Viewing profile — dearilos
dearilos
HN member- Joined
- Thu, Dec 08, 2022, 7:03 PM UTC
- HN karma
- 11
- Public activity
- 51 items
- HN profile
- View on Hacker News ↗
About dearilos
email - ilya (at) myhomecat.com
Recent public activity
-
story
Show HN: HomeCat – Turn a phone video into permit-ready building plans
Hey HN! Ilya and Nikita here. We’re building HomeCat, a tool that turns a video walkthrough of a property into permit-ready building plans - https://myhomecat.com The basic workflo…
-
comment
Comment #45811194
Put up guardrails to enforce quality code.
-
comment
Comment #45732742
We’re fixing this slop problem - engineers write rules that are enforced on PRs. Fixes the problem pretty well so far.
-
comment
Comment #45686070
We’re trying to solve a similar problem, but using linters instead over at wispbit.com
-
comment
Comment #45608281
We're trying to solve a similar problem at wispbit - this is an interesting way to do it!
-
comment
Comment #45587624
We use ast-grep for the determinism part. I should have clarified - we don’t charge for fully deterministic runs. Only ones where the LLM is involved as a judge.
-
comment
Comment #45587573
It supports fully deterministic rules, which we use LLMs to help you write. Agreed on all of this too. This is why we built the CLI tool - to shift left the work.
-
comment
Comment #45585620
We combine determinism + LLMs to catch things a human would normally have to. If the LLM finds a violation, it generates a comment. Big agree on the CLI being open and letting you …
- comment
-
comment
Comment #45584635
We do a two week trial and then it's $0.2 per file reviewed. Buying in bulk + optimizing rules gives a significant discount.
-
comment
Comment #45584362
Love it :) Thank you!
-
story
Show HN: Wispbit - Linter for AI coding agents
Hey HN! Ilya and Nikita here. We're building wispbit ( https://wispbit.com ) - a tool that helps keep codebase standards alive. With the help of AI coding tools, engineers are writ…
-
comment
Comment #45583825
This is pretty much what I’m solving. LLMs need a “linter” of sorts that can guide them to write good code.
-
comment
Comment #45362757
I'm building something to solve exactly that - automating all the boring and repetitive parts of code review.
-
comment
Comment #45362737
I'm building something to do exactly that - just reduce and automate the boring parts of code review like enforcing standards.
-
story
Show HN: Wispbit – Keep codebase standards alive
Hey HN! Ilya and Nikita here. We're building wispbit ( https://wispbit.com ) - a tool that helps keep codebase standards alive. With the help of AI coding tools, engineers are writ…
- story
- story
-
story
Show HN: Open Source AI Code Review Agent for Teams
Hey HN! Ilya and Nikita here. We're working on wispbit - the open source AI code review agent for teams - https://github.com/wispbit-ai/wispbit . We made wispbit because we previou…
-
comment
Comment #44665692
problem with the tools you're using is that they're not built for code review im building one that lets you write and enforce your own rules so you don't get the typical slop email…
-
comment
Comment #44665676
i'm taking an approach where we scan your codebase and keep rules up to date you can enforce these rules in code review after CC finishes writing code email ilya (at) wispbit.com a…
-
comment
Comment #44665574
do you use anything today for automated code reviews?
-
comment
Comment #44665530
ive been building out a directory of code review rules for the last couple of months! are you open to chatting and sharing notes on what works/doesn't work? my email is ilya (at) w…
-
comment
Comment #44659630
I'm actually building something like this. A code review tool that can be ran by Claude Code (and other tools like cursor, kiro, windsurf) where it does the first pass. You can als…
-
comment
Comment #44659604
Do you use any tools to help with the code review part?