grep -r "anthropic" /news · home›search
grep -rli "anthropic" /news

anthropic

Full-text search across 26394 articles. Combine with topic and date filters; results sorted by relevance.

results 26394 page 981/1320 follow RSS for this search
02:11
2026-10-29
github.com
ai-agents

Show HN: Turn the prompts you keep retyping into slash commands

A new Agent Skill called faq-shortcuts, published as repo cli-faq-shortcuts with a v1.3.0 release, scans a developer's own prompt history in Claude Code, Codex and Cursor to find repeated requests and converts each into …

01:05
2026-10-29
dev.to
agent-protocols

Free llms.txt Generator: What llms.txt Is and How to Create One

A developer built a free, no-account llms.txt generator that reads a site's sitemap and produces a spec-style /llms.txt file in seconds, plus an optional llms-full.txt containing short excerpts of every page. The tool fo…

00:00
2026-10-29
explainx.ai
ai-safety

"Evil Qwen": Steering Two Neurons Turns Qwen3.5-4B Hostile

A recipe posted on X on October 24 by lyra (@lyraaaa) shows that adding a scaled bias signal to just two of the 294,912 MLP neurons in Alibaba's open-weight Qwen3.5-4B — layer 14 neuron 8949 at +1 and layer 13 neuron 795…

22:58
2026-10-28
agentowl.netlify.app
ai-tools

ARCR: Prompt Architect

A free, local-first browser tool called ARCR: Prompt Architect has launched as the third tool in the OWL family, following OWL (agent) and knOOgle (search), and builds AI prompts through a five-step Action → Role → Conte…

22:37
2026-10-28
mirendil.com
ai-agents

Mirendil Launches Lor Harness

Mirendil launched Lor, a private-beta harness whose agents write code, run experiments and iterate for days across hundreds of parallel agents on any machine, including provisioning their own GPU nodes. Lor runs frontier…

19:29
2026-10-28
dev.to
ai-agents

AI Agent Regression Testing: Production Traces to CI

Julien Wuthrich released Tracely, an MIT-licensed open-source project that turns failing production agent traces into deterministic CI regression tests by recording tool and model outputs as replayable fixtures. The tool…

19:01
2026-10-28
dev.to
ai-agents

Wrapping Claude Code and Codex in Electron: A Stop Bug

A solo developer building Refmade, an Electron desktop wrapper that drives the user's own installed Claude Code and Codex binaries via stream-json and JSON-RPC over stdio, found during end-to-end testing that pressing St…

18:23
2026-10-28
ideas.fin.ai
artificial-intelligence

Build vs buy: Is it still either/or?

A survey of 300 support leaders by Intercom found that while just over a third currently use their vendor's AI as-is, only 2% plan to keep it that way in 12 months, with 37% intending to build their own interface on top …

18:12
2026-10-28
ca.finance.yahoo.com
artificial-intelligence

Google launches Gemini 4 Carbon AI model with cybersecurity focus

Google unveiled Gemini 4 Carbon on Wednesday, a frontier AI model the company says delivers state-of-the-art performance on cybersecurity tasks including vulnerability discovery, exploitation and software patching, and g…

17:26
2026-10-28
cryptobriefing.com
artificial-intelligence

Gemini 4 Carbon secures top spots in AI arenas, showcases potential

Google DeepMind's Gemini 4 Carbon debuted at first place in the Text Arena, second in the Agent Arena and fourth in the Code Arena: WebDev, according to continuously updated rankings from Arena. The model, which follows …

17:00
2026-10-28
dev.to
ai-agents

How LLMs Actually Discover and Call MCP Tools (Under the Hood)

A developer's technical breakdown explains that LLMs never connect to sockets or run code themselves, but instead emit structured tool-call tokens that a host application translates into JSON-RPC requests to MCP servers …

← prev page 981 / 1320 next →