Senior engineer writing about infrastructure, distributed systems, and AI research. Currently training LLMs from scratch and building things that scale.
Three new agent frameworks shipped in 2026. I ran the same coding task on all three with Claude Opus 4.8. DeepAgents: 51s. Eve: 74s. Mastra/AI SDK: 80s. All passed 30/30. They diverge on architecture, context management, and what happens when your agent runs for 50+ turns.
I put Tencent's CubeSandbox on a low-end dedicated box and measured every part of the spin-up path. Warm resume ~20 ms, cold create ~72 ms, a 40-wide cold burst at p50 ~490 ms (p99 over a second), a thousand create-delete cycles in 23 seconds, and a density wall at 165 concurrent. Plus how it lines up against the managed sandboxes for coding and RL, and why I ran it on bare metal.
Seven principles from making a production LLM agent an order of magnitude faster without touching the model, and the reusable optimization prompt they became. Nothing here is domain-specific; they work for any agent that burns tokens in a loop.
I rented an 8×B200 and tried to run GLM-5.2 on TileRT, the runtime MiMo used to push a 1T model past 1000 tok/s. TileRT doesn't support GLM-5.2, so I reverse-engineered its IndexShare attention and weight-remapped it onto the kernel. Result: ~480 tok/s, OpenRouter-identical quality, ~5× faster than vLLM on the same GPUs, capped at 2048 tokens by the closed kernel. The apples-to-apples numbers (TileRT 480 / vLLM 96 / OpenRouter 104), why MTP made vLLM slower, and what it'd take to beat it.
A complete, apple-to-apple comparison of the three agent frameworks that matter in 2026, full feature matrix plus a real benchmark on live Daytona sandboxes with gpt-5. All three can code; they diverge on durability, cost, and architecture. Includes a pick-by-use-case guide for analytics, coding, multi-agent, RAG, voice, and enterprise.
A technical note on Blackwood Diffusion: a masked-denoising language model with a 49,152-token agentic tokenizer, staged context growth, and revision-native generation.
How I designed a custom 128K Byte-BPE tokenizer for DarkForest, and the data curation strategy that turned a noisy corpus into something a model can learn from.
No fine-tuning. No LoRA. No base model. Training a 7 billion parameter language model from random weights, on rented H100s. General-purpose first, then specialized for code through SFT and RL on real agent trajectories.
How to build a chat system where multiple specialized AI agents handle different types of requests instead of one agent trying to do everything.
When your AI operation takes 30+ seconds, you cant just show a spinner. Here is how to use Server-Sent Events to stream progress in real time.
How I added Claude Code-style team coordination to Codex — one lead agent spawning and coordinating multiple teammates in parallel using a shared filesystem task board.
How I built a reusable chat component library with React 19 and Vite that works across multiple projects.
First post on abhishek.it.