Sabitlenmiş Tweet
Aaron
2.4K posts
Aaron
@aaronbatilo
Putting the ML in YAML. Eng @CoreWeave. Previously at @MicrosoftAI, @InflectionAI, @Cohere, @Color I like smash melee
Colorado, USA Katılım Haziran 2014
160 Takip Edilen311 Takipçiler
he does this on purpose when he doesn’t get his way.
it’s like having another toddler.
English
Me: man, I need a filesystem for my database
This guy:
Mike Freedman@michaelfreedman
Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL. Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database. There are two ways to use it: File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories. Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills. Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API. Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost. I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome. tigerfs.io
English
Just gave a talk at GTC (about RL ofc). Bucket list item checked off!
English
turns out that google's core structural advantage in the AGI race is that its hq in mountain view is too far away from sf for the pause ai people to get to
David Krueger@DavidSKrueger
A week from today, we will be at Anthropic, OpenAI, and xAI, demanding that leaders agree to a conditional AI pause. These companies are recklessly endangering all of our lives. Their excuse is that they can't pause unilaterally. So they must commit to pausing if others do.
English
Aaron retweetledi
@dylan522p Mf you're not in the crowd. You're probably in some lovely air conditioned green room
English
I just witnessed someone in front of me market buy Nvidia stock as Jensen is talking and then post screenshots on WeChat alongside his view from the crowd
English
Apparently, no one codes after lunch?
cat@_catwu
It’s a great time to build something new! For the next two weeks, we’re doubling rate limits on weekends and outside 5-11am PT on weekdays
English
One of the crispest articulations I have for how models have gotten better compared to last year: if the sequence of things it should do is spelled out, they will reliably do it. This includes asking the LLM to revert things it did, or asking it to do it again with the plan.
English
@clairevo @thesamparr Executives across my entire company ask me to talk to their ICs. Not just engineering.
1. Get people curious, teach them the most accessible possible version of what these models do and how they work
2. Show them what's possible
3. ???
4. Prompt
English
@thesamparr It’s 3 things: you gotta change your culture, blow up the operating model, and actually fix your code base.
You can only drag people so far, then it’s a combo of sticks (no headcount, tied to comp) and carrots (fun hack weeks, build in public, promos)
claire vo 🖤@clairevo
I quit my executive job to live the AI-native startup life. And I've spent years studying what it takes to shift an existing team to a new way of working. In my experience, it takes 3 things: - a new operating model - technical readiness (prepare the repos!) - cultural change I'm SO psyched to be kicking of this very limited @MavenHQ weekend course (April 18-19) for EPD executives and super senior ICs with my friend Zach at LaunchDarkly, a Principal Engineer that went from AI-skeptic to the AI-champion in our team. This is NOT for - ICs looking to learn things like claude code - people wanting high level consulting fluff - small teams who are already yoloing the tokens This IS for - VP+ executives in product, engineering, and design - staff + engineers - 100+ person teams who need to move AI mountains @gaganbiyani has been asking me to put something together for several years, and I said I would only do it if it was something I really thought I could uniquely speak to, was technical, and focused at my peers. This is that. I'm also excited we'll have @chintanturakhia and @thenanyu as guest speakers to talk about what they're seeing and doing as EPD leaders. We just opened enrollment, and recommend you register as an exec-sr. IC pair to get the most out of the content: maven.com/clairevo/ai-na…
English
How is everyone getting team adoption for Claude?
I spent a lot of time on Twitter, as do you. We see all this AI stuff popping up. We're on top of it, or at least sorta. I know what's going on and are testing all these fringe ideas.
But how are all you people getting your team to actually use it effectively without spending all their time on Twitter and learning, which we know they won't and probably shouldn't be?
English
--dangerously-skip-permissions
is how I run Claude Code
also how I run my life
English
this post is undefeated @jeffreyhuber
every wave of fresh grads, like clockwork
Kevin Gu@gukevinr
give your agents a db, not just a file system x.com/gukevinr/statu…
English
I’ve started referring to all of you as “my friend” by the way
English
