BestHub
Sign in
Tagged articles

Computer Use

21 articles · Page 1 of 1
Machine Heart
Machine Heart
Sep 14, 2026 · Artificial Intelligence

GPT-6 Astra Deep Dive: Looped Transformers, Computer Use & the Hidden Reasoning Debate

Sebastian Raschka analyzes GPT-6 Astra's breakthroughs in 3D rendering and computer use, explains looped transformer architectures from Universal Transformers to Mixture-of-Recursions, and argues that shorter reasoning traces stem from model capability gains, not recurrent depth obscuring chain-of-thought.

AI ArchitectureChain-of-ThoughtComputer Use
0 likes · 37 min read
GPT-6 Astra Deep Dive: Looped Transformers, Computer Use & the Hidden Reasoning Debate
Top Architecture Tech Stack
Top Architecture Tech Stack
Sep 4, 2026 · Artificial Intelligence

GPT-6 Astra: AI Agents Shift Focus from Token Price to Task Completion Cost

GPT-6 Astra introduces agent capabilities that operate software environments, browse the web, run tests, and maintain cross-window context, shifting AI coding evaluation from token pricing to task completion cost, with benchmarks showing 57.7% on Terminal-Bench 4.0 and 97.6% on FrontierMath Tier 4, plus pricing at $10/$50 per million tokens.

AI agentsCodexComputer Use
0 likes · 9 min read
GPT-6 Astra: AI Agents Shift Focus from Token Price to Task Completion Cost
Node.js Tech Stack
Node.js Tech Stack
Sep 3, 2026 · Artificial Intelligence

GPT-6 Astra: OpenAI's Computer-Using Agent Hits 99.9% ARC-AGI and Automates Full Workflows

OpenAI's GPT-6 Astra integrates reasoning, computer operation, and continuous execution into a single model, scoring 72.6% on OSWorld 2.0, 57.9% on Terminal-Bench 4.0, and 99.9% on ARC-AGI-3 with a Provider Adapter, while demonstrating autonomous tax filing, CRM updates, code migration, and zero-day vulnerability discovery — all with new cross-context memory and safety boundaries.

AGIAI SafetyAI agents
0 likes · 12 min read
GPT-6 Astra: OpenAI's Computer-Using Agent Hits 99.9% ARC-AGI and Automates Full Workflows
ThinkingAgent
ThinkingAgent
Jun 26, 2026 · Artificial Intelligence

How Small Models, Edge Agents, and Multimodal Interaction Power the Next Wave of Computer Use

The article examines the 2025‑2026 surge of sub‑10B parameter models, outlines edge‑side AI agents, details multimodal interaction layers, and explains how Computer Use enables AI to operate computers, offering a roadmap for integrating these technologies across mobile, desktop, and IoT scenarios.

AI agentsComputer UseModel Quantization
0 likes · 17 min read
How Small Models, Edge Agents, and Multimodal Interaction Power the Next Wave of Computer Use
AI Programming Lab
AI Programming Lab
Jun 17, 2026 · Artificial Intelligence

How to Choose Between Codex @Computer, @Chrome, and @Browser

The article breaks down Codex's three distinct computer‑control surfaces—@Computer, @Chrome, and @Browser—explaining their installation, trigger words, use‑case boundaries, performance trade‑offs, and a priority rule so users can pick the most suitable option for each task.

AI agentsAppshotsBrowser plugin
0 likes · 12 min read
How to Choose Between Codex @Computer, @Chrome, and @Browser
Architect's Tech Stack
Architect's Tech Stack
Jun 2, 2026 · Artificial Intelligence

Why the Latest Codex Update Is a Game‑Changer for Windows Users

OpenAI's recent Codex update adds true Computer Use support on Windows, letting the model see the screen, click buttons, type, and control desktop applications, with a simple @Paint or @computer prompt, though it runs in the foreground and requires ChatGPT Plus or higher.

AI automationChatGPTCodex
0 likes · 3 min read
Why the Latest Codex Update Is a Game‑Changer for Windows Users
AI Insight Log
AI Insight Log
May 30, 2026 · Artificial Intelligence

How Codex’s New Windows Support Lets AI See Screens and Control Apps

OpenAI’s Codex 26.527 update brings the Computer Use agent to Windows, enabling AI to view the screen, simulate mouse clicks and keyboard input, plus remote control via mobile, while outlining usage scenarios, platform differences, permission requirements, and security safeguards.

AI automationCodexComputer Use
0 likes · 8 min read
How Codex’s New Windows Support Lets AI See Screens and Control Apps
Design Hub
Design Hub
Mar 31, 2026 · Industry Insights

Four Minor AI News Items Reveal the Shift from Model Competition to Workflow Dominance

The article examines four recent AI coding tool events—a source‑map leak, a computer‑use preview, an OpenAI plugin, and an Apple AI mis‑push—to argue that the AI race is moving from pure model superiority toward competition over workflows, interfaces, and system‑level integration.

