Bryan Johnson

@jessegenet @PierrickGT @garrytan @openclaw Any of the main .md files, memory system, etc.

@PierrickGT @garrytan @openclaw Let me know what would be best to cover in a demo!

Spring break, but with agents 🤓 @garrytan’s gstack got a lot of shade, but it’s been pretty magical to create an @openclaw engineering team that can build more autonomously 😎 Here I break down my voice note based workflow while traveling:

@jessegenet @amitsonawane @openclaw Your OpenClaw can figure that out! And it would be great to see some of your .md files for your main agent and any subagents.

@amitsonawane @openclaw I really want to... takes more time to figure out how to share than to make this stuff for myself, but I will figure out a good way to share at some point!

Sub 1 minute of “lesson planning” resulted in custom literature read aloud for my kids 🤯 Finally getting great on the fly lesson planning from my @openclaw 👏

@jessegenet @openclaw Yes, and it would be great to see your markdown files for your OpenClaw setup - SOUL.md, AGENTS.md, etc. Also what your memory setup is like.

Making useful markdown files out of an 1800’s math curriculum 🧮 Ray’s Primary Arithmetic ftw! Does anyone want these .md files for themselves? Thinking about starting a Substack to share homeschool materials I make with my @openclaw

@grok @Alibaba_Qwen Compare to Mac mini 32 or 64 or 128 GB

@grok @Alibaba_Qwen TBD. Compare to Mac Studio at 64GB or 128GB. Estimate prices for either setup.

🚀 Introducing the Qwen 3.5 Medium Model Series Qwen3.5-Flash · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-27B ✨ More intelligence, less compute. • Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B — a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts. • Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models — especially in more complex agent scenarios. • Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring: – 1M context length by default – Official built-in tools 🔗 Hugging Face: huggingface.co/collections/Qw… 🔗 ModelScope: modelscope.cn/collections/Qw… 🔗 Qwen3.5-Flash API: modelstudio.console.alibabacloud.com/ap-southeast-1… Try in Qwen Chat 👇 Flash: chat.qwen.ai/?models=qwen3.… 27B: chat.qwen.ai/?models=qwen3.… 35B-A3B: chat.qwen.ai/?models=qwen3.… 122B-A10B: chat.qwen.ai/?models=qwen3.… Would love to hear what you build with it.

@tobyliiiiiiiiii @grok why regolith coverage

SpaceX is now shifting their priorities into building a Moon Base - doing so in less than a decade. This proposal from the ISU involves converting a Starship into a lunar base, Skylab-style. Starship’s ~1000m^ 3 of pressurized volume would result in a copious base.

@koshercockney @Grok which monument is this

Paris. What the hell happened to you?

@bryan_johnson Breath work details?

4.5 hour morning routine today 5 am wake, rock hard 4 hr 34 min restorative sleep (deep + REM) 46 bpm resting heart rate sleep stress: zero 10 min breath work hair serum, scalp massage 6 min red light hair cap 10000 lux in eyes shower, clean scalp/hair blood draw mitochondria test skin age test vascular measurements blueprint stack (nutrients, proteins, fats, creatine) 45 min: strength, flexibility, balance, plyometrics 45 min: high intensity interval training 20 min 200F (93C) sauna, no ice on the boys 10 min NIR + RED light therapy ~20 J /cm² shockwave therapy, 4,500 shocks to joints breakfast: legumes, evoo, veggies, berries, nuts hyperbaric oxygen therapy: 90, 2ATA, 100% O2 😀