Viewing profile — nkov47
nkov47
HN member- Joined
- Mon, Dec 23, 2024, 12:47 AM UTC
- HN karma
- 27
- Public activity
- 15 items
- HN profile
- View on Hacker News ↗
About nkov47
No profile information was provided.
Recent public activity
-
story
Show HN: Coarena - A community-driven arena to benchmark models for computer-use
We built a computer use agent once and got it benchmarked at the 2nd position in the biggest benchmark for this field but in the process, we realized one thing, how outdated and in…
-
story
Show HN: Open-Cowork – an open-source, model-agnostic computer-use agent
Hi HN, We built Open Cowork, an MIT-licensed desktop agent that can operate a computer through screenshots, mouse input, and keyboard input. We started working on this after using …
- story
-
comment
Comment #48952601
That’s exactly the failure mode we’re most worried about. A UI saying “success” is weak evidence that the underlying work is correct. We’re using a layered approach rather than rel…
-
comment
Comment #48937573
Exactly. We’ve found that for real production workflows, “did the task finish?” isn’t enough. You need to know what the agent saw, why it acted, what changed, and where a human app…
-
comment
Comment #48937563
I mean we've spent a year of our life on this(ironing out infra for more than half of the time), so i wouldn't say super low quality but again YC accepted us based on how our busin…
-
comment
Comment #48937517
This is a great read of it, and honestly we probably did undersell that part. The handoff works through checkpoints. The deterministic workflow defines the state it expects before …
-
comment
Comment #48937493
Yep, this is a real failure mode, and screenshot-after-action alone does not solve it. A field can look populated while the application never commits the underlying value. We try t…
-
comment
Comment #48937450
Thanks!!! completely agree that this is where trust is won or lost. We support explicit human approval gates in workflows, so you can have the agent prepare everything, then pause …
-
comment
Comment #48937410
We've hit 82.8% on OSWorld Verfied(on the official page) and with our latest internal testing we're hitting 85.6% which we've posted ( https://github.com/coasty-ai/coasty-osworld )…
-
comment
Comment #48928741
We're SOC2 and HIPAA compliant and have zero data retention policies through our enterprise platform where it's all covered and we don't keep any data that you don't want us to!
-
comment
Comment #48927274
Yes, you have access to all your logs and screenshots and playback!
-
comment
Comment #48926062
With our API, you can also create a very customizable blend of deterministic workflows and AI calls for CUA, so for example, Coasty for recovery can kick in when something unexpect…
-
comment
Comment #48925999
We don't just provide end-to-end API, we're a SOTA harness where you can bring in your own OpenAI or Claude keys and run it on and also we're the only modular API in the market - w…
-
story
Launch HN: Coasty (YC S26) – An API for computer-use agents
Hey HN, we’re Nitish and Prateek, the founders of Coasty ( https://coasty.ai/computer-use ). We’re building computer-use agents that can complete workflows inside legacy desktop so…