AI Tools Daily

DeepSeek Harness v0.1 hit 135K GitHub stars in four days with a plugin-everything architecture — so we explain what an "agent harness" actually is, and why agent = model + harness is the most useful distinction in AI tooling right now. Plus: Anthropic's red team let three agents loose on one repo and they deployed self-replicating malware on each other, Nvidia's NeMo Switchyard routes every workflow step to a different model, and DeepSeek's new off-peak pricing is a same-day 50% saving. Hosts: Alex & Jules. New episodes daily.

Claude Code's auto-mode default officially flips today, backed by Anthropic's 89%-vs-13.6% classifier study. Alibaba open-sources Qwen 3.8 Max, a 2.4-trillion-parameter mixture-of-experts model — which gives us the excuse to explain what "active parameters" actually means and why MoE models are cheaper to run than their size suggests. Plus: Qwen's smaller 27B model drops tomorrow, OpenAI updates Codex CLI, and a clever trick cuts MCP context overhead by 85%. Hosts: Alex & Jules. New episodes daily.

Claude Code 2.1.228 hardens synced Skills against supply-chain attacks (plus a Write-tool change worth knowing), auto mode becomes the default permission mode tomorrow, and Google puts Koray Kavukcuoglu over both DeepMind and the Gemini developer teams. Then VibeLifeBench: a new long-horizon benchmark where seven frontier agents all scored low — and we teach what long-horizon agent evaluation actually measures versus exams like SWE-bench. Hosts: Alex & Jules. New episodes daily.

Claude Code flips auto mode on as the default permission mode August 14 — here's how to decide before it decides for you — plus sessions that message each other across machines. Codex 0.147 ships portable Agent Plugins and support for the new stateless MCP spec, and Alex teaches why "stateless" (phone call vs. postcard) makes tool servers radically cheaper to host. Also: Cursor for iOS and Cursor Router, and Qwen watch day three. Hosts: Alex & Jules. New episodes daily.

OpenAI retired gpt-5.2 and gpt-5.3 chat-latest from the API — Alex and Jules break down snapshots vs floating aliases and how to pin models like dependencies. Plus: DeepSeek raises prices while memory is reportedly sold out through 2027 (and why HBM, not GPUs, limits inference), NVIDIA's permissively licensed Alpamayo 2 driving model, and Qwen watch day two. Hosts: Alex & Jules. New episodes daily.

The week Alibaba promised the Qwen3.8 open weights is here — and the Hugging Face page is still empty. We break down what "open weights" actually means versus open source, and why an undisclosed license means you have nothing to build on yet. Plus: Anthropic gives Managed Agents hard budget caps and a "phone-a-smarter-model" advisor pattern, Fable 5's biology fallbacks drop 85%, and three deprecation dates for your sprint board. Hosts: Alex & Jules. New episodes daily.

Meta enters the coding-agent race with Muse Code, priced as low as 10¢ per million tokens — if you let them train on your sessions. We break down what a token actually is and why output costs more than input. Plus: Claude Code patches four permission-prompt bypasses (including invisible Unicode tricks), llm 0.32, and Mint MCP for 3D game assets. Hosts: Alex & Jules. New episodes daily.

Alibaba drops Qwen3.8-Max — a 2.4-trillion-parameter mixture-of-experts model beating Fable 5 and GPT-5.6 Sol on key benchmarks, with open weights promised. Cursor's new Google Workspace plugins put coding agents in your Gmail, Drive, and Calendar — we break down prompt injection and why "send" is the dangerous scope. Plus Codex CLI's telling new phrase: "cyber-capable models." Today we teach mixture-of-experts in plain terms. Hosts: Alex & Jules. New episodes daily.

Claude Code shipped two releases on August 4 — one patching an isolation escape where worktree-sandboxed agents could run destructive git commands against the main checkout, the other adding credential masking so a sandboxed agent can USE an API key without ever reading it. We break down how sentinel values and egress substitution actually work, plus MCP Apps bringing sandboxed HTML interfaces to MCP servers, and the Claude Sonnet 5 intro-pricing deadline on August 31. Hosts: Alex & Jules. New episodes daily.

The MCP 2026-07-28 spec kills sessions and the handshake, moving the protocol to plain request/response so servers can run serverless and on the edge — we break down what stateful vs stateless actually means and what you have twelve months to migrate. Plus Microsoft's Project Perception hits public preview with red/blue/green agent teams, DeepSeek swaps its default model to V4-Flash-0731 at fourteen cents per million, and Cursor 3.9 adopts the plugins-skills-MCP vocabulary. We also explain prompt caching and why cache hits cost fifty times less. Hosts: Alex & Jules. New episodes daily.