Sushaantu

I’ve been thinking about defaults - how they quietly decide outcomes - for a long time. I finally published a first draft of The Default Book. AI helped me accelerate the writing, but the ideas have been fermenting for years. Curious to hear what others think. 📖 thedefaultbook.com

Milei is correct - you can't negotiate with the left

Context:

The political left in Latin America creates problems for the political right to fix which requires budget cuts. Political left uses Palestinian style rejection by putting children/students on the forefront. Classic.

Openclaw has a been super useful for my workflow but pretty much every update breaks something and I have to be very cautious about tokens running out. *pointing out 2 areas where alternatives can target and make a space for themselves*

💯

OpenAI Symphony is good. Really good.

@_tenZdhon_ Remnants of when not everyone had an ID card to show their age

Just found out India has height based pricing Under 4.5 feet and you pay less Might be the new pricing strategy for consumer apps

@snowclipsed It used to be the other way round until a month ago

opus 4.6 as planner and 5.3-codex/5.4 as executor is pretty sick

@nateliason Same. Just switched to Opus in the end.

Codex 5.4 is such an amazing coder but so hilariously bad in OpenClaw. For some reason it is ~4-5x more likely to say "I'll do X" instead of actually doing it compared to Opus. Even Kimi & MiniMax do a better job here.

As long as a human is involved in decision making process - the AI race will come down to just vibes - agents with better vibes and intelligence will win. Intelligence alone might not be sufficient

Anthropic is still the goat when it comes to personality of its agents. It feels like talking to a really smart helper who gets you.

NotebookLM, like most AI tools is great when you need to condense information. It absolutely blows when you give it a small idea and ask to expand on it.

Tried @openclaw with GPT 5.4 and it is no where as smart as Opus.

@ejae_dev @openclaw Not yet but excellent idea

@Su @openclaw have you tried piping gws output into openclaw agents yet? the structured json should plug right in

Newly launched GWS CLI with @openclaw will be amazing github.com/googleworkspac…

Frontend design skills just plaster Instrument Serif and call it a day

we recently started an agent experience team at cloudflare, the space is changing so fast that almost every week a new pattern emerges... i've been pulling together patterns, tools, and best practices as a collection to help keep me up to date

I felt fairly comfortable using Codex in the terminal, but the Codex App is goated. Once I got past the initial hurdle, it’s faster than working in the terminal.

Codex is my angel investor

@soumitrashukla9 The tweet I was looking for to switch from Claude Max -> Codex Pro Thank you

My main issues with Codex over CC are now solved: 1) Speed: Conditional on quality, codex 5.3 is much faster than CC (and its quality is often better too btw than Opus 4.6) 2) Compaction: I’ve been running a single session since Sunday and I’m approaching O(1000) compactions. No performance degradation, memory loss, context mishaps AT ALL. CC and Codex are not perfect substitutes for me anymore, as they were for the past three months. Codex 5.3 is clearly superior now — and by a long shot. (CC is a “nice to have.”)