Viewing profile — ashish004
ashish004
HN member- Joined
- Sun, Apr 21, 2024, 6:29 AM UTC
- HN karma
- 12
- Public activity
- 15 items
- HN profile
- View on Hacker News ↗
About ashish004
No profile information was provided.
Recent public activity
-
comment
Comment #49121476
This is cool!
-
comment
Comment #49003113
What is the major advantage of this versus using conductor / cmux / intent / amp ? Also, versus claude code over rc (remote-control)
-
comment
Comment #48905081
Out of all AI slops, this is best one and depicts what Dario's AI (Claude) is capable of.
-
comment
Comment #47929814
True. Thats exactly what we have done. Once finalrun is installed, it ships all the skills to generate and run the test from the same repo.
-
comment
Comment #47924507
Saw the website https://clawd.rip , pretty cool and informative.
-
comment
Comment #47820566
[flagged]
-
comment
Comment #47685536
Hey, thats true, verification of ai generated code needs proof with video of each action, console logs and network logs. Would love to know how you are solving for web. would be a …
-
comment
Comment #47684274
Do share us feedback.
-
comment
Comment #47682423
Just updated README.md, it's lot simpler and addresses on the core. Thanks for the feedback, please checkout
-
comment
Comment #47679506
Yes gavinray, It gets persisted to the project. Its lives alongside the codebase. So that any test generated has the best context of what is being shipped. which makes the AI model…
-
comment
Comment #47678902
Hi Avikaa, finalrun provides skills that you can integrate with any IDE of your choice. You can just ask the finalrun-generate-test skill to update all the test for your new featur…
-
comment
Comment #47678807
[dead]
-
comment
Comment #47676540
We have built a QA agent that can understand your plain english intent and uses vision to reason and navigate the app to test your intent. You can check our benchmark here https://…
- comment
-
story
Show HN: Finalrun – Spec-driven testing using English and vision for mobile apps
I wanted to test mobile apps in plain English instead of relying on brittle selectors like XPath or accessibility IDs. With a vision-based agent, that part actually works well. It …