Julio Tinoco

Using OpenClaw is basically is like driving your own Ferrari (that you have to be a mechanic for yourself) and it's broken down all the time, but gives you the time of your life vs driving a reliable Honda (Hermes Agent) vs riding the bus (Claude / ChatGPT)

I’ve wanted to do this for a decade. But I never did - I refuse to give any company my DNA. It is me. So this week I sequenced my genome entirely at home. Literally on my kitchen table. I never exposed my DNA sequence to the internet. Not at any point. I used a MinION to do the sequencing (it’s smaller + weighs less than an iPhone). I used open-source DNA models for the analysis (Evo2 and AlphaGenome) running locally on a DGX Spark and Mac Studio. I traced mechanisms behind my family’s multigenerational autoimmune conditions that no clinician has been able to understand. When I set out to do this I didn’t know if it would actually work. It does. Your genome is the most private data you will ever have. You probably shouldn’t let it leave your house.

Kosmos and the other Edison agents have the best access to biological data today, which is critical for making new scientific discoveries. Here's an example of our Analysis agent identifying how genetic mutations alter brain development in autism, reproducing results from a recent paper. In their recent Nature paper, Gordon et al. measured the effect of genetic mutants on autism using patient iPSC–derived cortical organoids and time-resolved bulk RNA-seq, revealing genotype-linked expression similarities of ASD forms and their strongest divergence from normal organoids at the earliest stages. In our new post, the Edison Analysis Agent autonomously reanalyzed the public dataset and reproduced both key results, recovering genotype-driven clustering of ASD forms and independently recapitulating their “early divergence, later convergence” trajectory across development.

Claude Sonnet 5 drops next week. ↳ 1M context ↳ Half the price of Opus 4.5 ↳ Best-in-class for agentic coding ↳ crushes Opus 4.5 at coding WHILE BEING 50% CHEAPER ↳ new Swarm feature lets you spin up *multiple teams* of agents that run in parallel and use claude code THEMSELVES ↳ basically an entire dev team on your computer but they work 10X as fast. ↳ 1M context window, SOTA SWE bench they're also hiring security researchers for "self-improving AI" which means this model can likely build a better version of itself autonomously.

This is absolutely insane and proof that voice is about to transform the workplace. At Wispr, employees use voice hundreds of times a day to multitask across their entire workflow. Here’s one dev using Cursor and Gmail simultaneously, all through WHISPERING, on a $10 mic.