DEVELOPER TOOLS
AI coding
Coding assistants and software agents changing how teams design, build, test and maintain products.
EDITOR'S SELECTION
Latest analysis
GitHub Copilot's August VS Code release expands agent sessions and review
VS Code 1.132 through 1.135 add side conversations, portable agent plugins, cross-window sessions, richer review tools, an integrated browser and multilingual dictation.
· Ethan Brooks · 9 min readA supervised self-repair case shows why compiling is not an agent safety check
A newly published engineering account describes an unattended code-repair loop that was safe only because an unrelated bug stopped it before it could rewrite files.
· Priya Raman · 9 min readHow to sandbox an AI code-repair agent before it edits a repository
A safe repair workflow isolates the checkout, constrains writable paths, freezes validation and requires explicit review before changes reach the main branch.
· Ethan Brooks · 10 min readOpenAI plans to remove its models from Cursor after SpaceX acquisition
OpenAI says it intends to end its model-supply contract with Cursor on November 12 after Cursor's acquisition by SpaceX, while withholding future models during the transition.
· Ethan Brooks · 9 min readHow to prepare an AI coding workflow for a model-provider exit
OpenAI's proposed Cursor cutoff shows why coding teams need portable prompts, representative evaluations and a rollback path before a model disappears from a platform.
· Ethan Brooks · 10 min readGPT-5.6 joins Kiro for spec-driven coding work
OpenAI's GPT-5.6 Sol, Terra and Luna models are now available in AWS's Kiro coding agent, pairing the model family with requirements, design documents, task plans and review checkpoints.
· Ethan Brooks · 8 min readMeasure coding-agent cost by the accepted change—not the token
OpenAI's Kiro announcement makes a large cost claim for one benchmark. Teams need a reproducible method that includes retries, tests and human review before choosing an agent.
· Ethan Brooks · 10 min readHugging Face Candle fixes an ONNX Reshape compatibility gap
A focused Candle commit now honors ONNX's allowzero behavior and corrects -1 dimension inference. The patch shows why model portability depends on operator edge cases, not file conversion alone.
· Ethan Brooks · 8 min readA practical AI code-review workflow for pull requests
AI review can find patterns and draft fixes, but it should complement tests, security controls and accountable human approval rather than become an automatic merge signal.
· Ethan Brooks · 9 min readHow to evaluate an AI coding assistant across a real team
Autocomplete demos miss the work that determines value: review load, model portability, security, repository context and whether generated changes survive production.
· Ethan Brooks · 10 min readClaude Sonnet 5 brings a more agentic default model to Claude Code
Anthropic's new Sonnet model targets coding, tool use and autonomous work while keeping a lower price point than its Opus-class frontier models.
· Ethan Brooks · 8 min readCoding agents just crossed into the design canvas
Figma’s new agent workflow lets tools such as Claude Code, Codex and Cursor work with native canvas objects and design-system rules. The handoff between design and code is becoming a shared workspace.
· Ethan Brooks · 7 min readOpenAI launches GPT-6 Astra for ChatGPT Work, Codex and the API
OpenAI's newest flagship model targets computer use and professional workflows, with API pricing beginning at $10 per million input tokens and $50 per million output tokens.
· Ravi Kapoor · 10 min readHow to migrate GitHub Copilot workflows from models deprecated on September 1
GitHub is retiring six Copilot models on September 1. This guide inventories model dependencies, enables supported alternatives and validates agent workflows before the old selectors disappear.
· Owen Wright · 10 min readAn ONNX portability checklist for moving models between runtimes
ONNX makes model exchange possible, but it cannot guarantee identical behavior in every runtime. Use this validation sequence before treating a converted graph as deployable.
· Elena Morris · 10 min readGPT-5.6 arrives across ChatGPT, Codex and the OpenAI API
OpenAI's July flagship release brings one model family to consumer chat, coding agents and the API, followed by substantial price cuts for its Luna and Terra variants.
· Ravi Kapoor · 7 min readCursor review: a powerful AI code editor that still needs engineering discipline
Cursor combines fast completion, codebase search and tool-using agents inside a familiar editor. OpenAI's planned model withdrawal adds a new reason to evaluate its multi-model workflow rather than depend on one provider.
· Ethan Brooks · 12 min read