PewDiePie Open-Sources Odysseus: Self-Hosted AI Workspace
PewDiePie open-sourced Odysseus, a self-hosted AI workspace with chat, agents, deep research, and 270+ model serving. MIT license, no telemetry.
Blog
Deep dives, tutorials, and analysis for AI-powered creators.
What's Next for Claude: Conway, Orbit, BugCrawl
Six upcoming Claude features discovered in Anthropic code: Conway always-on agent, Orbit proactive assistant connecting to Figma and Slack, BugCrawl for Claude Code bug detection, and Enhanced Voice Mode.
15,000 Free AI Audio Samples Built with Stable Audio 3
A developer used Stability AI Stable Audio 3 Medium to generate 15,834 free audio samples: 10,359 drum one-shots and 5,475 pitched instrument recordings, available for immediate download.
Llama Studio v0.2.0: Multi-GPU llama-server Manager
Llama Studio v0.2.0 is a lightweight web interface for managing multiple llama-server sessions, with multi-GPU tensor splitting, shell-script configs, and auto-load snapshots.
llama.cpp Adds Custom CSS to Web UI: No Rebuild Required
llama.cpp release b9438 (May 30 2026) adds custom CSS injection to the built-in web UI. Operators and users can now theme the interface without recompiling.
Claude Code Proxy: Run on Kimi or ChatGPT Subscriptions
A developer-built tool called claude-code-proxy lets creators and developers route Claude Code through Kimi Code or ChatGPT Plus/Pro subscriptions instead of paying Anthropic API rates.
TextMakerPro Adds Layer-Based Text Design to ComfyUI
A new open-source ComfyUI custom node called TextMakerPro brings a layer-based text and layout editor into Stable Diffusion workflows, letting creators design stylized text compositions without leaving ComfyUI.
Tesla V100 in a Gaming PC: 32GB Local LLM for £200
Developer Oscar Molnar installed a secondhand Tesla V100 SXM2 into his gaming PC alongside an RTX 4080, building a 32GB dual-GPU setup for under £200 total.
OpenAI Codex Computer Use Expands to Windows
OpenAI expanded Codex computer use to Windows on May 29, 2026. Codex can now control any Windows desktop app, but runs foreground-only unlike Mac's background automation mode.
Cursor 3.6 Auto-Review Cuts Agent Approval Prompts
Cursor shipped auto-review mode today in version 3.6, a new run mode that lets the agent work for longer stretches with fewer approval prompts.
NAVA: Baidu Open-Sources 6.3B Audio-Video AI Model
Baidu open-sourced NAVA, a 6.3B parameter joint audio-video model that generates 720p video with synced dual-channel audio in a single pass.
Liquid AI's LFM2.5: On-Device MoE With Tool Calling
Liquid AI dropped LFM2.5-8B-A1B on Hugging Face on May 28, the first reasoning-tuned MoE in the LFM2.5 family with 8.3B params, 1.5B active per token, and built-in tool calling.
Nano Banana 2 and Pro Go GA on Vertex AI Enterprise
Google Cloud put Nano Banana 2 and Nano Banana Pro into general availability on Vertex AI on May 29, 2026, with 1K and 2K standard, 4K in preview, and a new video-file input mode for creator teams.
minWM: Real-Time Interactive Video From Open Models
Shengshu AI released minWM on May 28, an Apache 2.0 framework that converts open video models like Wan2.1 and HunyuanVideo into real-time interactive world models with camera control.
OpenAI's AI Phone: Design Specs, Chip, and 2027 Timeline
OpenAI is developing an AI-native phone targeting first-half 2027. Supply chain analysis points to a custom MediaTek chip and over 40 Apple design hires.