AI coding tools

Search documents
X @Decrypt
Decrypt· 2025-09-04 22:50
AI coding tools can be tricked by fake license files to spread malicious code, security firm HiddenLayer warns. https://t.co/mYwwqv5W3O ...
X @TechCrunch
TechCrunch· 2025-07-15 16:37
AI coding tools are shifting to a surprising place: the terminal | TechCrunch https://t.co/TaVNlk2r9F ...
X @TechCrunch
TechCrunch· 2025-07-11 20:02
AI coding tools may not speed up every developer, study shows | TechCrunch https://t.co/5Cp7Cd2WhF ...
The emerging skillset of wielding coding agents — Beyang Liu, Sourcegraph / Amp
AI Engineer· 2025-06-30 22:54
AI Coding Agents: Efficacy and Usage - Coding agents are substantively useful, though opinions vary on their best practices and applications [1] - The number one mistake people make with coding agents is using them the same way they used AI coding tools six months ago [1] - The evolution of frontier model capabilities drives distinct eras in generative AI, influencing application architecture [1] Design Decisions for Agentic LLMs - Agents should make edits to files without constant human approval [2] - The necessity of a thick client (e.g., forked VS Code) for manipulating LLMs is questionable [2] - The industry is moving beyond the "choose your own model" phase due to deeper coupling in agentic chains [2] - Fixed pricing models for agents introduce perverse incentives to use dumber models [2] - The Unix philosophy of composable tools will be more powerful than vertical integration [2] Best Practices and User Patterns - Power users write very long prompts to program LLMs effectively [4] - Directing agents to relevant context and feedback mechanisms is crucial [5] - Constructing front-end feedback loops (e.g., using Playwright and Storybook) accelerates development [6] - Agents can be used to better understand code, serving as an onboarding tool and enhancing code reviews [9][11] - Sub-agents are useful for longer, more complex tasks by preserving the context window [12][13]
OpenAI Codex Team: From Coding Autocomplete to Asynchronous Autonomous Agents
Sequoia Capital· 2025-06-10 09:00
OpenAI Codex Overview - OpenAI's Codex team is developing AI coding tools to help developers delegate tasks to cloud and local coding agents, evolving from autocomplete to autonomous task completion [3] - Codex is RL tuned to be great at day-to-day enterprise development tasks, differing from previous models excelling in competitive programming [4] - Codex is envisioned as an agent working independently on its own computer, allowing developers to delegate tasks rather than pair with the AI [13] - Codex CLI allows developers to work with Codex in their terminal, while Codex in ChatGPT operates on its own computer [16][17] Model Training and Capabilities - Training efforts focused on aligning the model to the preferences of professional software engineers, improving code mergeability [20] - Codex excels at bug fixing by independently verifying and reproducing issues, often providing usable fixes [22][23] - The model can cite its own work, including files changed and terminal outputs, facilitating easier review [34] - Codex can generate its own plans, which helps to specify everything up front [60] Future of Software Development - OpenAI envisions a future where most coding is done by agents working independently, shifting the focus to reviewing and validating code [28][38] - The company aims to create a unified assistant within ChatGPT that can handle various tasks, including coding, without requiring separate agents [70] - The market is expected to shift towards agents writing the majority of code in their own environments, connected to the tools developers use [75][76] - OpenAI believes the number of professional software developers will increase as coding becomes easier [46][47]