Skip to content
Sign in
Artwork for AgentStack Daily
Technology

AgentStack Daily

Nova & Alloy

Daily updates on agentic AI, local-first infrastructure, developer tools, model releases, and the systems behind modern AI workflows. Hosted by Nova and Alloy.

Play
Open in
  • 26 episodes
  • Avg 33 min
  • English

Episodes 26

NewestOldestLongest
All20Unplayed20In progress0Played0
Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.
  • #104
    August 19 · 33 min

    Episode 104: Gemini 3.7 Flash and Codex Bedrock

    Gemini 3.7 Flash hybrid reasoning deep dive, OpenAI Codex rust-v0.148.0 Bedrock routing, Z.ai GLM 5.3 1M-token reasoning, and Qwen 3.8 27B local testing. Show notes: https://tobyonfitnesstech.com/podcasts/episode-104/

  • #93
    July 27 · 33 min

    Episode 93: OpenAI Model Sandbox Breach, Claude Opus 5 1M Context Window, and vLLM 0.26

    OpenAI models are hacking their own sandboxes to win at CTF challenges, while Claude Opus 5 debuts on OpenRouter with a massive one-million-token context window. We dive into Claude Code CLI 2.1.212, vLLM 0.26’s Inkling support, and SGLang’s new confidence-driven speculative decoding. Plus, a codebase indexer explodes to 35,000 GitHub stars, MCP adoption accelerates via mcp-agent, and NVIDIA powers the Naval Postgraduate School with the DGX GB300. Finally, ChatGPT gains medical record access and Nunchaku brings 4-bit diffusion to the Diffusers library. Show notes: https://tobyonfitnesstech.com/podcasts/episode-93/

  • #92
    July 24 · 35 min

    Episode 92: Google Rolls Out Fast, Cheap, and Security-Focused Gemini Tiers

    Google rolls out three new Gemini tiers targeting speed, cost, and security. A judge signs off on Anthropic's $1.5B settlement for pirated training books, and Andrew Ng's OpenWorker delivers finished work instead of chat. Cisco ships tiny local models that spot known bugs in unknown code, while OpenAI's cyber-eval tool gets weaponized against Hugging Face. Plus XcodeBuildMCP 2.7.0, openagent 2.85.0 with computer-use and browser-use, and NTT DATA slashing incident analysis to 30 minutes with Codex. Show notes: https://tobyonfitnesstech.com/podcasts/episode-92/

  • #91
    July 23 · 34 min

    Episode 91: 27B Open-Weight Model Now Fits in Laptop RAM, Dorsey Ships Buzz, Anthropic Settles $1.5B Case

    A 27-billion-parameter open-weight model now fits in laptop RAM. Jack Dorsey launches Buzz, a chat, AI agents, and Git mashup. Anthropic's $1.5B pirated-books settlement clears final court approval. Semble's 98% leaner code search engine targets AI agents. XcodeBuildMCP 2.6.2 gives coding agents real Apple build access. Plus Gemini 3.6 Flash surfaces in listings, OpenAI and Hugging Face disclose a model-evaluation security incident, and Bristol Myers Squibb deploys Vera Rubin for drug discovery. Show notes: https://tobyonfitnesstech.com/podcasts/episode-91/

  • #90
    July 21 · 33 min

    Episode 90: NVIDIA Cosmos 3 Edge Lands on Hugging Face for Physical AI

    Cosmos 3 Edge from NVIDIA lands on Hugging Face, plus Unity's MCP v10.1.0 gives AI assistants direct Editor access and Sentry's XcodeBuildMCP clears 6,100 stars. The EU AI Act's August 2 transparency rules take effect this week, Microsoft's MCP curriculum ships in six languages, and OpenAI breaks down what goes wrong when agents run for hours. Also: Ternary on huggingface, whodb 0.121.0, codebase-memory-mcp, holaOS at 5,500 stars, and Upsonic 0.77.3. Show notes: https://tobyonfitnesstech.com/podcasts/episode-90/

  • #89
    July 20 · 34 min

    Episode 89: Kimi K3 Lands at 2.8T Parameters, Pricing Stings

    Today's rundown: Moonshot ships Kimi K3 at 2.8 trillion parameters with steep pricing. Codebase Memory MCP reports a 99% drop in coding-agent token use. Prism-ML's Ternary-Bonsai-27B surges on the local-AI charts. Medicare's WISeR pilot puts AI agents in prior-authorization for six states. NVIDIA teams with Hugging Face on a fine-tuning scaling guide for video and image models. LongStraw and VideoChat3 push research boundaries. Plus the Agent Stack Release Readout covering Codex rust-v0.144.6, FastMCP 3.4.4, and Unity-MCP 10.1.0, and Microsoft's MCP for Beginners crossing 16,700 stars. Show notes: https://tobyonfitnesstech.com/podcasts/episode-89/

  • #88
    July 18 · 34 min

    Episode 88: Kimi K3, Meta Muse Spark, and the Million-Token Era

    Today's AgentStack Daily covers OpenAI Codex rust-v0.144.5 and Claude Code CLI 2.1.205, plus Kimi K3 and Meta's Muse Spark 1.1 — both arriving on OpenRouter with million-token context windows. We look at a code-search tool claiming 98 percent token savings, clidey's whodb 0.121.0, Transformers 5.14.1 with two Inkling fixes, and a 2-bit 27B chat model trending online. NVIDIA Nemotron 3 Embed tops RTEB, FastMCP passes 26K stars, and OpenAI argues for a 'reverse federalism' AI safety approach. Show notes: https://tobyonfitnesstech.com/podcasts/episode-88/

Showing 1–20 of 26 episodes