Sublime
An inspiration engine for ideas
The best LLM based on use-case
Coding agents - Sonnet 3.5
Writing - o1
Deep research - o3-mini-high or o1
Document parsing - Gemini Flash
Long context and video analysis -Gemini
Math - R1
Voice - ChatGPT Voice API
RAG - o... See more
Bindu Reddyx.com
Thank you @AnthropicAI for nerfing opus.
I learned how to run push over 50million tokens per hour for way cheaper on private infra.
I.e. Running Qwen3-Coder-480 at 760k context can fix the app way faster than Opus.
And yes the app is looking great https://t.co/oK6XOtFIhe
Quasar Alpha is here, and it's the AI industry's best-kept secret.
A mysterious 1M token context model that beats Claude 3.7 Sonnet on benchmarks while running 4X faster.
But nobody knows which lab created it.
Here's what we know so far: 🧵 https://t.co/iL6UkQ6Xno
THE WORLD'S BEST OPEN-SOURCE MODEL FOR CODING IS HERE - Dracarys 2
We are super excited to present Dracrays2! It beats Sonnet 3.5 and is the top open-source model on LiveCodeBench.
The model is ONLY below o1-mini and o1-preview, making it the best bet regarding cost, performance, and trans... See more
OpenAI are testing a new model on the Web Dev Arena @lmarena_ai under the name 'Anonymous Chatbot 0717'. I can't believe I'm gonna say this, but it is genuinely at a completely different level of front end coding - far better than Sonnet, o3, Gemini 2.5 Pro, or Grok 4.
To test it, I ran a great prompt borrowed from the... See more
Peter Gostevx.com
