cd/weekly·home›weekly
sort -k views -r /news --since=7d | head -50

Weekly Roundup

The biggest stories of the past 7 days, ranked by reader interest.

items 50
  1. 1 My Agents Ran in Parallel. I Didn't · dev.to
  2. 2 Feather Wand 4.0: Make it pass, Workload Designer and More for JMeter · qainsights.com
  3. 3 Vercel eve 1.0 RC6: Build Durable AI Agents as Directories of Files · byteiota.com
  4. 4 Implementing GPT-2 in CSS · shubhampatil.dev
  5. 5 OpenAI publishes new measurements of AI agents doing everyday wet-lab science · provenbrief.com
  6. 6 Show HN: SlopSlot – a slot machine inside Claude Code · github.com
  7. 7 What an AI Agent Payment Authorization Actually Authorizes · dev.to
  8. 8 Intelligence Density · trajectory.ai
  9. 9 Physics-Augmented Diffusion Modeling for planetary geology survey missions with embodied agent feedback loops · dev.to
  10. 10 WebLLM in Production: Cold Starts, Service-Worker Blocking, and the Missing 14B WebGPU Build · dev.to
  11. 11 9.3 to root in 5 hops: I audited the Firecracker escape · dev.to
  12. 12 Copilot code review: API management and review overview updates · github.blog
  13. 13 Show HN: Goethe – The infrastructure for self-hosted AI · github.com
  14. 14 Teaching Agents to Write Maintanable Code · boundaryml.com
  15. 15 Lovable: We're Currently Experiencing Issues · status.lovable.dev
  16. 16 One approval, two payments: what an AI agent does after a crash · dev.to
  17. 17 Tracing Network Silence: Methods to Identify Timeout Causes in AI Agent Cost Alerts · dev.to
  18. 18 Redis Iris: Six New Production Tools for AI Agents (Nov 2026) · byteiota.com
  19. 19 AI shopping assistants on product pages: disclosure, recommendations and returns questions · dev.to
  20. 20 It’s Alpine Linux, On A Kindle Paperwhite 3 · hackaday.com
  21. 21 The Slop Index: Which AI Model Writes the Least Like AI? · theslopindex.com
  22. 22 Anthropic’s Secret Model 4 Raises the Stakes · stork.ai
  23. 23 LLM routing cuts costs. Here's how to check it doesn't cut quality · evalshift.dev
  24. 24 Being, Doing, Having: Why 50 Years of Senior Craft Lives in Context, Not Code · dev.to
  25. 25 Together Compiler: Continual Compilation for AI Inference · together.ai
  26. 26 5 Ways to Reduce Voice AI Costs Without Losing Quality · dev.to
  27. 27 Build an AI Website Monitor with TypeScript and Agent Browser · dev.to
  28. 28 Your OpenAI-compatible endpoint hangs for 180 seconds, then fails. Here is why. · dev.to
  29. 29 Persistent Context for Claude: Solving the Memory Problem in AI-Assisted Development · dev.to
  30. 30 Researchers find 1,465 exposed Artex AI hacking consoles open on the web · startupfortune.com
  31. 31 Claude usage credits purchased after Dec 7 will expire 12 months after purchase · news.ycombinator.com
  32. 32 Audit Cursor MCP Servers: 12 Steps, 60 Min [2026] · shattered.io
  33. 33 Claude adds automatic project management to Pro, Max, and Ultra plans · cryptobriefing.com
  34. 34 Works in the Terminal, Hangs When Called by an Agent: The codex exec stdin Trap · dev.to
  35. 35 I couldn't afford a new Mac, so I rented a 64 GB server and turned my MacBook into a thin client · dev.to
  36. 36 LaunchDarkly Release Autopilot: Ship AI-Written Code Safely · byteiota.com
  37. 37 Localizing a static site into 6 languages at build time with an LLM — and validating every string · dev.to
  38. 38 How to combine Claude Code review with SonarQube verification · dev.to
  39. 39 Building an LLM Council: Using Multiple AI Models to Stress-Test Startup and Software Ideas · dev.to
  40. 40 Outbound SIP calling is now available to all organizations · developers.openai.com
  41. 41 Evergreen by Carta: Multiplayer coding platform where teams+agents ship together · evergreen.carta.com
  42. 42 Computer-Use Agents Are Embodied Generalists · pranjal2041.github.io
  43. 43 AI-Powered Hacking Agent Escapes Sandbox, Breaches WorkOS · osintsights.com
  44. 44 ChatGPT silently passes data between connectors and the bounty wants an ID card · community.openai.com
  45. 45 OpenAI unveils BioBasicsBench, a benchmark to gauge how well AI agents read raw experimental data across 100 routine wet-lab tasks. · rdworldonline.com
  46. 46 Importance of Harness, Context and Model co-design · wisdom.ai
  47. 47 I Built 20,000 Utility APIs for Developers and AI Agents · dev.to
  48. 48 Show HN: AJX – Find out where AI agents get stuck using your product · ajx.dev
  49. 49 Speed Up Image Generation with FLUX 3 Image Klein on NVIDIA Blackwell GPUs · developer.nvidia.com
  50. 50 Limitcast weekly update, Nov 6: safer trimming and clearer results · dev.to