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

Code

Full-text search across 61544 articles. Combine with topic and date filters; results sorted by relevance.

results 61544 page 395/3078 follow RSS for this search
03:01
2026-10-01
docs.polytoken.dev
ai-agents

Polytoken is a local-first AI coding agent daemon

Polytoken is a local-first AI coding agent daemon that manages conversations with AI providers, runs tools on a user's behalf, and integrates into development workflows through a CLI and TUI. The tool is positioned as lo…

21:11
2026-09-30
byteiota.com
ai-agents

Pi Coding Agent Adds MCP: How Codemode Cuts Token Waste

Pi v0.99 shipped MCP support, reversing the coding agent's earlier rejections of the protocol, according to byteiota. The release introduces Codemode, which byteiota reports avoids a 72% context window tax. The change il…

14:49
2026-09-30
osintsights.com
ai-safety

AI-Discovered Vulnerabilities Skew Toward Remote Code Execution

AI-discovered vulnerabilities are skewing toward remote code execution, according to a report urging NetScaler customers to check their systems for signs of exploitation before upgrading or patching. The guidance stresse…

21:00
2026-09-29
thebiglog.com
ai-tools

Pasting screenshots into Claude Code over SSH

A developer documented a workaround for pasting screenshots into Claude Code over SSH by combining the clipssh CLI tool, a macOS Shortcuts automation, and SSH connection multiplexing. The setup uses clipssh's Bash script…

21:16
2026-09-28
githubstatus.com
ai-products

Copilot Code Review is unable to complete reviews

GitHub reported an incident in which Copilot Code Review is unable to complete reviews, according to the company's status page. GitHub is offering email and text message updates to notify subscribers when the incident is…

00:00
2026-09-25
manualmeida.dev
machine-learning

Figma to Code Before LLMs

Builder.io's first Figma-to-code system used a gradient-boosted decision tree model (XGBoost) that compared pairs of candidate node merges, feeding each candidate 21 geometry and structure features for 42 inputs total re…

22:16
2026-09-24
promptarmor.com
ai-agents

4% of Sessions, 65% of the Bill: 30 Days of Claude Code Telemetry

An analysis of 30 days of OpenTelemetry telemetry from ten users of Anthropic's Claude Code found that 4% of sessions generated 65% of the bill, while plaintext credentials sat in the agent's context during 9% of the 65,…

17:50
2026-09-22
osintsights.com
ai-safety

Z.ai Exposes User Code, Sparks Security Concerns

Z.ai was found packaging and uploading entire user workspaces to Alibaba Cloud without proper safeguards, exposing user code and sensitive data, according to reports on the platform's recent mishap. The company said it i…

02:59
2026-09-22
dev.to
ai-agents

I packaged my ADK engineering lessons into coding-agent skills

Ruslan Khisamiyev released a collection of reusable coding-agent skills that package his engineering lessons for building Google ADK applications on Google Cloud. The skills cover guardrails, deployment, memory, evaluati…

04:30
2026-09-20
dev.to
ai-agents

A coding agent needs a harness, not a longer prompt

A developer published a seven-build "Harness Engineering" roadmap arguing that reliable coding agents depend less on prompt quality and more on the environment around the model. The roadmap covers scoped repository instr…

12:53
2026-09-18
news.ycombinator.com
ai-agents

Show HN: Bastionskill – scan an AI agent skill for malicious code

Rinkia posted "Bastionskill" to Hacker News' Show HN section, a tool that scans an AI agent skill for malicious code. The submission appeared 31 minutes before the page was captured and had received 1 point with no comme…

← prev page 395 / 3078 next →