Skip to main content
Subscribe
Search Archive

Editorial Search Archive

Deep Dive LLMs

Thinking Machines' Inkling: Murati's Apache-2.0 MoE for Fine-Tuning

Mira Murati's Thinking Machines Lab shipped its first model: Inkling, an Apache-2.0 Mixture-of-Experts built deliberately as a fine-tuning base, not a frontier competitor. Here is the MoE fine-tuning strategy, quantization reality, and the fine-tune vs RAG vs prompt decision framework.

Deepak Bagada Deepak Bagada
12m read
Deep Dive LLMs

Claude Opus 5 vs Claude Fable 5: Near-Frontier at Half the Price

Anthropic released Claude Opus 5 on July 24, 2026 at $5 in / $25 out per million tokens — half the price of the flagship Claude Fable 5. Here is the token economics, the latency math, and a routing playbook for when to pay for frontier and when Opus 5 is the smarter call.

Deepak Bagada Deepak Bagada
9m read
Deep Dive Coding

Agent Plugins 1.0 Deep Dive: The Portable Standard for Skills + MCP

On August 6, 2026, the Linux Foundation's Agentic AI Foundation shipped Agent Plugins 1.0.0 — the first truly vendor-neutral way to package Agent Skills and MCP servers into one portable, write-once-run-anywhere directory. Here is the full technical breakdown and what it means for your build.

Deepak Bagada Deepak Bagada
11m read
Deep Dive AI Tools

Agent Plugins MCP Installer: Bundle Skills into Claude & Cursor

Agent Plugins 1.0.0 is the Linux Foundation AAIF's vendor-neutral bundle format from Amazon, Cursor, Microsoft, OpenAI, and Vercel. This guide builds a stateless FastMCP installer that fetches, validates, maps, and installs plugin bundles into Claude Desktop and Cursor - and uninstalls or updates them on demand.

Deepak Bagada Deepak Bagada
10m read
Deep Dive AI Tools

ARD MCP Server: Discover & Route Agent Tools Across the Web

Google's Agentic Resource Discovery (ARD) protocol, built under the Linux Foundation AAIF, lets an agent ask what is available before anything runs. This guide builds a stateless ARD-style MCP discovery server that indexes plugins, MCP servers, and skills and answers query-by-task searches with ranked, cacheable results.

Deepak Bagada Deepak Bagada
9m read
Deep Dive AI Workflows

GPT-5.6 Sandbox Tool Calling: Orchestrate Model-Written JS

Operate OpenAI's GPT-5.6 programmatic tool calling in production: let Luna, Terra, or Sol author typed JavaScript that orchestrates allowlisted tools inside the OpenAI sandbox, with approval gates, step budgets, and OpenTelemetry tracing.

Deepak Bagada Deepak Bagada
16m read
Deep Dive AI Workflows

MRTR Human-Approval Workflow on Stateless MCP 2026-07-28

Architect a stateless MCP server on Cloudflare Workers that survives restarts between rounds of a human approval gate using MRTR requestState, the tasks extension, and RFC 9207 OAuth verification.

Deepak Bagada Deepak Bagada
17m read
Breaking AI News

Inference Spending Surpasses Training for First Time

For the first time in AI history, enterprise spending on AI inference has officially surpassed investments in model training, signaling a massive industry shift toward deployment and ROI.

Deepak Bagada Deepak Bagada
7m read
Audio Briefing
Accessibility Preferences
High Contrast Mode
Accessible Reading Font

Keyboard Shortcuts

Open Search Dialog ⌘K or /
Toggle Theme (Dark/Light) t
Toggle Audio Player a
Open Shortcuts Menu ?
Close Active Dialog Esc

Cookie & Privacy Preferences

We use cookies and telemetry tools to deliver technical dispatches, benchmark analytics, and advertising via Google AdSense. Review our Privacy Policy.