smb06

Discussed here: https://news.ycombinator.com/item?id=48947560

I feel like I've been hearing about atmosphere on Earth-like planets for a while. Or maybe I've missed some nuance.

It is a separation-of-duties argument for code written by AI agents and also reviewed by the same AI agents.

If you ask Agent1 to write code, the PR diff coming out of it should really be reviewed by Agent2 (or 3 or whatever), the reviewer should be a different system than the code gen agent.

The core claim is that a model is a poor judge of its own work — it shares the same priors and blind spots that produced a bug, so self-review trends toward a shallow review rather than catching blind spots.

The system that writes the code shouldn't also be the thing that signs off that it's safe to ship.

The mid-terms could really become about whether AI as a technology should be in the hands of the public/society or left to tech companies

My rent has gone up by 15% over the last two years and it is reflective of the increase in salaries in AI startups.

TL;DR -- more configurability with Claude Code, better out-of-the-box experience with Codex.

That tracks with the rest of their philosophy too

Their code reviewer was previously called Diamond

Do you use Copilot for coding and then also Copilot for reviewing? Or are you using some other coding agent and Copilot only for PR reviews?

Just tried it out. Very cool but would be helpful to also be able to upload .svg files

Part of Youtube premium or ad supported?

I read their pitch as trying out multiple agents to do the same task and then pick your favorite approach

On the flip side, our SaaS runs primarily on GCP so our users are fine. But our billing and subscription system runs on AWS so no one can pay us today.

CodeRabbit has GA'd its support for AI code reviews directly in your terminal. CodeRabbit CLI agent works with your coding agent (Claude Code, Codex, Gemini, etc.) and allows you to automate code reviews and bug fix right as you are building in your CLI.

To get started, run this command in your terminal ask your coding agent to run CodeRabbit reviews: curl -fsSL https://cli.coderabbit.ai/install.sh | sh

This is old news at this point.

Even louder horns and even brighter headlights. Its like everyone is trying to blind all other drivers at night.

The real warning sign (like flashing red lights x100) will be when potential AI Inra unicorn startups start delaying their IPOs or their public stock fails to rally after IPO

Hey folks - just wanted to share that CodeRabbit recently shipped AI code reviews for Cursor, Windsurf and VS Code.

In order to have code reviews fit seamlessly into the daily coding work in the editor we had to completely rebuild our AI code review agent so that we could fast, and accurate code reviews in the editor.

Objective was to review every code change well before the PR is raised so that there are fewer comments and back-and-forth in the PR.

Would love to hear your feedback on how we balanced code review quality with speed of delivering review comments.

Hey folks - just wanted to share our announcement that CodeRabbit now runs in the IDE bringing free AI code reviews in the code editor.

No more context switching when conducting code reviews. Developers can maintain their flow state and get immediate feedback on committed or uncommitted changes. Reduces clutter in the PR as well to get your code reviewed before the PR is raised. No cost to run code reviews in the IDE (with some rate limits).

Shouldn't take more than a few minutes to install the CodeRabbit plugin. Would love to hear your feedback.

I couldn’t think of an agency that has delivered a better ROI than NASA.

Every big company i have worked at (2) didn't really reach out to anyone from my previous job to verify my details. Every startup I've worked at (3, all early stage) did extensive background verification on all my claims. Guess the risk for early stage startups getting a new hire wrong is more pronounced.

A significant portion of my PhD funding came from DARPA and NSF. If I was doing that work today, I probably would not be able to study ways to implement quantum tunneling in devices made with novel semiconductor materials (Gallium Arsenide)

And any regulations that might have forced them to consider environmental impacts are probably gutted too.

Can’t wait for a day when there is a 2-paragraph summary of legal terms and conditions within the browser perhaps with a simple plugin.

Or assigning a national security threat score if we like too many Chinese tik tok videos

Only recently heard about Travels of Sam Wise having a substack and from his father, William Dalrymple, no less. Was listening to William's podcast (The Empire Pod) and he mentioned this substack.

Love the first article. I've known about Rampur all my life but never knew there was so much to explore there. Thank you, Sam!

The artificial part or the intelligence part?

Most people in my circle are tired, deflated and have given up. And that reflects in our online posts and interactions. Resigned to fear the worst.

Oh they want to eliminate the possibility of public filing a FOIA request. Democracy died in Darkness.

OANN too: https://amp.cnn.com/cnn/2025/01/31/media/pentagon-press-rota...

I can understand companies having targets on who they have in their interviewee pool but it hasn’t made sense to me to have targets on who you hire.