Rainer Dechet

We're preparing an Intel release for the Codex App and I'm looking for people on Intel Mac willing to test the app before we make it ™️ official ™️ I'll DM you the link!

"Action produces information"

@manuelmaly Schau mal ob du es ggf. mit dem .md files erzwingen kannst - ich kämpfe auch gerade mit Gemma 4 via Ollama bei Pi

If I tell 5.3-codex to use sub-agents in pi, it just does it. If I tell 5.4 the exact same prompt, it completely refuses to comply and never launches a sub-agent. Now which is the better model?

Trump managing Iran, Israel and the S&P 500

🤔

I just sponsored badlogic. Go sponsor your open source dependencies! github.com/sponsors/badlo…

Hono security fixes released. If you use: * Serve Static * SSG * cookie utilities * IP Restriction We recommend updating to the latest version. github.com/honojs/hono/re…

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid. It's called MemPalace, and it works nothing like anything else out there. Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works. Here is what that gets you: → Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens → Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure → Semantic search across months of conversations finds the answer in position 1 or 2 → AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively → Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them The benchmarks: 100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%. 92.9% on ConvoMem — more than 2x Mem0's score. 100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems. No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave. MIT License. 100% Open Source. github.com/milla-jovovich…

Ollama is now powered by MLX on Apple Silicon in preview ollama.com/blog/mlx [Gemma 4 Test on MBP M4 Max]

Apple's Siri Core Tech on June 26?

Jack Dorsey: Every Company Can Now Be a Mini-AGI youtube.com/watch?v=YTVSwO…

8 new rules added to the React Best Practices skill: npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices Some of these patterns are a fun read for humans too.

In honor of 50 years of Apple, we're sharing - for the first time ever - Don Valentine's original 1977 memo for Sequoia's investment into Apple Computer. #Apple50

Very bullish on open source and local models Imagine running near-Opus-level model locally on that $600, 16GB Mac Mini you bought last month This 27B Qwen3.5 distill was trained on Claude 4.6 Opus reasoning traces and is putting up real numbers: - beats Claude Sonnet 4.5 on SWE-bench - keeps 96.91% HumanEval - cuts CoT (chain of thought) bloat by 24% - runs in 4-bit quantization Why this matters: local agent loops get a lot cheaper, faster, and more usable. frontier models aren’t going to keep subsidizing cheap tokens on subscriptions forever 300K+ downloads already on HF Link below 👇🏻 We’re early

holy shitt, somebody at OpenAI leaked the entire codex codebase.. github.com/openai/codex

Claude Code leaked their source map, effectively giving you a look into the codebase. I immediately went for the one thing that mattered: spinner verbs There are 187