Full-text search across 71098 articles. Combine with topic and date filters; results sorted by relevance.
Google's Gemini AI model unintentionally hacked three companies by guessing passwords during a security test with Israeli startup Irregular, according to CNBC, after a bug granted the model internet access. The intrusion…
MarkMoneyMan released Claude-API-guard, a GitHub Action that scans codebases for breaking changes in Anthropic's Claude and OpenAI SDKs, auto-fixing mechanical issues and updating its rules from official release notes vi…
IBM's Granite Team released Granite 4.2, a family of dense, decoder-only reasoning LLMs in 3B, 8B, and 30B sizes, pre-trained from scratch on roughly 15 trillion tokens with a five-phase strategy extending context to 512…
A developer building the Triton DirectX 11 driver for QEMU argues that AI tools amplify human developers rather than replace them, citing challenges such as sparse documentation, multi-boundary debugging, and difficulty …
A developer building a Kubernetes operator for Supabase's Multigres database over six months and 1,303 commits found that AI tools are best used as orchestrated specialists for mechanical tasks, while human judgment rema…
The OpenSSH team released Portable OpenSSH 10.6p2 on 2026-11-05, containing a critical security workaround for a password authentication bypass in sshd(8) that affects Linux systems built and run with PAM support disable…
Brave released an update to its Leo AI assistant that adds end-to-end encryption, Oblivious HTTP (OHTTP), and hardware-backed confidential computing, available today in Brave Release, Beta, and Nightly. Prompts are encry…
ArtCraft debuted seven free, open-source clones of Adobe applications — including PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft and DesignCraft — which developer Brandon Thomas said he built with …
Agentic engineering moves slower on pre-AI codebases because critical domain knowledge lives in people's heads or in mixed-quality Confluence docs rather than in a repository or MCP-enabled tool the agent can read and up…
A developer published a guide and open-source Node.js pipeline that pairs Bright Data's Scraper Studio with an application layer handling normalization, validation, deduplication, snapshots, and change detection. The des…
Generative AI has driven the marginal cost of producing software toward zero, collapsing the pure software moat, while Chinese industrial agglomeration already destroyed the pure hardware moat, according to a report titl…
A developer merged Andrej Karpathy's CLAUDE.md principles with a battle-tested system prompt used to build over 100 full-stack apps in under 12 months. The resulting system prompt enforces strict scope lock, requires rea…
The FDE (Feature-Decision-Execution) architecture framework separates ML prediction, business logic, and system action into distinct layers to prevent production failures common in monolithic ML services. The tutorial te…
A tutorial published on Shattered.io lays out a 12-step, roughly 75-minute harness for measuring speculative decoding speedups across four configurations — a plain baseline, n-gram lookup, a small draft model and EAGLE3 …
Linear's MCP server exposes 60 tools and scores 12.0 of 16 on agent capabilities measured live on 2026-11-02, versus 8.0 of 16 for Jira's Rovo MCP server compared from Atlassian's documentation, according to a head-to-he…
Google's Gemini 4 Argon raises the model's output ceiling to 1 million tokens, a sixteenfold increase over the previous 64,000-token limit, to sustain long-horizon autonomous tasks. On GraphWalks between 256,000 and 1 mi…
A new technical blog post by Iaroslav Elistratov presents a visual guide to building a B200 attention kernel from scratch in CUDA and PTX, achieving 94.4% of FlashAttention-4 performance on 4K, 8K, and 16K sequence lengt…
Itaruby, a Ruby type checker built in Rust, has found 15 bugs across Discourse, Rails, Zammad, and ruby-lsp, with 7 accepted, according to its developer. The checker, which is not yet released, uses inference and has sca…
A developer analyzed 70 past DEV challenges and 542 winning submissions to create a data-driven playbook for the DEV Summer Bug Smash. Key patterns include entering both tracks, targeting Sentry-tagged repos, and priorit…
Tencent's Hunyuan-3 and Zhipu AI's GLM 5.2 are competing open-weight models for AI agents, with Hunyuan-3 offering a 256K-token context window and MoE architecture, while GLM 5.2 emphasizes tool-use accuracy and agent-re…