Sanket Pathak

Books read in 2026 📚

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.

@idlyupma Custom UI for search + learning, agentic payment layer, plus most things baked into the good old search UI seems like a pretty massive breakthrough in bringing AI to consumers

@sanketpath any particular highlight?

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

@thsottiaux Codex

How do you refer to it

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?

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!

@_swanand Did you mean Neuralink? :P

I need a Granola for my mind, which listening to my thoughts and sending me structured notes later.

It's time for interfaces to break out of flat land. Lately, I have been experimenting with spatial experiences supported by foundational gestures. Truly feels magical.

Bengaluru in a bit:

Like how we used to user test on entry level android devices + edge connections gauge true user experience. It must be mandatory for devs at LLM orgs to use a limited tier account atleast once a month for work :p

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.

highly recommend making a small silly thing while agents are working on your work stuff. i made a lasso throwing game: yeehaw-roundup.vercel.app it's fun and easy and mindless 👢 exciting what a random idea can do with claude + gpt + vercel in just under an hour!

Honestly, so happy to see GitHub gang taking over my feed today! Team, especially design engineering team, cooked 🤌

@iprithvitharun Cooking 🍳 Don’t mind at all.

@sanketpath @conductor_build I've got something for you harmonic.build Mind being a beta tester.

Hey @conductor_build, how can I use Opus 4.6? (Not the 1M - API model).

If you use Next.js, read this and update.

@aviaviaviii Walks and voice journaling > Schedule to fetch voice journal via Monologue MCP > run it through voice clean up skill ✨ github.com/sanketpath/age…

the sudden motivation in life to journal / do morning pages / 750 words is real, thx to second brain

Claude Code weekly limits are increasing 50%, now through July 13. Live now for all Pro, Max, Team, and seat-based Enterprise users.