Somehow gemini-cli is so janky and doesn't get the latest models. But Antigravity is the new golden child? Just have a great suite of predictably quality products.
It's the vercel way. There have been plenty of experiments leading up to this (even by vercel employees before they joined) but re-packaging it as "the" solution, rather than just a tool renderer from props (tool schema)
OpenAI seems to limit how "hard" your gpt-5-codex can think depending on your subscription plan; whereas Anthropic/Claude only limits how much use you get. I evaluate Codex every month or so with a problem suited to it, but rarely gets merged over a version produced by Charlie (which yes is $500/mo, but rarely causes problems) or something Claude did in a managed or unmanaged session. ymmv
It's a really good platform for Typescript microservices which scale-to-zero (up to very high theoretical limits), but it wouldn't be a platform you'd migrate a monolith PHP app to (for example).
You're describing why reasoning is such a big deal. It can do this freakout in a safe, internal environment, and once it's recent output is confident enough flip into the "actual output" mode.
Great to see Huggingface stick to their guns with CodeEval and python tooling. Agentic turn-by-turn tool calling is fine and all, but we're underutilising their ability to write an execute code in an "agent-like" environment.
Easy to setup and instant forks for devs was it for me. Felt the pain with dev app state in the past and this took <20 minutes to migrate (beta users only) and go live, and get back to feature work.
My grandparents were terrible at smartphones. To them, it's like a landline phone, but you have to charge it every 1-2 days. Yet my grandpa was decent at PC, and email, and so on, as it was in "a place" and easy to drive.
You can "self-host" as in `next build` and `next serve`, but it runs as a monolothic runtime. Next-on-vercel compiles each api route to a serverless function and supports various additional flavours of server side rendering of pages. Open Next is being able to run like Next-on-vercel but on AWS, your own infra, Cloudflare Workers, and others.
Truly, (for those who don't want to log in) it's just a shared playground conversation with GPT-4, in Danish, where the author got a result they're obviously unhappy with.
Author, do some more robust tests, write a blogpost about it, and submit that instead.