I disagree. Assuming code complexity is roughly fixed, more sophisticated code analysis will result in a smaller surface area for bugs. Bugs will still be found, but there will be less bugs to be found and less opportunities to exploit.
I disagree. I routinely hit the 5 hour limit on Pro with Opus 4.7 just trying to have it do one design task or comprehensive code review on a large PR, and the worst part is, the overhead and bringing all that context back into another 5 hour window blows through 30%+ of my 5 hour usage limit.
Claude absolutely improves code review quality, but it still misses a lot. It's a second pair of eyes, it doesn't replace/remove the work you have to put in to fully review the code yourself.
It's like saying that you code reviewed faster just because someone else also reviewed the code, that's not how it works.
Do lots of deep research and code reviews on large legacy codebases. I've created lots of documentation to reduce token consumption but it's still a lot of token consumption.
Lately I've been using claude mainly to design plans and do code reviews while Codex does all the implementation. Having two very different models helps to work out any weird quirks one might have.
It's more accurate to say that RAG is alive and well and is just incorporated into the agent's responsibility, it's just one more tool that it can call on instead of the user manually doing it.
My mother in law did this. There are a lot of ignorant and uneducated people out there. They think "take this for pain" = "take more for more pain", popping one an hour not really understanding how insanely dangerous it is since acetaminophen has such a subtle effect until it's too late.
Turtle WoW built off a 20 year old client with their own original content. After how many decades do you think it is acceptable for people to be allowed to mod and sell their own version of it? 75 years like with Disney? Would you feel that society would be worse off if people were allowed to sell modded N64 games?
For new developments, absolutely, but once something has been out for decades (plural), modifying and selling that isn't so unethical. Keep in mind that Turtle WoW built off and supported that original game client from over 20 years ago, they weren't just backporting a bunch of content from Blizzard's newer releases. It's the same as if someone wanted to sell a modded Super Nintendo game, society would not be worse off for this.
Not only content, but countless bug fixes and new features (such as the guild bank). There's also a related project (SuperWoW) that injected a dll to fix and extend the client (which is still Blizzard's old original client).
The US still enforces copyright law on song distribution which is the big difference. It basically requires a middleman (like spotify) that soaks up all the revenue from that distribution while giving almost nothing back to the artists.
I've always liked China's business model for music. In China, all music is free to stream and download. Musicians make their money the more traditional way, through performances, merchandise, promotions/advertising, etc.
If the operators of Anna's Archive live somewhere like Russia or China, there's a good chance nothing will ever come of any of this legal action. Anna's Archive's biggest challenge is just maintaining availability of infrastructure.
While the technology is young, bugs are to be expected, but I'm curious what happens when their competitors' mature their product, clean up the bugs and stabilize it, while Claude is still kept in this trap where a certain number of bugs and issues are just a constant fixture due to vibe coding. But hey, maybe they really do achieve AGI and get over the limitations of vibe coding without human involvement.
This is the biggest bottleneck for me. What's worse is that LLMs have a bad habit of being very verbose and rewriting things that don't need to be touched, so the surface area for change is much larger.
I'm personally appreciative of these comments. It's good that people make claims, be challenged, and both sides walk away with informative points being made. It's entirely possible both sides here are correct and wrong in their own way.
I wonder if requiring it twice a month would fix both issues, since it's too frequent to plan around (versus quarterly), while frequent enough to allow transparency (versus annually).