Sublime
An inspiration engine for ideas
gpt-4o claims to outperform claude opus.
I don't trust benchmarks.
So I ran my own tests:
test #1 β analyze a 42-page PDF https://t.co/k2aCkNzzbW
Very happy to be supporting https://t.co/oRLDFt5xia. πͺπΊπͺ banners suck, but let's make them 1P and performant for nowβ¦
ππππππ { π²ππππππ±πππππ } ππππ "@ππ·π»π/πππ‘ππ π"
Just learned that https://t.co/e5mFlvWGK9... See more
π€― Did an independent evaluation of @AnthropicAI prompt caching - and holy sh**
Built a quick "chat w/ 5 weeks of @thrusdai_pod transcripts" code to evaluate these claims & just shoved ALL those transcripts in system prompt π€―
TL;DR - 90% cheaper sonnet & 97% cheaper haiku
Alex Volkov (Thursd/AI)x.comBenchmarks for programming languages and compilers, Which programming language or compiler is faster
programming-language-benchmarks.vercel.appUnlighthouse
unlighthouse.dev
BREAKING: claude 3.5 is live since 1h.
They claim to be better than gpt-4o.
So I ran my own little test:
test #1 β copy the UI of a website https://t.co/b3mAsHFo0o
Ruben Hassidx.comVisualping: #1 Website change detection, monitoring and alerts
visualping.io