I sequenced my genome at home, on my kitchen table.
I wrote up exactly how I did it - the equipment, protocol, theory, and cost:
https://t.co/Nkjqaho2zm
I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!
As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently:
"openai/gpt-5.1",
"google/gemini-3-pro-preview",
"anthropic/claude-sonnet-4.5",
"x-ai/grok-4",
Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response.
It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses.
Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain.
That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored.
I pushed the vibe coded app to
https://t.co/EZyOqwXd2k
if others would like to play. ty nano banana pro for fun header image for the repo
If you still believe COVID left the population “unchanged”, open a dating app. It sounds absurd, but stay with me here.
The cognitive bluntness is so widespread that the dating platforms themselves have had to acknowledge behavioural deterioration since 2020.
It’s not subtle🧵
oh my.. hows this even possible
Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model
the model is free to download and test in playground
link in comments
This is a 192 megapixel photo of our home, the milky way Galaxy.
Until recently it was my highest resolution deep space photo ever. Next week I will share a galaxy photo that is double the resolution... but there's a catch.
The galaxy I shot is 2.5 MILLION light years away!
The Driller Bot from #Transformers Dark of the Moon was the most complex asset ILM had done for Transformers by that point. It had 70,000 individual parts, over 7x more than Optimus Prime.
This sequence where it is crushing the skyscraper took 288 hours per frame to render with all of the reflections and simulations.
During the last weekend, ILM used their entire render farm, amounting to 200,000 rendering hours per day which is 22.8 years of rendering time in 24 hours.
Finding beauty in beauty is easy, boring.
The interesting thing is learning to find beauty in the ugly, in the strange, in the bizarre, in the chaos...
Once learned, beauty is everywhere, and what was originally beauty moves to a secondary plane that we can always revisit.
Being an artist is an intimate, personal experience.
We share our desires, imagination, subconscious thoughts, fears, pains, hopes, and dreams & transmute them into a visual language called “art.”
never compare. what you create is unique to you and by you. the right collector will come when the time is right. keep working, keep developing. enjoy your progress you make.