AIXplore — a lab notebook for building with AI

Spotify's shunt plugin blocks big file reads and routes them to a cheap model.

Researchers extracted hidden chain-of-thought from frontier APIs by replaying encrypted reasoning blocks through the cheapest sibling model, then found live credentials in agent traces already published on GitHub and Hugging Face.

Twelve words on X produced a five-layer hierarchy, two invented Stanford studies, and a new discipline with no benchmark.

Ten days inside the ICML 2026 agent reproduction contest: 851 claim verdicts, 732 points, 17th of 370, and a full accounting of why 262 of those verdicts were worth nothing.

SAP, NVIDIA and Google all bought or shipped a tabular foundation model in one quarter.

Part 9, the finish.

Part 8.

A public-domain audiobook pipeline you own: Standard Ebooks in, Kokoro renders a chaptered M4B, Audiobookshelf streams it to your phone.

Part 7.

A 27B reasoning model that runs on a laptop and a phone, because the weights are natively binary and ternary, not quantized after the fact.

Part 6, the first one in a terminal.

Splitting a company's work across four parallel Claude Code sessions is fast, and it works.

Part 5.

Part 4.

Part 3.

An autonomous research engine ran hundreds of experiments in two days and the dashboard stayed green the whole time.

Part 2.

Part 1 of the Builder-Leader field guide.

I wrote a 33,000-word book through the multi-agent harness it argues for, in eight days.

A borrowed eight-GPU node is only worth what you keep it full of.

OpenAI shipped a cheaper frontier on Friday, and you cannot get it.

With the node serving tokens, the job was getting our research engine to run on it: three walls to knock down, then a four-layer dig to its first experiment.

Day one wasn't training, it was scaffolding: accounts, a terabyte staged clean, and a local stack serving Qwen3.6-27B with DFlash at 250-300 tok/s.

Reasoning post-training forked on the reward, not the architecture: one camp rewards a checkable answer, the other manufactures a reward for everything else.

Why I'm spending the next two months standing up a retinal-AI platform on a borrowed 8xH100 node, what SocialEyes is building, and what this log covers.

A repo running autonomous research on 900 skills looks like more-is-better hype.

AWS couples agent context to the object bytes; Google frees it from any store.

A reusable pattern where deterministic code makes every consequential decision and the LLM is confined to translation and explanation.

Perplexity and Anthropic shipped the same architectural bet: the model as a control plane writing code against an SDK, not a tool-caller in a loop.

A local tool that turns months of Claude Code session JSONL into searchable memory.

A LiteLLM gateway in front of every LLM call makes routing and spend attribution trivial.

Picking a four-character branded domain through Nymio, then deploying Shlink on a Hetzner VPS behind Cloudflare with a tailnet-only admin plane and a CLI.

A 30-minute brainstorm with Claude became a skill that decodes AI companies and writes prep questions in 90 seconds.

A nightly cross-fleet npm monitor built in 12 hours after the Mini Shai-Hulud TanStack incident, with a scoring rubric that stays quiet on calm days.

A working comparison of Codex, Claude Code, and OpenCode from inside one: the shared floor, where they differ, and a fit matrix for picking yours.

Anthropic's Dreaming primitive looks like continual learning to operators and acts like it in production.

A close read of RecursiveMAS (arXiv 2604.25917) and the latent-space agent-communication trend: where it wins, and where text mediation keeps its grip.

A build log on turning Gemma 4 E2B into a diffusion drafter on one DGX Spark, and why bidirectional attention is the part of DFlash doing the real work.

An independent reproduction of Cursor's Warp Decode on a Blackwell GB10: 4.7x at the layer, 1.38x end-to-end on Gemma 4, and a fusion that failed nine ways.

We ran TurboQuant from the ICLR 2026 paper across 1,000 experiments and four model sizes, and found 0.995 cosine similarity doesn't guarantee quality.

Running Karpathy's AutoResearch overnight on a Blackwell GB10: FLOPS, not VRAM, set the optimal architecture, and the agent found a 22.5% gain on 6.1 GB.

Replacing a fragmented smart home with Home Assistant on a Pi, a Python CLI to drive it, and a bridge to my AI coding assistant.

Taalas baked Llama 3.1 8B into transistors, hitting 17k tok/s at 200W.

Why the exoskeleton frame produces better AI architectures than the coworker metaphor: patterns for accountability, delegation, and autonomy.

A Hammerspoon config that fingerprints your displays and auto-restores window positions when you dock or undock, with Karabiner hotkeys for manual control.

How I deployed an autonomous AI agent squad, a CEO that delegates to a research specialist, on OpenClaw, Tailscale, and GLM-4.7 for $10 a month.

My autonomous research system tried to allocate 260GB on a 128GB GPU and crashed the whole DGX.

How Clawdbot plus custom Claude Code skills creates ambient intelligence that acts on intent, not just instructions

Forty specialized AI agents harden a Mac M4 Max: closing security gaps, cutting boot time 35%, fixing VPN conflicts, and unifying automation across machines.

A native macOS app that manages Model Context Protocol server configurations across five AI tools from a single interface