Dan Shipper (Every): Gemini 4 is out and surprisingly good, but shaky at refactors and held back by Antigravity
Dan Shipper @danshipperX
Why it matters
First-hand independent review after a week of early access, with concrete test results (21% on a refactoring benchmark vs 81-85% for rivals); about 14k views about 2.5 hours after posting (fxtwitter, Oct 13).
Summary
Shipper summarises Every’s week of testing. Strengths: writing and editing (‘my new favorite writing partner’), fast from-scratch builds (a webcam heart-rate monitor in 35 minutes at low effort). Weaknesses: self-verification and existing codebases (in 17 of 38 benchmark runs it opened and closed its code-review step 30 milliseconds apart; 21% on his ‘Senior Engineer’ refactoring benchmark versus 81% to 85% for GPT-6 Astra, Fable 5.1, Sonnet 5.5 and Opus 5.5). He says Antigravity ‘feels six months to a year behind Claude Code and Codex’. Links the full review at every.to. Verified via api.fxtwitter.com on 2026-10-13 (~18:40 CEST): 14141 views, 107 likes, 10 reposts; posted Tue Oct 13 16:03:55 +0000 2026.
Archived text
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 @every spent the past week testing it across coding, writing, design, and knowledge work, and were pleasantly surprsied.
It’s a breakthrough if your company lives in Google’s ecosystem, and a strong option for frontier hoppers as a secondary model for certain tasks. I
Here’s our vibe check:
My new favorite writing partner. DeepMind hired professional writers with red pens to stamp out AI slop, and it worked. I use it to untangle structure and sharpen metaphors; it also taught me something new tracing in a few of my favorite books. It’s got a natural feel for structure and detailed explanations that Astra and Opus lack.
Shaky at refactors, fast on greenfield apps. At low effort on a from-scratch build, Gemini 4 built @kieranklaassen a working webcam heart-rate monitor in 35 minutes—matching Claude Opus 5.5’s quality and beating OpenAI’s models on that test. Where it cuts corners is self-verification and existing codebases. In 17 of Kieran’s 38 benchmark runs, it opened and closed its code-review step just 30 milliseconds apart instead of inspecting its changes. And on my Senior Engineer benchmark—refactoring a vibe coded slop codebase—it worked for four hours and 47 minutes and scored just 21% (versus 81% to 85% for GPT-6 Astra, Fable 5.1, Sonnet 5.5, and Opus 5.5). Not great.
A 2026 model trapped in a 2025 harness. Antigravity, Google’s desktop agent app, feels six months to a year behind Claude Code and Codex—lacking cloud environments, SSH, a built-in browser, and smart permission checks (leaving you clicking constant pop-ups or using unrestricted “Turbo” mode).
Net Result: I keep ChatGPT and Claude open day to day, and switch to Gemini 4 when I need an editorial partner to structure a tough essay, sharpen a metaphor, or close-read a book. Reach for it for live writing collaboration, fast low-effort prototypes, or steerable UI and dashboard design—ideally via Cursor or the API to skip Antigravity.
When a model is good enough to force you to use a bad harness, it tells you something.
State of Play: Google hadn’t shipped a major flagship upgrade since Gemini 3 Pro last November. For teams whose companies live in Google’s ecosystem, the model you can use inside your approved work tools finally belongs with the frontier pack. DeepMind closed the model gap; now Google needs to bring the app around it into 2026.
Read our full vibe check: https://every.to/p/vc-gemini-4-argon-puts-google-back-on-the-frontier?utm_source=danx&utm_campaign=vibecheck-gemini-argon&utm_content=dan-261013