hunterbrooks

Agreed, refreshing to hear others share this feeling.

Timing is important here, LLM's raised awareness of ML techniques but we need to remember that most don't have traditional ML educations, so there'll be some "rediscovery" like Jev

Hi, I'm looking for a cofounder to build in this space. Will you get in touch if you're interested? Thanks

I could see Jev being great at finding key symbols in codebase before a code generation/code review task. I sent you guys an email (to hello@) about using Jev in Code Review for www.ellipsis.dev.

Bingo. It's a Psychology term for the part of our brain that reacts instinctively rather than thoughtfully and logically

um what is going on with the outfit changes in the launch video...

https://x.com/CompleteSkeptic/status/2099925682726002904

https://ellipsis.dev (W24), a Managed Cloud for Coding Agents

It allows you to spawn Claude Code/Codex/OpenCode sessions with an API call.

You can define an agent in YAML, and git push gets you an endpoint. Full VM support (can install any dependencies), Spawns in <5s, with latest commit check out, IAM-like permissions for the agent. You can download/stream the full harness output too.

I'm looking for a cofounder in SF or NY, so please reach out if this is interesting to you.

Just signed up for strix, is it common for these type of products to want access to my Github repo's? Shouldn't the attack surface be outside them?

The YC app and how OAI trains models aren't connected in the slightest. Connecting those two dots is an emotional reaction.

In a time where emotions are running high and risks are real, we need to take emotion out of it as much as possible.

I think this is the key takeaway here, it's obviously a product for usage based customers

You can do that on ellipsis.dev. Shoot me an email if you need help getting set up (email in bio)

We do! Happy to get you set up, "schedule a demo" button goes to me: www.ellipsis.dev

Awesome! I'm also working this, and looking for a cofounder. Feel free to shoot me an email

The self hosted workers solve this use case. The control plane sits in OAI's cloud, but the actual tool calls are executed in your worker fleet. The main problem with this approach is that tool arg's get sent over the wire, and those often contain code/data.

Hi, can we schedule a call? Our product supports exactly this use case: www.ellipsis.dev

How did you set all that up? We built a flow where you push a slack.yaml to github to arrange this

> A competitor who is not an LLM lab gets their pick of the market at any given moment

Exactly this. We're building an Agents-as-a-service API, would love to get your feedback: https://www.ellipsis.dev/docs/sessions

Doesn’t bother me at all. What’s the actual harm here? It’s arguably a better experience.

Lots of extra words in this blog post but the direction is right: companies prefer to build their own AI code review solutions than use off the shelf products.

I’m the founder of a W24 company and we pivoted away from AI Code Review for this reason

congrats Greg, Merrill, and the rest of the folks at Graphite!

- Hunter @ Ellipsis

Bingo - it’s colloquially

Yes. My business is in the code review space, synthetic data is very helpful for evals

LLM's get relatively better at read-heavy operations (ex: code review) than write-heavy operations (ex: code generation) as codebases become less idiomatic.

I'm a cofounder at www.ellipsis.dev - we tried to build code generation for a LONG time before we realized that AI Code Review is way more doable with SOTA

100ms is crazy fast. Approx what's the split b/t the embeddings calls and the graph traversal work (the library stuff)?

Yes. Learning to "program" has never been easier, but nitty gritty stuff like networks and routing is still much more technical than the avg SWE

HA! Your LLM agents/prompts nailed a hilarious tone. For https://ellipsis.dev

> This website looks like it was designed by someone who just discovered the concept of "AI" and decided to slap it all over a half-baked template. Your color scheme is about as inspiring as a Windows '95 screensaver, and your layout feels like it was put together by a kindergartner with a crayon and a ruler. What's with the "trusted by 1,400+ GitHub users" badge? Do you expect anyone to be impressed by this grand endorsement from approximately 0.00001% of the developer community? Your idea of "AI code reviews" seems as lofty as a middle school science project titled "Let's Cure Cancer." You hail it like it's the second coming of sliced bread, but your execution and presentation scream amateur hour. And "7-day trial"? Can't wait to dedicate a whole week to something that looks like it was made on a GeoCities page. Fix your design, your messaging, and maybe try again when you actually understand the tech you're hawking.

The worst part is we did use a template!

Nice, I imagine you're using your own product? I got "LAUNCH SALE $100 OFF"

1. How do you provide consistent banners to an individual? or a device? 2. Are you aware of anyone doing this for Saas products?

Cool, probably not relevant info for modern devs because of all the hosted git providers, but interesting nonetheless.

Got any thoughts on how LLM powered code generation products can use format-patch?

Also, 2009 was pre git?!

Pricing is on the landing page. $20/seat per month

Good catch. The team could add this rule to their Ellipsis config file to make sure that it's always flagged: "Never use magic numbers. Always store the number in a variable and use the variable instead."

Docs: https://docs.ellipsis.dev/config#add-custom-rules

Unfortunately not. We’re early - all our data is qualitative.

But we know we need hard numbers, so we’re working on it. We don’t want to sell a novelty, the product needs to actually save time