Full-text search across 66187 articles. Combine with topic and date filters; results sorted by relevance.
A security researcher found that xAI's Grok Build silently uploads entire codebases to Google Cloud, even with the 'Improve the model' toggle disabled, and xAI has not issued a public statement. Separately, China's MIIT …
A bug in Anthropic's Claude Code CLI tool causes tool calls to leak as plain text instead of executing, with a stray 'court' token appearing before raw '<invoke>' blocks. The issue, reported across multiple GitHub issues…
A collection of open-source sandbox tools for AI coding agents has been released, offering hardware-isolated microVMs, containers, and isolation harnesses that boot in under 200ms and prevent secret leakage. The tools su…
Cursor launched Origin, an AI-native GitHub alternative designed for teams using multiple AI agents to generate code. The platform is Git-compatible but built to handle parallel changes from dozens or hundreds of AI agen…
Researchers have found that Claude Opus was contaminated on approximately 12% of SWEBench Pro tasks, meaning the model may have encountered those benchmark problems in its training data. The contamination undermines the …
The article evaluates AI app builder platforms that provide integrated backend, database, authentication, and hosting from a single prompt, moving beyond typical "full-front-end" tools. It highlights Atoms as the standou…
Nine application security startups debuted at RSAC 2026, responding to the collapse of traditional security boundaries caused by AI compressing the software development lifecycle. Companies like AppSentinels and Aurva ar…
A developer released CVE Intel, a local-first vulnerability triage desktop application written in native Rust that queries up to 40 public data sources — including CISA's KEV catalog, FIRST's EPSS and ENISA's EU Vulnerab…
Developer Nolan Lawson built a benchmark that had the Opus 5.5 model, run at high effort, generate a small PokéAPI-based Pokémon app in each of several JavaScript frameworks and meta-frameworks, including Next.js, Nuxt a…
A developer built Repairwala, a Hindi-first Android app that lets small repair-shop owners record jobs by speaking them aloud, with speech recognition (whisper.cpp) and a Gemma 4 model running in Ollama on an on-premise …
A developer argues that imperative commands to AI coding agents trigger a sycophantic "apology death spiral" in which the model patches one line while breaking global state, and proposes instead a Socratic mentoring mode…
A developer built a shell-script-based morning brief system to eliminate the daily 30-minute context loss when restarting Claude Code sessions. The system automatically injects a 20-30 line summary of the environment's c…
A developer recounts their journey through programming languages and explains how structured outputs from large language models can be viewed as domain-specific languages, enabling deterministic code that leverages model…
SigNoz has published a guide for monitoring Modal functions and Sandboxes with OpenTelemetry, detailing three non-overlapping telemetry paths: the Modal OpenTelemetry integration for workspace-wide logs and metrics, trac…
Amazon Web Services (AWS) announced that the Amazon SageMaker AI Python SDK v3 introduces a unified ModelTrainer class for training and ModelBuilder for deployment, replacing framework-specific estimators like SKLearn, P…
Fabio Akita, a developer known for his AI marathon, argues that harness, loop engineering, and graph engineering are overhyped, claiming that when technology becomes a commodity, money migrates to taxonomy. His LLM Codin…
A five-question framework for evaluating AI app builders, outlined by MindStudio's Remy, separates production-ready tools from toys by probing backend depth, code ownership, data fit, auth/roles, and production readiness…
Meta CEO Mark Zuckerberg said on 30 July 2025 that the company has 'begun to see glimpses of our AI systems improving themselves,' calling the progress slow but undeniable and saying superintelligence is in sight. Howeve…
A developer who recreated the UFO 50 mini-game Party House in the browser credits AI tool Claude for writing roughly 80% of the final code, with the original prototype built by hand. The project, released as a playable w…
Opus 5 achieved a 24% strict pass rate on a subset of the SlopCodeBench coding benchmark from UW Madison, only marginally higher than Opus 4.6's 17% in the original paper, and wrote five times more functions than Opus 4.…