mager
31.9K posts

mager
@mager
Agentic Engineer @Uber 📈 Building @beatbrainxyz @prxpsxyz @loooomxyz ❤️ KLM
Chicago Katılım Ocak 2007
4.1K Takip Edilen11K Takipçiler
Sabitlenmiş Tweet

My first Japanese baseball game: Hanshin Tigers in Osaka mager.co/blog/2026-05-2… ⚾️ 🇯🇵 🐯
English

@hanshintigersjp Will the game be rained out tonight? We are visiting from Chicago and very excited to see the Tigers play! Hoping the rain isn’t too bad!
English
mager retweetledi
mager retweetledi
mager retweetledi


Killing my Openclaw setup for a native Claude experience mager.co/blog/2026-05-1…
English
mager retweetledi

The thesis is simple: the future belongs to individuals who build compounding AI systems, not to individuals who use corporate-owned centralized AI tools.
I'm trying to build these in open source so you can have them for free. That's what GBrain is.
Garry Tan@garrytan
English
mager retweetledi

SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
SIXERS WIN
....@SIXERS WIN
English

@courtney883 @tiffani I would obsessively check everyone’s away message. I used to put cryptic messages in there about my crushes.
English

Nothing better than hearing that “door open” sound and seeing your crush online. These were the days. Truly.
RetroNewsNow@RetroNewsNow
On May 1, 1997, AOL Instant Messenger (AIM) was released
English
mager retweetledi
mager retweetledi

Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights:
The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Three examples of new horizons:
1. menugen: an app that can be fully engulfed by LLMs, with no classical code needed: input an image, output an image and an LLM can natively do the thing.
2. install .md skills instead of install .sh scripts. Why create a complex Software 1.0 bash script for e.g. installing a piece of software if you can write the installation out in words and say "just show this to your LLM". The LLM is an advanced interpreter of English and can intelligently target installation to your setup, debug everything inline, etc.
3. LLM knowledge bases as an example of something that was *impossible* with classical code because it's computation over unstructured data (knowledge) from arbitrary sources and in arbitrary formats, including simply text articles etc.
I pushed on these because in every new paradigm change, the obvious things are always in the realm of speeding up or somehow improving what existed, but here we have examples of functionality that either suddenly perhaps shouldn't even exist (1,2), or was fundamentally not possible before (3).
The second (ongoing) theme is trying to explain the pattern of jaggedness in LLMs. How it can be true that a single artifact will simultaneously 1) coherently refactor a 100,000-line code base *and* 2) tell you to walk to the car wash to wash your car. I previously wrote about the source of this as having to do with verifiability of a domain, here I expand on this as having to also do with economics because revenue/TAM dictates what the frontier labs choose to package into training data distributions during RL. You're either in the data distribution (on the rails of the RL circuits) and flying or you're off-roading in the jungle with a machete, in relative terms. Still not 100% satisfied with this, but it's an ongoing struggle to build an accurate model of LLM capabilities if you wish to practically take advantage of their power while avoiding their pitfalls, which brings me to...
Last theme is the agent-native economy. The decomposition of products and services into sensors, actuators and logic (split up across all of 1.0/2.0/3.0 computing paradigms), how we can make information maximally legible to LLMs, some words on the quickly emerging agentic engineering and its skill set, related hiring practices, etc., possibly even hints/dreams of fully neural computing handling the vast majority of computation with some help from (classical) CPU coprocessors.
Stephanie Zhan@stephzhan
@karpathy and I are back! At @sequoia AI Ascent 2026. And a lot has changed. Last year, he coined “vibe coding”. This year, he’s never felt more behind as a programmer. The big shift: vibe coding raised the floor. Agentic engineering raises the ceiling. We talk about what it means to build seriously in the agent era. Not just moving faster. Building new things, with new tools, while preserving the parts that still require human taste, judgment, and understanding.
English

@kieranklaassen Autopilot or auto repo or self healing software or software hospital?
Čeština


Get ready. New @digg coming. Been using it - it’s fire. 🔥 @kevinrose and team cooked
Kevin Rose@kevinrose
English







