Advertisement · 728 × 90

Posts by Bryan Russett

Enough DDR5 to pay for a house

Enough DDR5 to pay for a house

I feel like a million bucks

7 hours ago 173 11 12 3
Preview
A Rave Review of Superpowers (for Claude Code) I have no connection to the authors of the Superpowers plugin for Claude Code, but I have been raving about it to everyone I talk to. Using Claude Code with ...

For anyone using Claude Code, I cannot recommend the Superpowers plugin by @s.ly enough. I've been raving about it to enough people that I just wrote up my thoughts as a quick blog post emschwartz.me/a-rave-revie...

1 week ago 14 2 4 0
Reflecting on The Soul of a New Machine | The Observation Deck

RIP Tracy Kidder, who inspired so many of us, and gave us permission to feel unapologetic passion for our chosen craft bcantrill.dtrace.org/2019/02/10/r...

2 weeks ago 146 25 8 2
Preview
Instagram Create an account or log in to Instagram - Share what you're into with the people who get you.

Our latest foster. If you’re in the Bay Area consider adopting this sweet boy. He had literally been sedated to be euthanized when he was rescued www.instagram.com/reel/DWVIIbo...

2 weeks ago 13 1 0 0
Clash Write rules for your AI agent. Clash enforces them.

For a great example of why we are building clash.rs and why the power of being able to apply specific sandboxes to specific binaries is important.

2 weeks ago 2 1 1 2

Everyone has been asking for this writeup, now it’s live!

1 month ago 4 0 0 0
The butterfly meme where the butterfly says "context 95% full. start a new chat" and the guy says "is this AGI?"

The butterfly meme where the butterfly says "context 95% full. start a new chat" and the guy says "is this AGI?"

Context windows out to thwart all our beautiful dreams

3 months ago 45 5 2 0

On brand, @ahl.bsky.social and I are picking this one up on the podcast today. Join us at 5p Pacific for a wild tale of death by uptime!
discord.gg/QrcKGTTPrF?e...

4 months ago 32 5 1 2
Advertisement
More Output sorry boss, couldn't come in today, just wasn't energetically favorable

Assistant slides thermodynamics textbook across desk "I'm gonna need you to show your work on that Gibbs free energy calculation." AG = AH - TAS Where: • ДН = enthalpy of getting out of bed (highly positive) • T = temperature (it's cold out there) • AS = entropy of staying home in pajamas (maximized) Yeah... the math checks out. See you tomorrow. Maybe. Depends on the activation energy required.

More Output sorry boss, couldn't come in today, just wasn't energetically favorable Assistant slides thermodynamics textbook across desk "I'm gonna need you to show your work on that Gibbs free energy calculation." AG = AH - TAS Where: • ДН = enthalpy of getting out of bed (highly positive) • T = temperature (it's cold out there) • AS = entropy of staying home in pajamas (maximized) Yeah... the math checks out. See you tomorrow. Maybe. Depends on the activation energy required.

i gave sonnet 4.5 a tool called `more_entropy()` that just returns random @ponder.ooo skeets and it **obsesses** over it
timkellogg.me/boredom/sonn...

6 months ago 17 1 0 0

I see someone else made this joke already but I’m going to hold this bag

6 months ago 3 0 0 0

Would be funnier if they didn’t allow people named Sam to join

6 months ago 2 0 1 0

if you know any folks dealing with (or trying to get out ahead of) that security nightmare, please connect me :)

7 months ago 0 0 0 0
Preview
This MCP Server Could Have Been a JSON File There's a lot of buzz around MCP. I'm not convinced it needs to exist.

Great post by @chris.blue materializedview.io/p/mcp-server...

7 months ago 9 5 0 0

love that place

7 months ago 1 0 0 0

lol

7 months ago 0 0 0 0
Text reads: Mozilla, in its finite wisdom, embedded LLM bots into recent versions of Firefox for the vitally-important purpose of... naming tab groups. Now, some users are noticing CPU and power usage spikes caused by a background process called Inference.

Ugh. Reminder again for Firefox users to visit your about:config page, search for the browser.ml.chat.enabled key, and set that to false:

Displayed is a screenshot of Firefox showing the config search bar with the listed search. The word "false" is circled in red.

Text continues: If yours says true then double-click it until it reads false.
Doing that turns off the Al chatbot features in Firefox, but also the stupid new LLM tab-naming feature that's rolling out.