AI-coding-agentsClaude CodeComputer Use
0 likes · 13 min read
Four Minor AI News Items Reveal the Shift from Model Competition to Workflow Dominance
AI Insight Log
AI Insight Log
Mar 31, 2026 · Artificial Intelligence

Can Claude Code Make Human Testers Obsolete? New Computer‑Use Feature Lets AI See and Click

Anthropic’s Claude Code now includes a Computer Use capability that lets the AI directly control macOS applications—writing, compiling, launching, clicking UI elements, debugging visual bugs, and performing end‑to‑end UI tests without any code, while requiring specific macOS permissions and operating in a research preview with several limitations.

AI testingClaude CodeComputer Use
0 likes · 9 min read
Can Claude Code Make Human Testers Obsolete? New Computer‑Use Feature Lets AI See and Click
Top Architecture Tech Stack
Top Architecture Tech Stack
Mar 27, 2026 · Artificial Intelligence

How Claude’s New Agent Features Turn Your Phone Into a Remote Workhorse

Anthropic’s latest Claude update adds true computer‑control, scheduling, and Claude Code Desktop, enabling users to issue a single mobile command that drives desktop applications, runs code, processes files, and automates tasks, effectively turning the model into an autonomous agent that works beyond the chat window.

AnthropicClaudeComputer Use
0 likes · 15 min read
How Claude’s New Agent Features Turn Your Phone Into a Remote Workhorse
Design Hub
Design Hub
Mar 6, 2026 · Artificial Intelligence

How Powerful Is GPT‑5.4? A Deep Dive Into Its Design‑Focused Capabilities

OpenAI's GPT‑5.4 combines a 1 M‑token context window, native computer‑use, and benchmark‑leading performance—outperforming humans on 83 % of tasks and cutting token usage by 47 %—while showcasing demos that let designers generate games, websites, and 3D assets in a single prompt.

AI agentsComputer UseGPT-5.4
0 likes · 7 min read
How Powerful Is GPT‑5.4? A Deep Dive Into Its Design‑Focused Capabilities
ShiZhen AI
ShiZhen AI
Mar 6, 2026 · Artificial Intelligence

GPT-5.4 Beats Human Baseline and Cuts Agent Token Use by Half

OpenAI's newly released GPT-5.4 integrates reasoning, coding, computer use, and agent tool calls, achieving a 75% success rate on OSWorld-Verified tasks—surpassing the human baseline—while its Tool Search feature reduces agent token consumption by 47% and supports up to 1 million tokens for long‑running workflows.

AI modelAgentComputer Use
0 likes · 15 min read
GPT-5.4 Beats Human Baseline and Cuts Agent Token Use by Half
AI Explorer
AI Explorer
Mar 6, 2026 · Artificial Intelligence

GPT-5.4 Unveiled: 1M‑Token Context Window and Native Computer Control

OpenAI's GPT-5.4 launch introduces three model tiers, a 1 million‑token context window, native computer‑use abilities, higher factual accuracy and a new Tool Search feature, reshaping enterprise AI capabilities and intensifying competition with Anthropic and Google.

AI benchmarksComputer UseEnterprise AI
0 likes · 9 min read
GPT-5.4 Unveiled: 1M‑Token Context Window and Native Computer Control
Node.js Tech Stack
Node.js Tech Stack
Feb 18, 2026 · Artificial Intelligence

Claude Sonnet 4.6 Unveiled: The New ‘Super‑Worker’ Model with Epic Computer‑Use Leap

Anthropic’s Claude Sonnet 4.6, released on Chinese New Year, boosts computer‑use ability, supports a 1 million‑token context window, adds dynamic web‑search filtering, and improves benchmark scores (OSWorld 72.5%, SWE‑bench 79.6%, GPQA 89.9%) while keeping the same price, earning high praise from industry leaders.

1M token contextAI benchmarksAnthropic
0 likes · 8 min read
Claude Sonnet 4.6 Unveiled: The New ‘Super‑Worker’ Model with Epic Computer‑Use Leap
ShiZhen AI
ShiZhen AI
Feb 17, 2026 · Artificial Intelligence

Sonnet 4.6 Nears Opus Performance While Retaining Sonnet Pricing

Anthropic released Sonnet 4.6 just 12 days after Opus 4.6, delivering near‑Opus capabilities across coding, computer use, long‑context reasoning, and agent planning with a 1 M‑token window, while keeping the lower Sonnet price, prompting mixed community debate and rapid ecosystem adoption.

AI benchmarksAnthropicComputer Use
0 likes · 12 min read
Sonnet 4.6 Nears Opus Performance While Retaining Sonnet Pricing
Meituan Technology Team
Meituan Technology Team
Jan 23, 2026 · Artificial Intelligence

How EvoCUA Set a New Open‑Source SOTA for Computer‑Use Agents with Evolutionary Learning

EvoCUA, a native computer‑use agent from Meituan, combines a verifiable data‑synthesis engine, a ten‑thousand‑level sandbox infrastructure, and an experience‑driven learning paradigm to overcome data‑scaling and feedback challenges, achieving a 56.7% success rate on the OSWorld benchmark and surpassing previous open‑source models.

AI AgentComputer UseData Synthesis
0 likes · 27 min read
How EvoCUA Set a New Open‑Source SOTA for Computer‑Use Agents with Evolutionary Learning