syl.py⚡️

Growth & sheets @augmentcode | ex-CRO at @Pusher | ex Growth @Census

[Luke Wroblewski @LukeW]

the most impactful change in tech.
the most quoted scene in tech comedy.
52sec and vertical (cause it has to be).
⬇️

[syl.py⚡️ @Copypastaa]

@robinebers have you tried Intent by Augment ? https://t.co/mXBkzqc3jL

[syl.py⚡️ @Copypastaa]

Intent is packed with so many features, and we ship new ones 3 times a day, it seems.

Agents can now comment on each other's specs to collaborate

- Main agent writes the core spec.
- get other agents (security, perf, design, etc) to review & comment

🧙

https://t.co/DOnWY5LMs0

[Amelia Wattenberger 🪷 @Wattenberger]

https://t.co/ZGHFYwy6jq

[Chris Kelly @amateurhuman]

It's Auggie CLI Hackday over at @augmentcode, what better time to get Auggie in @zeddotdev.

[Augment Code @augmentcode]

Yesterday's Tasklist launch didn’t exactly surprise early users.

Turns out they spotted the feature weeks ago.

So this time, we built something unpredictable.
Something no one could guess.
Something no one wanted.
(Except one guy. As a joke.)

We shipped it anyway.
Power users found it early (again).
And somehow… it sold out instantly.
Introducing the world’s first B2B GaaS™: Augment Grass

Real 3x3” squares of authentic grass, delivered to your desk.
🔒 SOC2 compliant
⏳ 24/7 grass support
😌 10,000+ grounded devs

Ask around. They’ll tell you: it’s straight GaaS.

🌱 https://t.co/Tk7zaKADrB

[syl.py⚡️ @Copypastaa]

@garrytan Companies seems to be doing ok on large codebase with Augment Code

https://t.co/PefMHN4ZOJ

[Rowan Trollope @rowantrollope]

I did a side-by-side of Cursor (with Claude 4 & Gemini 2.5) vs AugmentCode on a medium-size codebase.

Easy Task: make a sidebar collapsible.

Cursor+Claude/Gemini failed—multiple back-and-forths, never got it working.

AugmentCode nailed it on the first try.

I find Cursor gets increasingly confused as codebases grow. Feels like more work than help—leaving me exasperated and thinking I should’ve just done it myself.

Switching to @augmentcode

@laserlikemike

[Amir @AmirNagri]

@augmentcode has been hands down the best AI editor I have used, and I am not saying it lightly, as I have been a very early user of @GitHubCopilot , then I switched over to @cursor_ai and use it for a long time, I also dabbled with @windsurf_ai .

contd...

🙏🔁 RT/❤️Like

[Augment Code @augmentcode]

Introducing Remote Agent - cloud-based dev agents with full-codebase context, deep IDE integration, and full toolchain access.

Available in VS Code.

[Dan McAteer @daniel_mac8]

🚨 NEW: Augment Code (@augmentcode)

💥 >>> the first AI Coding Agent built for large codebases

Augment Code is an AI agent that:

>> uses Sonnet 3.7 and o1 together

>> has a context window of 200k

>> tops SWE-Bench at 65.4%

🎯 free to use while in early access

check it 👇

[syl.py⚡️ @Copypastaa]

Augment Agent is live, my favorite feature? MCP integration.

My Favorite MCP? Spotify.

Auggie know that I love some lo-fi in the morning and automatically start a play for me 🫡

[Augment Code @augmentcode]

🧵We just released the #1 open-source agent on the SWE-bench Verified leaderboard by assembling the best of Claude Sonnet 3.7 and O1.

Open-source repo here: https://t.co/gcKeWuogTQ

Here's how we achieved 65.4% success rate on the hardest coding benchmark in the industry: 🧠👇

[syl.py⚡️ @Copypastaa]

@colin__flaherty @jyangballin Let's get that blog going! <3

[Colin @colin__flaherty]

Just bumped into @jyangballin on Stanford campus and discussed future of coding agents and swebench/sweagent. Very happy such smart and kind folks are working on this important problem with an open-source POV. The future is bright ☀️

Strongly believe open source is critical puzzle piece in AI safety story over the coming decade. To play our part, my research colleagues at Augment and I will begin by posting a blog post soon detailing all our learnings and hard-learned discoveries building coding agents for swebench

[syl.py⚡️ @Copypastaa]

@petergyang Checkout https://t.co/erFNWxyxfN. This is literally the reason we built it in the first place. We focussed a lot on code retrieval and providing the agent full context.

[syl.py⚡️ @Copypastaa]

After Deepseek R1, Grok3 is now out. Toping a bunch of benchmarks.

If it's not that hard to make frontier models, why do we still need OpenAI and Anthropic?

Actually no /s on that one

[syl.py⚡️ @Copypastaa]

@mckaywrigley check out https://t.co/erFNWxyxfN. Already great, more amazing stuff coming soon™

[Augment Code @augmentcode]

Learn how Augment Code became a core part of @kong's dev workflow - from managing complex microservices in Go & TypeScript to driving high-level engineering solutions.

Read the story: https://t.co/SiJYHrYInv

[syl.py⚡️ @Copypastaa]

@rrhoover I've been pitching the idea but @caitlinbolnick1 doesn't want to fund an Acquisition Studio at CRV 😂

[Census - a Fivetran company @census]

Got 3rd party data on your mind? 🧠

Join us next week on May 23 at 11 am PT for a Community-led webinar featuring OA Club Data Champion Ella Runciman, data engineer @ 1Password, on creating and using third party data in your warehouse.

RSVP below 👇
https://t.co/RA1k3jE8FX