Michael Brawn

Tech Whisperer, Software Developer. My views are my own. He / Him 🌈 💻🏕️

[Rodney @_ChanFace]

What's next?

- It goes to City Council May 20
(TEYCC is just DT councillors)
- City Staff still need to figure out a feasible plan
- We need to start organizing a community group to steward the space & make it a success! Plants, art, performances, street cleaning, & supports!

[Colin D'Mello | Global News @ColinDMello]

NEW: An advocacy group is planning to file a constitutional challenge to Ontario’s freedom of information clampdown, arguing it breaches the right of voters to be informed for a meaningful debate about public issues.

https://t.co/4saPiQQQ0x

#onpoli

[alex huot @alexhuot]

The list is longer than the song.

[Michael Brawn @MichaelBrawn]

@bytecrafter_1 @wesbos Not really though.
“Hey AI”, order my daily Starbucks, tell me my calendar for today, then put on my driving playlist.

[Michael Brawn @MichaelBrawn]

@wesbos @fanivi_ I thought of this as one AI entity that can get inside your apps.
Apps expose the APIs or the AI can “open” the app in the background (with permission) for not yet supported behaviours.
I don’t need a Starbucks applet running though AI chat as my primary use case. Maybe both?

[Michael Brawn @MichaelBrawn]

@jessegenet You can pretty much do the same thing on the much smaller and cheaper! @useTRMNL https://t.co/MzMlJTSZVb

[Michael Brawn @MichaelBrawn]

@GamewithDave https://t.co/d6uMuGOkR2

[Michael Brawn @MichaelBrawn]

@Godefroy @varun_mathur Depends on the latency and more than bandwidth.

https://t.co/pKRSYm2mdq

[Michael Brawn @MichaelBrawn]

@ManuelBichler @gitchad @varun_mathur First, shared inference at home across all your running devices.

[Varun @varun_mathur]

Introducing Pods

Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL.
A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management.

There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own.

Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live.

What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data.
- No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on.
- Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online.
- Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it.
- Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using.

Coming soon:
- Pod federation: pods form alliances with other pods.
- Marketplace: pods with spare capacity can sell inference to other pods.

[Michael Brawn @MichaelBrawn]

@solarscenes

[Michael Brawn @MichaelBrawn]

@humeancartesian @NoahRyanCo Frustose has to be converted to glucose in the liver first. Glucose can be directly absorbed into the bloodstream.

[Michael Brawn @MichaelBrawn]

@jasondoesstuff https://t.co/cbqhfvLIto

Save skill /visual-slideshow

[Michael Brawn @MichaelBrawn]

@karpathy I was thinking the same for skill scripts/code. Instead of providing agent skills with scripts or coded tools, simply provide templates or base skills and let the users agents evolve scripts as needed for the users needs.
Ex. X post injest skill md. Implementation deferred.

[Michael Brawn @MichaelBrawn]

@karpathy Has anyone put together the skill repo yet?

[draw.io @drawio]

https://t.co/AngZk3kiDe diagrams now stream into Claude as they're generated. Shape by shape, edge by edge. https://t.co/PBT5bhFMDC

[Daniel San @dani_avila7]

Claude Code 2.1.90 just dropped with a new /powerup command

Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool.

It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop.

Going to keep digging into this new release!

[Saurabh Suri @surim0n]

pitched the city of toronto on a free hackathon where builders use public open data to solve real city problems. top AI lab funding the grand prize. zero cost to the city. during the biggest tech week in the country.

their answer: "concerns about branding." so it got killed by "leadership"

the data is public. the builders are ready. the city said no to people volunteering to fix their problems for free.

so we're doing it anyway.

every participant gets API credits. winners get cash prizes, credits, and merch. judging panel includes engineers from the lab itself.

we need two things:

🏢 a venue partner - if your company, university, or org wants 150 of toronto's best AI builders in your space for a day, dm me. (space must have good vibes and be central to the city)

🧩 a nonprofit or community org with a real problem - we'll point the builders at it. housing, transit, food security, whatever. if the city won't bring the problems, someone else will.

the city couldn't figure out the paperwork. maybe you can.

the city doesn't have to show up for the city to benefit.

cc: @oliviachow @EvanLSolomon @fordnation @buildfutureto @cityoftoronto @MarkJCarney

[Claude @claudeai]

Computer use is now in Claude Code.

Claude can open your apps, click through your UI, and test what it built, right from the CLI.

Now in research preview on Pro and Max plans.

[chiefofautism @chiefofautism]

someone at ANTHROPIC just showed CLAUDE finding ZERO DAY vulnerabilities in a live conference demo

claude has found zero day in Ghost, 50,000 stars on github, never had a critical security vulnerability in its entire, history...

it found the blind SQL injection in 90 minutes, stole the admin api key, then did the exact, same thing to the linux kernel