@dzhng: Frontier models has gotten so good at one shotting web apps that it's no longer in my personal benchmarks Instead, one …
Summary
Frontier models have become so proficient at generating web apps that the author now benchmarks them on building a WebGPU water renderer from scratch, comparing Opus-4.8 and Fable-5 orchestrator with GPT-5.5 implementer.
View Cached Full Text
Cached at: 07/04/26, 10:43 AM
Frontier models has gotten so good at one shotting web apps that it’s no longer in my personal benchmarks
Instead, one of my bench now involves loop building a WebGPU water renderer, from scratch.
Left: Opus-4.8 Right: Fable-5 orchestrator GPT-5.5 implementer https://t.co/1QxIZSrJAX
Similar Articles
@hank_aibtc: Amazing! Running Gemma 4 in the browser, on par with ChatGPT?! Completely zero server, zero data upload, offline, pure WebGPU local inference! Xenova has open-sourced all 27 custom WebGPU kernels written by Fable 5: - Gemma 4 E2B (2.3B parameters...)
The article introduces Xenova's open-sourcing of 27 custom WebGPU kernels, enabling Gemma 4 to run fully offline and locally in the browser at 255 tok/s, and discusses advantages like privacy and offline use. It also mentions FLUX.2's 3D generation capability.
@auroter: Frontier AI is BRAINDEAD. GPT5.5 xHigh in Codex thinks I should use Tensor Parallelism to deploy Qwen 3.6 27B on my sys…
The author criticizes Frontier AI (GPT5.5 xHigh) for incorrectly suggesting Tensor Parallelism for a model that fits on a single GPU, and announces a planned shootout comparing several AI models (GPT5.5, Opus 4.8, Qwen variants, Nemotron) on a real-world problem.
@browser_use: Opus 4.7 GLM 5.2 We're benchmarking models on frontend design. We run each model on Browser Use v4 > One prompt from th…
Opus 4.7 and GLM 5.2 are being benchmarked on frontend design using Browser Use v4; results are shared via a link.
Been picking frontier models on benchmarks that don't match our deployment conditions
The article highlights a performance rank-order flip between Claude Opus and Gemini Pro on a forecasting benchmark, depending on whether models perform their own web research or are given fixed evidence. This suggests that Opus excels at the research phase while Gemini is superior at judgment over fixed evidence, exposing a mismatch between standard benchmarks and actual deployment conditions.
@DataChaz: MIND BLOWN that an open-source model running on a MacBook can go toe-to-toe with the cloud Spent yesterday in @atomic_c…
A tweet reports that an open-source model (Gemma 4 31B) running locally on a MacBook via AtomicChat can match cloud Gemini 3.5 Flash for generating a playable Mario game in HTML/Canvas, signaling a shrinking cloud moat.