Leon Ho

LLMs can be evaluated across three key dimensions: intelligence, cost, and inference speed. At the moment, I believe Google Gemini leads the field. What a comeback. https://t.co/gRnBHtoi4r

Pierre Bongrand @bongrandp

For the first time, Google is responding to OpenAI's announcement in < 24 hours The WAR is officially ON, and Google wants the LLM market Google is now dominating +90% of the price share https://t.co/HlBhoSEeoc

One big reason to use o3 https://t.co/EGyF1bCSkH

Fiction.live @ficlive

OpenAI Strikes Back https://t.co/lxR1bObUBH

Tested Strawberry on Llama 4 Maverick via @OpenRouterAI. Have to ask to think carefully to return the correct answer. https://t.co/Q2ATqxOWza

RT @Ahmad_Al_Dahle: As of today, Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scorin…

RT @swyx: With gemini 2.5 pro pricing and results, Google has fixed the biggest unknown/weakest link in their lineup and we can now confi…

It sounds like @cursor_ai will jump at it immediately. It will save them a ton.

Alex Albert @alexalbert__

We've introduced a new text_editor tool in the Anthropic API. It's designed for apps where Claude works with text files. With the new tool, Claude can make targeted edits to specific portions of text. This reduces token consumption and latency, all while increasing accuracy. https://t.co/c1Vi3Khgt8

My guess, based on the structure of OpenAI naming: 4o + reasoning = o1 4o mini + reasoning = o1-mini 4o + very deep recursive reasoning = o1 pro 4.5 + reasoning = o3 4.5 mini + reasoning = o3-mini 4.5 + very deep recursive reasoning = o3 pro That’s why o3 pro is economically