gemini 4 argon really struggles on our senior engineer benchmark task comes in at 21% far below Sol 6 and even Muse: https://checks.every.t...

VIBE CHECK: GEMINI 4—GOOGLE IS BACK https://x.com/i/broadcasts/1dGYlawYAdYKX

BREAKING: Gemini 4 is OUT and it's SURPRISINGLY GOOD?? I admit I was ready to trash this model qhen I saw the benchmarks but six of us at ...

we (@ArielleShipper) made the ultimate set of skills for running an automated hiring pipeline in Codex available for on the @every github: ...

I used muse wonder to make a video explaining personal benchmarks.. this is ummm pretty rough interestingly all of its videos so far are n...

disappointing showing for Muse Wonder on our senior engineer benchmark. it asks the model to rewrite a vibe coded slop codebase from scratc...

taking down my tweet about Muse's performance on our senior engineer benchmark! found a problem in the run, and going to restart it

extremely early take on Muse Wonder is that it's a mid writer one of my favorite canary tests is the McDonald's test. ask the model to do a...

in place of “alignment” which is impersonal and abstract id like to propose a new key dimension of model performance: Fidelity: how well do...

cracks are appearing in the frontier model duopoly!

made a feed that automatically tracks the books im reading (and have read going back to 2012!) maybe we should have a feed for everybody @e...

NEW JOB ALERT: @every we've built a personal benchmarking platform, Checks, to help anyone measure how good new models are for their real w...

tfw your ChatGPT app is controlling your Claude app is controlling your ChatGPT app

OpenAI’s Dots launched last week and they've taken over @every. A few things that stand out: They protect your attention. Over the weekend...

we couldn't have built the @every agent without Claude Managed Agents extremely fun to get to sit down and chat about it: https://twitter.c...

BREAKING: Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company. It comes with: - Everything y...

what we promise @every: as the frontier advances, so do you.

if you want to get better at using AI, just ask it to evaluate you and regularly suggest upgrades to your workflow

use codex to go from prompting to orchestrating agents with this step-by-step guide by @ArielleShipper https://every.to/p/codex-graded-my-...

dot has become my primary interface to AI over the last few weeks. my dot's name is boo. he's cute! in a year, i bet i'll still be intera...