Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Salesforce bets on AI 'agents' to fix what it calls a $7 billion problem in enterprise software

Salesforce announces Agentforce 360 as enterprise AI competition heats up

A Must-Have Tool for Writers

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
OpenAI

OpenAI Codex rivals Claude Code

By Advanced AI EditorOctober 13, 2025No Comments7 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Codex CLI supports both sandbox levels and approval modes. These tend to overlap; I’ve only tested approval modes. In general, the recommendation is to use auto mode if the folder you’re working in has a git repository, and to use read-only mode if it does not.

▌ Select Approval Mode
▌
▌ 1. Read Only Codex can read files and answer questions. Codex requires
▌ approval to make edits, run commands, or access network
▌ > 2. Auto (current) Codex can read files, make edits, and run commands in
▌ the workspace. Codex requires approval to work outside the
▌ workspace or access network
▌ 3. Full Access Codex can read files, make edits, and run commands with
▌ network access, without approval. Exercise caution

My first test of codex was an old standby: explaining the Cline repo.

martinheller@Mac cline % codex

╭───────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.42.0) │
│ │
│ model: gpt-5-codex /model to change │
│ directory: /Volumes/Data/repos/cline │
╰───────────────────────────────────────────╯

To get started, describe a task or try one of these commands:

/init – create an AGENTS.md file with instructions for Codex
/status – show current session configuration
/approvals – choose what Codex can do without approval
/model – choose what model and reasoning effort to use

▌ explain this repository

• I’m planning to explore the repository’s structure by listing top-level files
first before deciding how to approach explaining it fully. Since it’s likely a
moderately complex task involving multiple components, I’ll prepare to create
a plan to gather an overview and inspect key files like README and manifests.
For now, I’ll use shell commands in the repo path to get a directory listing.

• Updated Plan
└ □ Inspect repository structure and key configuration files.
□ Review main source directories to understand functionality.
□ Summarize repository purpose, architecture, and key components for the
user.

• Explored
└ List ls
Read README.md, package.json
List src
Read extension.ts
List core
Read README.md
List task
Read index.ts
List webview-ui
List webview-ui
List tests
List specs
List proto
List standalone
List hosts
List vscode
List services
List api
List providers
List api
List providers

• I’m gathering key parts of the system like the extension entrypoint, front-end
webview, the controller managing tasks, the task logic, gRPC host bridging,
and services for terminal and web. I also want to highlight the Model Context
Protocol integration and look into tests, especially those using the testing-
platform and playwright. This gives a clear map of how everything fits
together and what’s covered by tests.

• Explored
└ List testing-platform
Read README.md

• Updated Plan
└ ✔ Inspect repository structure and key configuration files.
□ Review main source directories to understand functionality.
□ Summarize repository purpose, architecture, and key components for the
user.

• Explored
└ Read index.ts
List hostbridge
List packages

• Updated Plan
└ ✔ Inspect repository structure and key configuration files.
✔ Review main source directories to understand functionality.
□ Summarize repository purpose, architecture, and key components for the
user.

• I’m gathering key file references with approximate start lines to clearly
explain the repository architecture. Since exact line numbers aren’t certain,
I’ll include paths with line 1 where appropriate—like for src/extension.ts:1
and src/core/controller/index.ts:1—to lend clarity and credibility without
overcommitting to specifics. I’ll consider checking webview-ui/package.json
next to confirm React usage before citing it.

• Explored
└ Read package.json
List mcp
List browser
List integrations
List terminal
List evals
Read README.md

• I’m putting together a thorough but concise overview of the VSCode AI
assistant extension, covering its main elements like activation, core
pipeline, controllers, task engine, services, integrations, the React webview
UI, testing, evals, proto definitions, docs, and packaging. I plan to update
the progress tracking right before delivering the final message.

• Updated Plan
└ ✔ Inspect repository structure and key configuration files.
✔ Review main source directories to understand functionality.
✔ Summarize repository purpose, architecture, and key components for the
user.

• I’m organizing the final message into clear sections with bullet points like
Overview, Runtime Architecture, AI & Tooling, and next steps. I’ll include
file path references with line numbers where possible and possibly peek into
provider files to confirm accurate referencing. This way, the user gets a
structured, easy-to-follow summary of the project.

• Explored
└ Read openrouter.ts, TerminalManager.ts, McpHub.ts, App.tsx
List cline
List host
Read BrowserSession.ts, ui.proto, ChatView.tsx
Search install:all in package.json
Search “build in package.json
Read package.json

• Ran python – <<‘PY’
│ import json
│ with open(‘package.json’) as f:
│ … +4 lines
└ bash: cannot create temp file for here document: Operation not permitted

• Ran node -p “Object.entries(require(‘./
│ package.json’).scripts).map(([k,v])=>k+’: ‘+v).join(‘\n’)”
└ vscode:prepublish: npm run package
compile: npm run check-types && npm run lint && node esbuild.mjs
… +7 lines
docs:rename-file: cd docs && npm run rename
report-issue: node scripts/report-issue.js

> Overview

– Cline markets itself as a human-in-the-loop agentic coding partner for
VSCode, combining editor, terminal, browser, and MCP tooling (README.md:1).
– Extension metadata, activation triggers, command registrations, and
marketplace packaging live in package.json:1, showing it targets VSCode 1.84+
and ships under Apache-2.0.
– The core architecture is documented as “extension → webview → controller →
task,” giving you the top-level mental model for how work moves through the
system (src/core/README.md:1).

