Books read in 2026 📚

🔕 Sanity 🧘

Do you have colleagues or a boss who’s using AI for everything, but with zero taste, creating more work and confusion for others?

DON'T INSTALL the new golden gate 27 beta on Mac this shit has lot of bugs ! It feels snappy and has like some cool animations until you start facing random bugs - spotlight spawns randomly somewhere on screen rather then being in centre - cannot view my desktop just shows black screen when trying to switch - many more

The Mickey Mouse pointers are back in macOS 27

27 Dev Beta folks: Has anyone tried the new dictation that’s apparently lot more accurate? I really hope it is! @grok ^ #wwdc

Good folks of X, I'm hiring again - - Lead Product Designer - 7y (Fintech experience preferred) - Senior Product Designer - 5y (Fintech experience preferred) - Senior Product Designer - 4y x 2 Remote (India) only JDs and application process here - tally.so/r/rjkbO2

BREAKING: Uber engineers now required to earn Claude Code credits by driving Anthropic employees.

We are losing our handle on things now

Watch me control my computer with just my voice. This is the future of operating systems. No hands. GPT-Realtime 2.0 is very, very underrated. Demo:

I built an Android app called JotWell, over the past few days. I need a few Android users to help me test it before I open it up wider. It’s an expense tracking app I’ve been building to make logging spending feel simple, fast, and less like a chore. If you use Android, you can join early access, try it for a few days, and send me honest feedback. (1/2)

In case anyone was wondering how it's pronounced, you just gotta ask; respectfully Sound on 🔊

This is probably the first Ferrari (or any car?) video ever, where the Ferrari hasn't moved an inch (or should I say pixel?) If it's a car, I would like to see how it looks or feels on the road or track?

What started as building a personal taste.md skill for myself, turned into building a pipeline to create any taste as a skill. The most important piece is references. This is where you should spend time. If the references suck, so does the skill. I find that references cropped tightly on details in high resolution work the best. Each image gets analyzed by both Opus 4.7 and GPT 5.5. The analysis is based on why the reference is successful as a piece of design - not what it does functionally. Using two models helps rule out biases and gaps from each. The models focus on layout, spacing, typography, rhythm, composition, hierarchy, etc. At the end, each image has: reference-01/ - opus-4-7-analysis.md - gpt-5-5-analysis.md Then we fuse them together using GPT 5.5 - but the md files are anonymized so 5.5 doesn't prefer itself. reference-01/ - fused-analysis.md reference-02/ - fused-analysis.md etc. After fusion, we have one synthesized analysis per reference. Now the goal is to combine all of those into a single rule set. This is where chunking matters. If you ask one model to combine 100 image analyses at once, the result becomes too broad. It summarizes instead of preserving the granular design rules we want. Instead we chunk the fused analyses into smaller groups. Each group gets merged into a chunk-level synthesis, usually from around 6 to 8 image notes at a time. Then one final model pass fuses those chunks into a single md rule set. Finally, using the rule set, we write a skill of concrete instructions. It enforces constraints, uses imperative wording, and avoids vague taste words.

it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ultra. oh agents? you do that in spark actually. no, not gemini api managed agents, that’s different. for coding use jules. unless you mean the agentic ide, that’s antigravity. no, that’s the old antigravity, download the new one. actually gemini cli is being deprecated, use antigravity cli. no the flash model is smarter than the pro model. unless you need pro. if it’s video, use flow. no, flow uses veo. no, nano banana is images. actually that’s in gemini now. unless you’re in search, then it’s ai mode. no, research is notebooklm. anyway it’s all very simple.

Tibo doesn't miss a chance! 😂 Is Codex running his Twitter account?

Least to say GoogleIO has lived up the hype! 🧑‍🍳

Faaak! Epic

Today we're launching Index: a platform for content owners to understand how AI agents use their work, and earn revenue when they do. Our first partners include @TheAtlantic, @FortuneMagazine, @PRNewswire, @PitchBook, @ZoomInfo, @Tracxn, @RocketReachCo, @enigma_data, @fiscal_ai, plus creators @alexeheath, @mariogabriele @azeem, @every, and @packyM.

Composer 2.5 - One shot Using Cloudflare's Kumo component library. It's so good!