Gemini 4 Argon is now available to everyone

MVMaker Views #frontier-models #gemini #Hacker-News #maker

Gemini 4 Argon is now available to everyone

Google's launch post is unusually specific about what the model did inside Google before release.

Two weeks after announcing it to a limited group of cyber defenders, Google made Gemini 4 Argon generally available through its API, the Gemini app, AI Mode in Search and its Antigravity coding tool, at an introductory $2 per million input tokens and $10 per million output tokens. Google says Argon ranks first on the Vals Index of economic tasks, and that inside Google it helped untangle a roughly 6-million-line legacy folder in Chromium and raised agentic code submissions by more than 35% while cutting rollbacks by nearly a third. These are Google's own figures.

Read it at the source

GoogleGemini 4 Argon: Built to solve your hardest problems Independent ↗ Hacker NewsDiscussion: Gemini 4 Argon Independent ↗

Cascadic Analysis 3

UndertowBenchmark scores can overstate real-world reliability

What hidden risk could pull against this, even if the news is good?

Google says Argon ranks first on the Vals Index and cites its own internal wins, like 35% more agentic code submissions. Those numbers come from Google's evaluations and Google's codebase; how the model does on an ordinary company's messy code is a separate question.

UndertowAutonomous cyber capability scales attackers enormously

What hidden risk could pull against this, even if the news is good?

Google lists finding and patching critical cybersecurity vulnerabilities among Argon's headline uses. A model that is good at finding bugs is now generally available through the API, to people who want to exploit those bugs as well as fix them.

UndertowDelayed Consequence / False Success Problem

What hidden risk could pull against this, even if the news is good?

Google credits Argon with refactoring hundreds of files out of a 6-million-line Chromium folder in weeks instead of months. Large automated changes that pass review can still hide subtle behavior changes that only show up when billions of browsers run them.

Rabbit Holes 1

Gemini (language model)

After exploring Gemini 4 Argon: Built to solve your hardest problems, the model family it belongs to is Gemini (language model).

Google DeepMind's family of multimodal large language models, successor to LaMDA and PaLM 2, first announced in December 2023.

Wikipedia · Wade · 5 min

0

Gemini 4 Argon is now available to everyone

Further down the stream