I still can't believe it, but @taylorotwell followed me back!!
So I'm releasing the next version of Veer!
Veer is an @inertiajs adapter for Rust. It implements the full Inertia v3 protocol, so you get a Rust backend with React, Vue, or Svelte on the frontend. No separate API needed.
https://t.co/2RMRAvVczC
Agree with Max here, I would further argue that opinionated frameworks have become even more important in the age where many devs are not reviewing AI-generated output.
Opinionated frameworks ensure the best standards are being followed under the hood.
I don’t know if I agree with this take. Good frameworks are intelligence caches.
The production of verifiable high-quality code has a cost to it (insert for now caveat). Frameworks can lower this cost as long as they don’t get in the way of agents.
It also helps grow in maturity in God, and so we are trusted with more blessings because its a confirmation we are ready. Just like human parents do.
This is why people will testify that tithing brought them blessings, only that many of us miss that its not the transactional exchange.
It was us practicing self-control, sacrifice, kindness and other fruit which that becomes a testament that we are grown and ready.
@MwaiAnika Well said, just to add..
Tithing is a *discipline*.. there are things in Christianity that aren't requirements anymore but they are used to help us maintain our submission to God & avoid idols.
So for example, consistent tithing helps us stay away from putting money before God
@codeslubber@ITCryptoRocket1@rohanpaul_ai No he fine-tuned a badly trained LLM(badly trained because he selectively unfroze weights) and then basically fine-tuned it to one-specific standard.. it doesnt really qualify as an expert system
Complex software development has become accessible to the developers of all skill levels. Specialization is probably going to become blurry apart from some niche fields like ML, AAA Game development.
Overall its now fully about what you are building, not if you can build it
The key to coding a module with LLMs, especially the highly capable ones is in being able to steer it to implement the bare minimum.
A lot of devs get enticed (by the model) to add unnecessary features that complicate the dev/review process. I am guilty of that as well
Opus 5.5 performs at the level of Fable 5.1. It's ~30% faster and ~40% cheaper than Opus 5 per task.
In Claude Code:
- 5-hour session limits increase 20% today
- Opus 5.5 is priced lower, so it goes 25% further within limits
- Pro, Max, and Team users get a reset to use anytime
@kvnobi In many foreign countries, it is lol
Funika usamuke lol.. you, Simon and a bunch of others in the creative/design/visual space are too elite for this trash market.
I swear by telling agents to reply in ISO 24495-1 English, avoiding unnecessary metaphors.
Sometimes, I might tell them to use ASD-STE100 if I want short precise directional statements but not conversational