Runtime Flow

– Activation bootstraps the host bridge, sidebar webview, diff providers,
and command palette entries before handing control to the controller (src/
extension.ts:1).
– The controller handles workspace discovery, auth, telemetry, MCP lifecycle,
and state sync between the extension host and webview (src/core/controller/
index.ts:1).
– Task orchestration manages API calls, context windows, tool invocations,
checkpoints, and multi-step plans while streaming partial responses back to
the UI (src/core/task/index.ts:1).
– Protobuf contracts define the bi-directional messages (asks, says, tool
calls, UI commands), letting the host, webview, and external clients talk over
gRPC (proto/cline/ui.proto:1).

AI & Tool Integrations

– A rich provider layer wraps dozens of model backends (OpenRouter, Anthropic,
Together, Bedrock, etc.) with retryable streaming support and per-model tuning
(src/core/api/providers/openrouter.ts:1 and peers).
– MCP Hub loads user-configured servers, watches configs, and proxies tool/
resource calls so Cline can extend itself with external capabilities (src/
services/mcp/McpHub.ts:1).
– TerminalManager reuses VSCode terminals, streams shell output via the new
shell-integration hooks, and captures results for the agent’s reasoning (src/
integrations/terminal/TerminalManager.ts:1).
– BrowserSession can launch or attach to Chromium and headless browsers to
automate web flows, collect screenshots, and surface console logs when tasks
require it (src/services/browser/BrowserSession.ts:1).

Frontend Webview

– The webview UI is a Vite/React app with Tailwind, Storybook, and Vitest,
bundled alongside the extension and built via dedicated scripts (webview-
ui/package.json:1).
– Providers wrap context, telemetry, and gRPC clients before rendering,
enabling server-driven state hydration and announcement handling in the
sidebar (webview-ui/src/App.tsx:1).
– ChatView composes messaging panes, token/cost analytics, quick actions, and
slash-command tooling, powered by protobuf-backed gRPC clients shared with the
host (webview-ui/src/components/chat/ChatView.tsx:1).

Testing & Ops

– A CLI-based testing platform spins up gRPC adapters and harnesses to
replay scripted conversations against the standalone server or the extension
(testing-platform/README.md:1).
– Recorded session fixtures exercise chat flows, slash
commands, and multi-root workspaces, enabling regression
checks without re-running full UI tests (tests/specs/
grpc_recorded_session_chat___can_send_messages_and_switch_between_modes.json:1
).
– The evals suite benchmarks Cline across standardized coding tasks, diff-edit
challenges, and model comparisons, with a CLI that toggles the extension into
test mode on demand (evals/README.md:1).

Next steps:

1. Install dependencies with npm run install:all (root + webview) and generate
protobuf stubs via npm run protos.
2. For local development, run npm run watch (host) in one terminal and npm run
dev:webview in another to iterate on the extension and sidebar UI together.

▌ Implement {feature}

⏎ send ⇧⏎ newline ⌃T transcript ⌃C quit 56.3K tokens used 91% context l
Token usage: total=56,294 input=48,978 (+ 918,272 cached) output=7,316 (reasoning 4,160)
To continue this session, run codex resume 01999c62-84cd-7e01-ab31-dd71d07da02b.

I’ve done this exercise with several large language models (LLMs) that have been trained on code. This is among the best summaries I’ve seen so far.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleVibe analytics for data insights that are simple to surface 
Next Article Tabby invests in NVIDIA HGX systems to boost AI Models
Advanced AI Editor
  • Website

Related Posts

OpenAI Will Stop Saving Users’ Deleted Posts

October 13, 2025

Judge lifts order requiring OpenAI to preserve ChatGPT logs

October 12, 2025

Hollywood-AI battle heats up, as OpenAI and studios clash over copyrights and consent

October 11, 2025

Comments are closed.

Latest Posts

Toledo Museum of Art Director on Digital Art, AI, and Future-Proofing

Smithsonian Closes Museums Amid Government Shutdown

The Rubin Names 2025 Art Prize, Research and Art Projects Grants

Kochi-Muziris Biennial Announces 66 Artists for December Exhibition

Latest Posts

Salesforce bets on AI 'agents' to fix what it calls a $7 billion problem in enterprise software

October 13, 2025

Salesforce announces Agentforce 360 as enterprise AI competition heats up

October 13, 2025

A Must-Have Tool for Writers

October 13, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Salesforce bets on AI 'agents' to fix what it calls a $7 billion problem in enterprise software
  • Salesforce announces Agentforce 360 as enterprise AI competition heats up
  • A Must-Have Tool for Writers
  • ‘Absolutely Don’t Do This’: Perplexity CEO Aravind Srinivas Warns Against Misuse Of AI Tools – Alphabet (NASDAQ:GOOG), Amazon.com (NASDAQ:AMZN)
  • Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models – Takara TLDR

Recent Comments

  1. Iyannapax on Stanford HAI’s annual report highlights rapid adoption and growing accessibility of powerful AI systems
  2. NeonPulseG5Nalay on German data protection official wants Apple, Google to remove DeepSeek from the country’s app stores
  3. Marshall on AI’s impact on software development \ Anthropic
  4. NeonPulseG5Nalay on MIT leaders discuss strategy for navigating Trump in private meeting
  5. VIAGRA IDIOT on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.