Long-running Claude for scientific computing
Science Long-running Claude for scientific computing Mar 23, 2026 In this post, Siddharth Mishra-Sharma , a researcher on the Discovery team, explains how to apply multi-day agentic coding workflows—test…
Search
All sources
xda-developers.com
32
anthropic.com
16
theregister.com
14
pcworld.com
7
developer.nvidia.com
7
wired.com
4
arstechnica.com
4
blog.cloudflare.com
4
theverge.com
3
github.blog
3
computerbase.de
3
9to5mac.com
3
Videos
More videosTop stories
Microsoft taps Claude to make Copilot Cowork a better agent
AI + ML Microsoft taps Claude to make Copilot Cowork a better agent Copilot gets tuned to handle long-running knowledge work tasks Microsoft on Monday celebrated freedom of choice by giving customers…
Qt's Latest AI Push Is Letting AI Agents Deal With Performance Profiling
…3 Comments The Qt Group announced today the QML Profiler Skill for Agentic Development. This new "skill" can delegate code performance profiling to AI agents for 2D Qt Quick applications. The hope…
I customized Claude Code to interrupt me with Warcraft sounds, and now I actually notice when it's done
…And now I don't, because I found a tool that gives Claude Code (or most other agentic IDEs) notification sound effects from some of the games from my youth, and it…
Discussions and forums
Show HN: Agent-estimate, how long a coding task takes, at agent speed
I have used Codex & Claude Code for coding for a while, but how long a coding task will actually take? When I ask Claude Code to estimate, the result is often from training data, which is based on human speed. That’s why…
3
1
CodeGuilds – community registry for Claude Code (skills, agents, MCP servers)
CodeGuilds – community registry for Claude Code (skills, agents, MCP servers)
2
Show HN: Claude Code plugin for deep multi-agent code reviews
Show HN: Claude Code plugin for deep multi-agent code reviews
1
Agentlocks – advisory file locks for Codex and Claude Code in one worktree
Agentlocks – advisory file locks for Codex and Claude Code in one worktree
2
LiteLLM Agent Platform: Run Claude Code/Codex On-Prem Sandboxes and Vaults
LiteLLM Agent Platform: Run Claude Code/Codex On-Prem Sandboxes and Vaults
3
Full-Stack Optimizations for Agentic Inference with NVIDIA Dynamo | NVIDIA Technical Blog
Coding agents are starting to write production code at scale. Stripe’s agents generate 1,300+ PRs per week. Ramp attributes 30% of merged PRs to agents. Spotify reports 650+ agent-generated…
Claude Opus 4.8 launches today with agentic improvements, new features
…In a comparison with Opus 4.7, there are some clear areas of improvement in agentic coding, computer use, and reasoning. Anthropic specifically says that Opus 4.8 is meant to be…
Anthropic's Cat Wu says that, in the future, AI will anticipate your needs before you know what they are | TechCrunch
…Topics agents , AI , Anthropic , Cat Wu , Claude , claude code When you purchase through links in our articles, we may earn a small commission . This doesn’t affect our editorial independence. Lucas Ropek…
Claude Code installed my IDE, and now I can't go back to manual setup
…Related Claude Code, Codex, and Pi can create their own AI agents now, and that changes everything Your LLM agents are smarter than you think Now that AI agents can do things…
Anthropic's Claude subscriptions no longer include Agent SDK and claude -p usage
…Sign in to your XDA account Summary Paid Claude plans get a dedicated monthly programmatic credit for Agent SDK, claude -p, Claude Code GitHub Actions. Subscription interactive credits no longer cover programmatic…
Orchestrating AI Code Review at scale
…Instead of building a monolithic code review agent from scratch, we decided to build a CI-native orchestration system around OpenCode , an open-source coding agent. Today, when an engineer at Cloudflare…