Sample

Basketball, American democracy, and Computer science

[Sample @sample]

Musk makes verification a false flag devoid of meaning and then spends verification resources hunting down false authenticity? What kind of nonsense... ? 🤔🧠💡

[Sample @sample]

@Official_m9g @GoogleAIStudio @GoogleAI Did they change something? Flash 3.8 for a while was lightning fast right? That was the entire upside of it against everything else. Completely capable but lightning fast

[Sample @sample]

@brianmccormick Exactly! How did they build the motor control necessary to develop those micro-adjustments in the first place? Through volume. Isolated hammering practice 🙀 That's what gave the nervous system thousands of opportunities to refine those "error correction loops"

[Sample @sample]

Elon Musk should be smart enough to know Russia isn't an honest actor, and granting sanction to their occupation is only launching ground for future invasion. Ukraine is successfully defending their country currently.

[Sample @sample]

@azlenelza I guess if it were you'd have a whole new dimension 😵‍💫

[Sample @sample]

@azlenelza It's interesting in visualizing the block's traces you can kind of make out what happened. It's also confusing how some of the people are "small" and some are large, because depth isn't relevant in the block.

[Sample @sample]

@azlenelza The block universe

[Azlen @azlenelza]

Continuation of my old video-as-3d-object demo

Always wanted to extend it further with segmentation so you can search for any type of object within the scene

[Sample @sample]

@CoachHackGO Social media needs a standard that every single "look at this awesome play" clip need to be backed with multiple versions that (unlike the majority of them) don't show simple, unforced, defensive mistakes

[Aaron Rupar @atrupar]

Trump: "Nobody knows that dumb has a B on the end"

[Sample @sample]

@thtbee_ The "release" a week ahead of release was interesting ... 😑

[Sample @sample]

@shengzheyao Develop locally on your phone's filesystem 😂. We don't even have Remote Work in the mobile Gemini app yet. 🤦‍♂️

[Sample @sample]

@qxmzu @opynrijal @shengzheyao Develop locally on your phone's filesystem 😂. They don't even have remote control in the Gemini app yet right? 🤦‍♂️

[Sample @sample]

@opynrijal @shengzheyao Develop locally on your phone's filesystem 😂

[Sample @sample]

What the heck, this is so weird. What's the use-case for a terminal client on your phone? 😑 Plus Gemini app doesn't even have Remote built in yet so... 😑

[Shengzhe @shengzheyao]

Antigravity CLI is coming to your phone 📱

With 1.2.15, agy now runs on Android via Termux.

Yes, the full agent. In your terminal. On your phone.

Code, debug, or kick off an agent from anywhere.

Try it on Termux:

curl -fsSL https://t.co/b23iPtEhhu | bash

Then run agy.

[Sample @sample]

Good analogies

[Kun Chen @kunchenguid]

there’s now a new mental model for the software stack

- skills are the new “apps”

you install them to get more functionality. people are starting to build and share skills more than real “apps”

many skills are very simple today but i think we’ll eventually see increasing sophistication

- mcp servers and CLIs are the new “APIs”

they allow services to encapsulate their core capabilities behind an interface the can be invoked in a composable way

many skills will be calling mcp servers or clis behind the scenes just like how a lot of apps call APIs today

- agent harnesses are the new “operating systems”

it sits between the user and the underlying resources, helping the user manage common concerns such as compute, memory, security etc

if you look closely, it’s hard to unsee the resemblance - claude is the new macos. codex is the new windows. pi is the new linux

skills run in agent harnesses just like apps run in existing OS

- LLMs are the new “computers”

they process instructions coming from the user, the skills, the agent harnesses, and compute the output

the model weights is the cpu. context window is the memory. actual computers are becoming more like the power source

ok so why do we need this mental model? i think it helps us think about where we play

if you want to be the new app developers - start to learn to write good skills

if you want to build a saas, figure out how to package things as good mcp servers and CLIs

if you want to be linus and write the new linux, build an agent harness. otherwise, you can still try to learn about how agent harness work like how CS students used to learn about OS

if you want to be the new apple or samsung, start to learn how LLMs are trained and play with open weight models - you may end up inventing the new raspberry pi!

[Brian McCormick @brianmccormick]

@PaulSpacey @justinskycak Is research on the violin and chess directly applicable to team sports?

[Turnbull @cturnbull1968]

“I know a guy. He can do the whole thing for $1.3M and get it done it two weeks.”

- Donald Trump

[Headquarters @HQNewsNow]

Trump defends the men in the Cornell gang rape case, saying he “feels bad” for them and they won't get a “fair shake”

[Rep. Jim McGovern @RepMcGovern]

I never thought I’d see the U.S. government try to whitewash Richard Nixon’s crimes & defend his profound abuse of the presidency. But here we are. Crooks protecting crooks.

[Sample @sample]

@kentcdodds Go ahead