heurist

Hard to paste in 2k words of context when you're talking. I don't think voice is the solution for most people who need to communicate heavily with AI.

Haven't had a chance to test astra vs 5.6 in these reviews yet. I've seen mixed feedback on astra generally so have hesitated in the upgrade. Have you tested and found any difference?

> Typically they are lower level code issues that humans would not have noticed

The author does not triage the feedback. Review bot assesses priority and agents fix the issues the automated review discovers. Nothing is blocked by the bot, humans can ignore if they think the feedback isn't helpful.

We use AI heavily in development but everyone has their own setup and way of approaching use. AI in PRs provides a consistent review layer beyond what the engineers do themselves, and catches a previously undiscovered issue in about 75% of the PRs.

We totally use it in CI. We were thoughtful in how we built our review bot and it catches a lot of issues before humans lay eyes on the code. Typically they are lower level code issues that humans would not have noticed. It's not the comprehensive review solution, which is why we still require some level of human attendance to the code, but it's very much worth using. We do set limits on PR size and description quality as well to mitigate the harsher AI slop issues.

"Pace the frontier" is one of those political marketer-written phrases you know is meant to be repeated until it becomes the frame everyone has to argue inside.

Who exactly gets to set the pace? OpenAI and Anthropic already have privileged access to capabilities the public doesn't. Amodei is now proposing government-backed coordination among frontier labs, including an antitrust waiver for safety discussions. Maybe the safety concerns are sincere. But it's awfully convenient that the proposed solution also makes the current frontier labs the permanent gatekeepers of machine intelligence.

And who actually has the resources to do the massive attacks he's worried about? Mostly labs and state actors. Not you and me. The people asking to restrict access are also the people best positioned to keep using the thing being restricted.

No, only 2x-ish weekly. 20x 5 hour limit.

I've been using both for a few years. OpenAI's limits have always lasted much longer for me (depending on whether a monkey got in their machine or not). Aside from not lying about limits they also don't assume I'm developing some kind of nerve agent and lock me out when I ask basic questions in my domain or nag me about my late night work hours. There was a time last year when I strongly preferred using Anthropic models, but at some point something about the responses (or maybe the company) changed and I now find them particularly offputting relative to OpenAI. Hope they fix it because the industry needs more competition.

I downgraded from the 20x today after learning that 20x only applies to 5 hour usage. I have barely used Claude/Claude Code in the last month and am considering downgrading further, even after this update.

It doesn't make much sense as compute isn't all that scarce (relative to other commodities) and will be less so in 15 years.

I find after 4 or 5 rounds of targeted feedback and requests to tighten the text AI can produce exceptionally readable documentation.

You are heavily discounting the human side of the generation effort. The first output from an AI might be slop but once you start injecting your own ideas and desires it lands much further away from what any AI would output on its own. (Not that there's no zero-effort slop around - there's a lot).

Claude Opus 4.7 responds with walk for me with and without adaptive thinking, but neither the basic model used when you Google search or GPT 5.4 do.

I work with some 'legends of programming' and they're all excited about it. I am too, though I am not a legend. It really is changing the game as a valid new technology, and it's not just a 'slot machine'. Anthropic is burning their goodwill though with their lack of QA or intentional silent degradation.

You should not be downvoted for expressing your concerns.