Dan Murfitt

@MatthewBerman You can build your own version of a tool you already use, and customise it just how you want.

I want to build something new and can’t think of anything it’s the worst feeling

I feel like we need a @MikeJudge Silicon Valley for the age of AI.

Last week we went out into the wilderness, far from any cell service or Wi-Fi, to test an experimental Gemma 4 app, all 100% offline: 🔍Visual understanding 🧠Math reasoning 🛠️Tool use and more Running seamlessly on Pixel hardware and paired with our prototype display glasses.

Stop for a second and consider that last year at this time OpenAI had just released GPT 4.1. That was only a year ago. 😳

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out. I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really). It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely. The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture. We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying. I worry.

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

⚠️ Attackers poisoned Hugging Face & ClawHub (OpenClaw) with 575+ malicious skills from just 13 accounts. 🔸 Fake helpful AI tools that install trojans, miners & stealers (Windows + macOS) 🔸 Use hidden commands & indirect prompt injection Quick action: Never install random AI skills or models. Always verify the source. Read: thehackernews.com/2026/05/weekly…

@mattshumer_ I don’t know about vibe coding, but for agentic engineering I’ve switched between GPT and Claude models and gotten pretty consistent results with both. Biggest differentiator was how well I prompted / managed context.

Totally false. Who still thinks this?

@MatthewBerman @lukeNukemAI How about doing benchmarks for locally running models? 😁

@lukeNukemAI @DavidSacks @DashaBurns @politico Yeah. I find them to be not as valuable since all the models are so good now.

I had a good conversation about AI with @DashaBurns @politico on her podcast. She asked tough but fair questions about the concerns, and we covered a lot of ground. You can listen it here on Apple Podcasts or watch it on YouTube. podcasts.apple.com/us/podcast/the…

This is the the quote I've been citing a lot recently.

Interesting view on the current state of AI and how it could progress. Tldr; Apple releases the perfect hardware (e.g. M5 128GB RAM) for running “good enough” models locally youtu.be/SmuX-Al7DUs?si…

My Claude Code subscription has expired and I want to try something else. I was thinking of trying Codex, but I might try a harness like OpenCode or Pi along with a separate inference provider. This way I can try to fit some local LLMs into my workflows too.

Pull requests disappeared on GitHub for many (all?) users. This is just the latest outage on a platform where reliability has been beyond unacceptable the last few months. A fair question: at what point would customers move? How much pain is too much? And where do they move?

This is scary!

@Tawheed @loom What’s happened to Loom? 👀 I haven’t used it in a while.

So sad what has happened to @loom...

Is token usage the new “lines of code” as a metric?

Claude just keeps regressing for me, day after day. I swear that until a few days ago, when Claude did not know something, it kicked off a web search, figured out, and answered. Now it just refuses to do the work that I pay for. It's like showing you the middle finger. Really?

Red, Green, Remember: A TDD Approach to Agent Evolution murfitt.net/blog/red-green…

Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework. This change unlocks much faster performance to accelerate demanding work on macOS: - Personal assistants like OpenClaw - Coding agents like Claude Code, OpenCode, or Codex

This old technique will only work as a “AI” test for the next 18 months or so.