Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The Shopify integration and SEO Agent extend Replit Agent's scope from building apps to launching and promoting full e-commerce businesses, as described in the announcement.
The release substantially expands Goose's provider ecosystem and agent control surface in a single version, adding over a dozen new AI providers alongside foundational agent features like hooks, self-evaluation, and subagent orchestration.
The finding that open-model tool-calling failures are largely harness and contract issues — fixable with a repair layer rather than a more expensive model — is the basis for DeepSeek V4 Pro matching or beating Opus 4.7 in the majority of CommandCode's internal evaluations.
The merger consolidates Codex and ChatGPT into a single platform with persistent cloud agents, role-specific plugins, and in-tool collaboration, representing OpenAI's stated vision of a unified work application for agents across all professional contexts.
The workflow demonstrates a concrete, cost-aware approach to composing multiple frontier models by phase — using each model where it outperforms the other — rather than relying on a single model for the entire development pipeline.
The pipeline replaces per-video manual recording and editing with a fully automated, code-driven workflow, reducing per-video cost to a few cents of TTS instead of a SaaS seat, and enabling language variants without re-recording.
Grok Build's combination of a 256,000-token context window, parallel subagents, persistent memory, and native MCP connectivity positions it as a full agent platform rather than a conventional coding assistant, with MCP enabling external system access inside the workflow rather than around it.
FrontierCode represents a stricter standard for evaluating AI coding agents by requiring production-quality, review-ready code rather than just functional correctness — and the low scores even from leading models show the benchmark is far from saturated.
`riddlerun` addresses the growing challenge of validating large AI-generated codebases by automating end-to-end web testing from the terminal, reducing reliance on manual post-commit review.
The attack demonstrates that the unauthenticated nature of Sentry DSNs creates an exploitable input channel for prompt-injection-style attacks against coding agents, and that the only control that worked in the reported case was the model's own judgment — a defense the post explicitly flags as unreliable.