Catherine Kim

intern @imbue_ai | fan of puzzles, musicals, and social deception games/shows

[Catherine Kim @inkycat]

best event ever! finding a clear career path as a generalist is such a "no right answer" problem so i was surprised to get so much applicable advice from all the panelists! I have a whole notes page full of takeaways. thank you @nikhilville for recommending this event!

[adel 🌟 @adelwu_]

held one of the most rewarding events last night with 100 of the most interesting people 💫

people said they felt so seen hearing from and meeting other people who never felt like they had clear career paths

i always screenshot feedback people send me so i can look at later 💖

thank you to my amazing inaugural panelists (@soleio @jocarrasqueira @maryrosecook & sarah) and venue @NotionHQ @ASalyers3 @brooks_hocog & emily) for all your support!

another event is in the works…TAG who you want to see below!! 👇

[Catherine Kim @inkycat]

@kanjun so proud of the team and excited for the other platforms 😎💪

[Catherine Kim @inkycat]

this >> not interested :( button that you have to click every single time

[Kanjun 🐙 @kanjun]

Twitter’s algorithm is optimized for addiction, not for us. We deserve better.

We’re releasing Bouncer today so you can take back control of your feed. Describe what you don't want, and Bouncer removes it.

It’s free, doesn’t collect your data, and will be open source soon.

[Kanjun 🐙 @kanjun]

Twitter’s algorithm is optimized for addiction, not for us. We deserve better.

We’re releasing Bouncer today so you can take back control of your feed. Describe what you don't want, and Bouncer removes it.

It’s free, doesn’t collect your data, and will be open source soon.

[Nikhil Kulkarni @nikhilville]

AGI? What about AG-us 🫶

[Catherine Kim @inkycat]

@adelwu_ i love the breadth-focused nature of this event!

[Catherine Kim @inkycat]

These games are amazingly fun to play and very creative! props to the team and super excited to get working on arc-agi-3

[ARC Prize @arcprize]

Announcing ARC-AGI-3

The only unsaturated agentic intelligence benchmark in the world

Humans score 100%, AI <1%

This human-AI gap demonstrates we do not yet have AGI

Most benchmarks test what models already know, ARC-AGI-3 tests how they learn

[Catherine Kim @inkycat]

@imbue_ai @modal never give up on a repo because you can't get it running again 💪

[Catherine Kim @inkycat]

--dangerously-skip-permissions with ease and grace

[Imbue @imbue_ai]

Teach your repo how to run itself 🦾💨

Introducing Keystone: a self-configuring agent inside a sandboxed @Modal container that generates a working dev container for any repo

→ pip install imbue-keystone

[Imbue @imbue_ai]

Offload just demolished xdist on our test suite

[Catherine Kim @inkycat]

@nikhilville ur welcome king 👑

[Catherine Kim @inkycat]

@imbue_ai @modal LOVE how fast it makes tests run

[Imbue @imbue_ai]

Your parallel agents needed scalable test coverage yesterday

Introducing Offload: a Rust CLI that spreads your test suite across 200+ @Modal sandboxes, freeing your CPU to keep your agents shipping.

On our Playwright suite, it took a 12 min run to 2, at $0.08 a run

[Imbue @imbue_ai]

…the average review takes 20mins and $25 💀

We made a better alternative. It’s called Vet and it’s basically free.

It runs in less than 30 secs (up to 5 mins for full PR reviews), only costs inference, and it can run in the loops agents work.

We open sourced it: https://t.co/Dq9U5CzII1

[Imbue @imbue_ai]

Your coding agent may be lying to you.

You ask it to write tests. It says they pass. It never ran them. You ask for a feature. It hits a wall and silently swaps in fake data.

We built Vet to fix this. It’s open source. Get the code below.

[Catherine Kim @inkycat]

@imbue_ai finally don't have to parse through all the reasoning to figure out if it lied 🙏🙏

[Catherine Kim @inkycat]

@thisisehsan @imbue_ai WORKING ON IT!! STAY TUNED FOR MORE IMBUE LAUNCHES 🎉

[Catherine Kim @inkycat]

@nikhilville lowk i hate bananas but the banana milk was too good

[Imbue @imbue_ai]

We built Evolver to improve our open source agentic code verifier, Vet. In other systems, we use it as an automatic prompt optimizer.

How Evolver works: https://t.co/tE94wpDX1q

How Evolver set a record on ARC-AGI: https://t.co/9Ix9oUXpTW