> We will require 30-day retention for all traffic on Mythos-class models, on both first- and third-party surfaces. We won’t use this data to train new Claude models, or for any non-safety-related purpose, and we’ve instituted new privacy protections including logging all human access to the data and ensuring its deletion after 30 days in almost all cases (see this post for further details). The data will help us defend against complex and novel attacks (including new jailbreaks and attacks that operate across many requests) as well as help us identify and reduce false positives.
That’s exactly why I’m getting downvoted, and I get it tbh. I knew people would ask for recommendations. It’s ok.
I haven’t used any of the tools you mentioned. We started using coderabbit just this year. The new PR review UI just came out. It’s made for big AI reviews which internally we’re trying to rein in. I like the direction they’re moving in with that, it uses AI to help you rather than bypass you. So you have the automated review that catches a bunch, and then they have a tool for you to step in and do your own review faster.
It’s funny there’s someone replying to me saying coderabbit is the best they’ve ever seen and in another thread someone else says it’s the worst. If that’s not AI for you… you just gotta try it
We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.
I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed.
Harris Teeter is an example of a large chain that has promotions (not coupons) that are applied at checkout only if you have your VIC card (their free membership program). There’s a lot of BOGO, a few dollars off etc offers that are tagged to the price label throughout the store.
You're combining state and local sales tax. State sales tax in Louisiana is 4.45%. Some municipalities add nothing on top of that, some add more. I said California's state sales tax is the highest and that's true.
I can answer for Conductor: you're getting the full Claude Code, it's just a GUI wrapper on top of CC. It makes it easy to create worktrees (1 click) and manage them.
Bread is mostly sliced bread in the US which lasts long. Can be frozen.
Lots of meat / fish is frozen.
Milk lasts for weeks in the store, same at your house (until you open it). I know in France milk is sold in bricks or bottles that aren't even refrigerated.
Most veggies can be frozen. And they weren't picked a couple days before you bought them, they can clearly last a long time.
I think that will fade. I don't know if you remember how mocked the airpods were when they first came out ("They look like q-tips"). All it'll take is a few celebrities spotted using one and they'll turn cool in no time.
> We will require 30-day retention for all traffic on Mythos-class models, on both first- and third-party surfaces. We won’t use this data to train new Claude models, or for any non-safety-related purpose, and we’ve instituted new privacy protections including logging all human access to the data and ensuring its deletion after 30 days in almost all cases (see this post for further details). The data will help us defend against complex and novel attacks (including new jailbreaks and attacks that operate across many requests) as well as help us identify and reduce false positives.