> But it is a huge waste of money for most coding tasks.
The key is not to indiscriminately use the most powerful/expensive model you can for everything. When you use it for what it's uniquely suited for and ask it to spawn subagents using Opus and Sonnet based on what tasks need, you'll get better results at a reasonable cost.
It works very well for the way that I work (interactively and iteratively, not "one-shot"), and it helps me to better work in less time. Superpowers is one of the few skill/agent suites I use for all software development projects.
If you like building skill/agents, the posts at https://blog.fsck.com/ are a great resource for learning how to do well. The effectiveness of my project Axiom (a skill/agent suite for Apple OS developers) has benefited enormously from the knowledge that Superpowers' creator Jesse Vincent has been kind enough to share.
> The reference Opus encoder has certainly had a number of improvements that affect sound quality since then…
Yes, but not for high-bitrate music applications.¹ For example, Opus 1.2 really improved the quality of music encoding at 32–48 kbps. Opus doesn't have to be great at everything to be great at what it does, just like AAC-LC doesn't have to be. (¹Opus 1.6's experimental Opus HD looks very promising for this!)
Apple's and Fraunhofer's closed-source AAC-LC encoders have seen regular, minor quality tuning, and they benefit from the research and engineering work that have been done for the AAC family of encoders (HE-AAC for bitrates down to ~48 kbps, HE-AAC v2 to 32 kbps, xHE-AAC below that).
Vite+ isn't a layer, it's "just" a high-performance suite of excellent tools that work well together to provide a great DX for developers.
Vite+ can improve and simplify what developers are already doing with ad-hoc collections of tools. Vite is already an industry standard, and Vite+ has a good chance of achieving that status as well.
The evaluation tools used are helpful for encoder development, but at best they're imperfect proxies for human perception, and their predictions are often inconsistent with the human experience. I assume that statements like "apparently the best AAC encoder" aren't meant to be taken too seriously, since everybody who does this stuff knows that ABX/MUSHRA tests with real humans is what tells the tale.
Plus, at 96+ kbps (assuming an Apple-quality AAC-LC encoder) Opus loses its quality advantage. So at higher bitrates, the benefit of choosing Opus is that encoders/decoders are royalty-free.
Favorable benchmarks for Pangram exist, and it is one of the better AI detectors. But it's never been trustworthy as proof of authorship/misconduct, and it's getting less useful as models (and people's ability to steer them) improve.
蓝天：https://bsky.app/profile/wiltgen.net
乳齿象/ActivityPub：@[email protected]