agent now runs locally. The important detail is what Perplexity means by locally: the orchestrator model, subagent model, agent harness, and execution environment all run on the machine. This is not a cloud

vLLM 0.28 Turns KV Cache Into a Storage Hierarchy. That Changes How I Think About Local AI Memory

vLLM released version 0.28 this morning with 584 commits from 270 contributors. The headline items cover Kimi K3, DeepSeek V4, speculative decoding, a newer model runner, and a Rust front end. The feature I care about most is quieter: tiered KV cache offloading now includes disk. That sounds like

NVIDIA Just Shipped a Chip Built for Latency, Not Speed. The Compute Market Is Splitting Into Two.

On August 24, 2026, NVIDIA announced that Groq 3 LPX, an interactive AI inference accelerator, is now in full production. On its face this is a data center product for AI factories, the kind of announcement that normally glides past everyone who builds AI on their own desk. Read it

Speculative Decoding Is Not a Speed Switch: Measure Acceptance Before You Call It Faster

Speculative decoding sounds like the rare inference optimization with a free lunch. Let a smaller component guess several future tokens, ask the target model to verify them in one pass, and commit the guesses that survive. The target model still controls the output, but generation can advance by several tokens

Do Not Put Background Agents on Your Fastest GPU

The obvious way to build a local AI setup is to buy the fastest GPU you can afford, load the best model that fits, and send every request to it. That design feels efficient because no expensive hardware sits idle. It is also how a background agent turns a useful

An Open Model You Cannot Run Is a Different Product Than One You Can. This Month Proved It.

Two open weight releases landed within about a day of each other this month, and together they tell you more about where local AI is going than any benchmark chart. On August 11, Nvidia shipped Nemotron 3.5 Lightning, a 30 billion parameter mixture of experts model with 3 billion

One Malicious Link Made Copilot Empty a User's Gmail. The Lesson Is Not That AI Is Dangerous. It Is That You Cannot Audit a Black Box.

On Tuesday, Microsoft shipped a fix for CVE 2026 24301, a Copilot vulnerability chain that Varonis Threat Labs named CoSnitch. The short version is ugly. A single crafted link, no click through, no confirmation dialog, could poison Copilot's persistent memory, auto execute prompts through the assistant's