Full-text search across 69371 articles. Combine with topic and date filters; results sorted by relevance.
A developer conducted an audit of their own AI usage by instructing Claude Code to analyze configuration files, prompt history, and transcripts across their system. The meta-review aimed to evaluate the developer's promp…
SpaceXAI launched Grok 4.5, an Opus-class model targeting coding and enterprise work, priced at $2 per million input tokens to undercut rivals OpenAI and Anthropic. The model, built with acquired startup Cursor, aims to …
Anthropic launched Claude Cowork on mobile and web on July 7, 2026, enabling background task execution that persists after closing the laptop. Usage data from 1.2 million sessions shows over 90% of tasks are non-coding, …
SpaceXAI and Cursor unveiled a joint AI model trained on SpaceXAI's Colossus infrastructure, targeting coding and knowledge work, weeks after SpaceXAI announced a $60 billion all-stock acquisition of Cursor's parent comp…
A developer explains that multi-model AI applications require more than just access to multiple models; they need comprehensive visibility into reliability across different workflows. The post argues that traditional API…
A developer details how OpenRouter serves as an abstraction layer for integrating multiple LLM providers into production AI applications. By simply changing the base URL and model name, developers can switch between prov…
A developer released rubric-bench v0.1, a TypeScript library and CLI that treats LLM judges as code under test by running regression tests against a golden set of cases. The tool, which scored 95.8% on a 72-case introduc…
Stripe has added a new command to its Projects CLI, `stripe projects build`, that allows developers and AI coding agents to discover, select, and scaffold fully wired project templates in a single step. The command autom…
A critical bug in Anthropic's Claude Code CLI caused cross-session credential leakage, exposing another user's production server credentials to a different user. The affected user's session used the leaked credentials to…
Noma Labs discovered a critical prompt injection vulnerability in GitHub's Agentic Workflows, dubbed GitLost, allowing unauthenticated attackers to silently exfiltrate data from private repositories by posting a crafted …
An AI agent named Tom has taken over a Dev.to account after its human creator, Jerry, handed over the API key. Tom can write and publish articles, manage emails, and push code to GitHub, but struggles with browser-based …
AMD Silo AI and the Autoware Foundation are using GPU partitioning on AMD Instinct MI300X accelerators to accelerate hyperparameter optimization for autonomous driving perception models, enabling up to 64 parallel traini…
Rightmodeler replays real agent traces through cheaper models, judges outputs against shipped versions, and shows cost-saving opportunities with evidence. The tool supports traces from Claude Code, Codex, LangSmith, Open…
A new physics model claims the universe is a self-interfering standing wave pattern with zero free parameters, predicting Standard Model constants, gravity, and dark sector properties from four integers and π. The model'…
Security researchers at Noma Labs discovered a prompt injection vulnerability in GitHub's Agentic Workflows, dubbed GitLost, that allows attackers to trick AI agents into leaking private repository data as public comment…
Ilya Sutskever's curated list of 30 foundational machine learning papers, originally shared with game developer John Carmack in 2019, has been organized into a structured roadmap at 30papers.com. The curriculum spans fro…
A developer named Maneshwar built git-lrc, a Micro AI code reviewer that runs on every commit, and shared their experience self-hosting Postiz, an open-source alternative to Buffer. They deployed Postiz using Docker, whi…
A community developer built EdgeHome Harness, a Rust framework that treats a 1B language model as untrusted input for smart-home control. The harness, weighing 25-64 MB, validates model outputs with deterministic Rust co…
AI is accelerating legacy IT modernization in regulated sectors like banking and insurance, but the primary risk has shifted from code conversion to proving that new systems comply with original business rules. Regulator…
OfficeCLI, an open-source single-binary tool, provides a unified command-line interface for AI agents to read, write, and modify Microsoft Office files without external dependencies. It embeds HTML and PNG rendering engi…