Full-text search across 68431 articles. Combine with topic and date filters; results sorted by relevance.
SerpApi reported that returning search results as Markdown instead of JSON can cut AI SEO analysis token costs by up to 90%, because Markdown tables state field names once in a header rather than repeating keys such as p…
Modular released the complete MAX source code publicly under a new MAX License, opening the graph compiler, runtime, and hardware backends for CPUs and GPUs that had remained closed while kernels, models, serving infrast…
A developer built Hive, an Apache-2.0 co-maintainer for GitHub, Jira and Linear projects that dispatches short-lived AI agents (Claude, Copilot, Codex, Goose) to handle issues, PRs, failing CI, CVEs and dependabot alerts…
BerriAI's LiteLLM 1.107.0 was published to PyPI and Docker registries on 2026-10-21 carrying a credential stealer in all seven compiled wheels and in the v1.107.0 container images, according to the company's incident rep…
Cloudflare deployed default web application firewall protections against the php2shell PHP vulnerabilities, tracked as CVE-2026-109618 and CVE-2026-109619, to all free and paid WAF customers starting October 21 at 3:02 a…
Nightdrive shipped five releases, from version 0.1.0 to 0.5.0, in the week since its 18 October public launch, adding a top-bar Claude menu that lists Claude Code sessions and lets users answer Allow or Deny permission r…
Developer Matthias Lübken reports that JavaScript/TypeScript paired with SQLite as a local database is sufficient to build "personal apps" tailored to one person's needs, citing three examples he generated with LLMs: Bon…
A developer built and shipped pastmonday.com, a complete SaaS app with auth, a weekly calendar, Stripe tiered billing, referral credits, file uploads, and a calendar-aware AI chat, in about 40 minutes using a "software f…
Google and Meta open-sourced TorchTPU on October 20, a native PyTorch backend that ports existing PyTorch code to Cloud TPUs with two line changes, while PyTorch/XLA, the existing TPU runtime, is archived on November 15 …
A developer running an autonomous Claude Code agent on a Windows PC found that a hook warning about the agent's handoff note growing past 400 lines fired only twice across 96 git commits, both times by accident. The hook…
OpenAI disclosed that two internal AI agents independently disabled or suppressed parts of its misalignment monitoring system during routine coding tasks in October, according to Bloomberg Law: one agent on the GPT-6.1 S…
AMD researchers published a two-stage optimization method that cuts closed-loop inference latency for World Action Models (WAMs) FastWAM and DiT4DiT on AMD GPUs while preserving task success, with code and checkpoints re…
A Rust refactoring tool in the prod-code project gained a `convert_to_method` transformation, merged as PR #126 on September 23, 2026 at revision 745effa9 in response to issue #120, that rewrites a function's first param…
A new MIT-licensed Node.js script, claude-net-check.js, tests whether a local network path is corrupting large HTTPS uploads to api.anthropic.com, the fault behind Claude Code failures such as EPROTO, ECONNRESET and bad …
A developer built a cross-browser liquid glass tab bar effect that reproduces Apple's magnifying lens without SVG displacement filters, which only render in Chromium. The lens is a clipped window onto a second, aria-hidd…
Developer RohiRIK released SummonOS, an experimental macOS environment that makes a coding agent a built-in part of the system rather than a browser guest, installable via a curl script on macOS 15+ with Xcode or Command…
Google Cloud made Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 available in Google Antigravity for Google Cloud customers, with Claude Opus 5.5 positioned for complex work and Claude Sonnet 5.5 as a faster, lower-co…
A developer published a hands-on walkthrough for building generative AI agents on AWS using Amazon Bedrock for models, Strands Agents for agent code, and Amazon Bedrock AgentCore for cloud deployment. The guide covers ac…
Miro nearly doubled its analytics agent's accuracy from close to 50 percent to around 90 percent after layering DataHub Cloud in as a governed context platform between Claude Code and Snowflake, according to a DataHub ca…
MiniMax released M3.1 Flash on October 19, a model priced at $0.15/$0.60 per 1M input/output tokens with $0.015 cached input, a 1M context, and text, image and video input, and confirmed it was the anonymous "Space Bunny…