Text reads: Mozilla, in its finite wisdom, embedded LLM bots into recent versions of Firefox for the vitally-important purpose of... naming tab groups. Now, some users are noticing CPU and power usage spikes caused by a background process called Inference. Ugh. Reminder again for Firefox users to visit your about:config page, search for the browser.ml.chat.enabled key, and set that to false: Displayed is a screenshot of Firefox showing the config search bar with the listed search. The word "false" is circled in red. Text continues: If yours says true then double-click it until it reads false. Doing that turns off the Al chatbot features in Firefox, but also the stupid new LLM tab-naming feature that's rolling out.

Just a heads up to anyone using Firefox:

7 months ago 1381 707 37 46
Advertisement
Since I love collecting questionable analogies for LLMs, here's a new one I just came up with: an LLM is a lossy encyclopedia. They have a huge array of facts compressed into them but that compression is lossy (see also Ted Chiang).

The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters.

This thought sparked by a comment on Hacker News asking why an LLM couldn't "Create a boilerplate Zephyr project skeleton, for Pi Pico with st7789 spi display drivers configured". That's more of an lossless encyclopedia question!

My answer:

The way to solve this particular problem is to make a correct example available to it. Don't expect it to just know extremely specific facts like that - instead, treat it as a tool that can act on facts presented to it.

Since I love collecting questionable analogies for LLMs, here's a new one I just came up with: an LLM is a lossy encyclopedia. They have a huge array of facts compressed into them but that compression is lossy (see also Ted Chiang). The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters. This thought sparked by a comment on Hacker News asking why an LLM couldn't "Create a boilerplate Zephyr project skeleton, for Pi Pico with st7789 spi display drivers configured". That's more of an lossless encyclopedia question! My answer: The way to solve this particular problem is to make a correct example available to it. Don't expect it to just know extremely specific facts like that - instead, treat it as a tool that can act on facts presented to it.

An LLM is a lossy encyclopedia simonwillison.net/2025/Aug/29/...

7 months ago 272 36 22 7

that seems to be the concern I’m seeing on socials right now, but it’s good to have a standard here I think

7 months ago 1 0 0 0
Preview
Cloudflare & Browserbase: Pioneering Identity for AI Agents For AI to be productive, agents need reliable, responsible web access. Browserbase provides web browsing capabilities for some of the largest AI applications. But today, websites can’t tell the differ...

This is cool

7 months ago 2 0 1 0

62 degrees and I just got a nice hug and cuddle from my toddler. It’s snuggle season

7 months ago 0 0 0 0
Vibe code cleanups specialist job titles on LinkedIn

Vibe code cleanups specialist job titles on LinkedIn

New job title just dropped on LinkedIn

“Vibe code cleanup specialist”

7 months ago 153 49 11 20

very cool! proud dad :)

7 months ago 1 0 0 0
Preview
A Conceptual Model for Storage Unification — Jack Vanlightly Object storage is taking over more of the data stack, but low-latency systems still need separate hot-data storage. Storage unification is about presenting these heterogeneous storage systems and form...

New blog post: A Conceptual Model for Storage Unification.

The post defines what storage unification means, defines terminology and evaluates different building blocks and approaches to doing it.

jack-vanlightly.com/blog/2025/8/...

7 months ago 7 2 0 0
Post image

[New Book Alert]

Systems Engineering for Agentic Applications

A guide for turning AI-powered prototypes into production-ready agentic applications

Released monthly, chapter by chapter.

If 100 people sign up, we are doing this

agenticapplications.substack.com/about

8 months ago 6 4 1 15

Reminder: our conversation with @scott.hanselman.com is this evening!

8 months ago 37 8 1 0
Advertisement
we are here to frame you
we are here to frame you YouTube video by number 0

We want you to build protocols!

For that, you need to know about message framing.

Conveniently, we produced a video about doing this in #rust on top of #QUIC with iroh :)

www.youtube.com/watch?v=h6bB...

8 months ago 27 4 0 1
Post image

We just launched Foursquare Spatial Desktop – a geospatial analysis tool powered by embedded DuckDB and built on sqlrooms.org. Everything runs locally: your data stays on your machine, no cloud needed. A modern reimagining of Kepler.gl. Mac only for now. More coming.
foursquare.com/products/spa...

8 months ago 62 15 2 0

amazing work all around 🙏

8 months ago 1 0 0 0

Awesome 🔥

8 months ago 1 0 1 0