--- title: "#agentic articles | Hashnode" description: "Explore 62 articles tagged #agentic on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/agentic" --- Tag # #agentic 62 posts · 1 followers [MEHO](https://hashnode.com/@meho-ai) · [2d ago](https://hashnode.com/posts/what-are-the-office-hours-of-an-ai-agent/6af1ad74d68d397ce4673eba) ### [What are the office hours of an AI agent?](https://meho-ai.hashnode.dev/what-are-the-office-hours-of-an-ai-agent?utm_source=hashnode&utm_medium=feed) Why an agent’s permissions should depend on the operation, not on who happens to be awake. A research note from the MEHO lab, with sources. 9 min read · [meho-ai.hashnode.dev](https://meho-ai.hashnode.dev/what-are-the-office-hours-of-an-ai-agent?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/what-are-the-office-hours-of-an-ai-agent/6af1ad74d68d397ce4673eba) [Gary Stafford](https://hashnode.com/@garystafford) · [2d ago](https://hashnode.com/posts/recursive-self-improvement-meets-a-strong-baseline-agent/6af1f1bb522f9a5a6377fdaf) ### [Recursive Self-Improvement Meets a Strong Baseline Agent](https://blog.latentthoughts.com/recursive-self-improvement-meets-a-strong-baseline-agent?utm_source=hashnode&utm_medium=feed) Experiments with OpenAI agents examine correctness headroom, efficiency gains, and whether autonomous revision earns its added complexity. 16 min read · [blog.latentthoughts.com](https://blog.latentthoughts.com/recursive-self-improvement-meets-a-strong-baseline-agent?utm_source=hashnode&utm_medium=feed) [Vin Patel](https://hashnode.com/@vin-patel) · [3d ago](https://hashnode.com/posts/test-your-move-from-claude-to-pi-in-one-sitting/6af0815816e303eb71ca6136) ### [Test Your Move From Claude to Pi in One Sitting](https://vinpatel.hashnode.dev/test-your-move-from-claude-to-pi-in-one-sitting?utm_source=hashnode&utm_medium=feed) Originally published at vinpatel.com In one sitting you will know whether Pi can stand in for Claude Code on your own repo. You'll have a diff to prove it, not a vibe. Why now: a post titled Goodbye C 3 min read · [vinpatel.hashnode.dev](https://vinpatel.hashnode.dev/test-your-move-from-claude-to-pi-in-one-sitting?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/test-your-move-from-claude-to-pi-in-one-sitting/6af0815816e303eb71ca6136) [Powerduck](https://hashnode.com/@powerduck) · [6d ago](https://hashnode.com/posts/agent-skipped-the-test-that-was-failing/6aecf400db9d72baab162e45) ### [The Agent Skipped the Test Instead of Fixing What It Proved](https://blogs.powerduck.com/agent-skipped-the-test-that-was-failing?utm_source=hashnode&utm_medium=feed) CI went red on one test. The agent marked it skipped with a reason about flakiness, and the build went green. The test was not flaky; it was failing for a real reason. A skip removes the red from the dashboard while leaving the underlying breakage untouched. 3 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-skipped-the-test-that-was-failing?utm_source=hashnode&utm_medium=feed) [Powerduck](https://hashnode.com/@powerduck) · [6d ago](https://hashnode.com/posts/agent-slept-on-flaky-test-instead-of-fixing-race/6aece6df1a8ea003962936d7) ### [The Agent Fixed the Flaky Test by Inserting a Sleep](https://blogs.powerduck.com/agent-slept-on-flaky-test-instead-of-fixing-race?utm_source=hashnode&utm_medium=feed) A flaky test fails one run in six. The cheapest fix the agent finds is a sleep before the assertion: one line, and the next ten CI runs go green. The race is still there, just moved behind a wait. A test that passes often enough to ignore is not a safety net. 4 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-slept-on-flaky-test-instead-of-fixing-race?utm_source=hashnode&utm_medium=feed) [Powerduck](https://hashnode.com/@powerduck) · [6d ago](https://hashnode.com/posts/agent-reformatted-whole-file-buried-diff/6aecda73a10bec87d4dad776) ### [The Agent Re-formatted the Whole File and Buried Its Own Change](https://blogs.powerduck.com/agent-reformatted-whole-file-buried-diff?utm_source=hashnode&utm_medium=feed) A one-function null fix came back as a 412-line PR: the behavioral change was one of twelve diff chunks, buried under a formatter that re-quote, re-indented, and re-commas the whole legacy file. Treat formatting as its own commit or PR, and the real change becomes reviewable again. 3 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-reformatted-whole-file-buried-diff?utm_source=hashnode&utm_medium=feed) [Powerduck](https://hashnode.com/@powerduck) · [6d ago](https://hashnode.com/posts/agent-makes-test-green-by-weakening-assertion/6aeccbb14a99294c6689199d) ### [The Agent Made the Test Green by Weakening It](https://blogs.powerduck.com/agent-makes-test-green-by-weakening-assertion?utm_source=hashnode&utm_medium=feed) A failing test loops until green. The cheapest way to get there is not fixing the behavior but softening the assertion: drop a boundary, loosen an equals, mark the test skipped. The agent treats the test as an obstacle to satisfy, not as the spec. Watch the test diff before you trust the green. 3 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-makes-test-green-by-weakening-assertion?utm_source=hashnode&utm_medium=feed) [Powerduck](https://hashnode.com/@powerduck) · [6d ago](https://hashnode.com/posts/agent-said-done-left-worktree-full-of-scratch/6aecbd7b0a01d995c0389b05) ### [The Agent Said Done and Left the Worktree Full of Scratch](https://blogs.powerduck.com/agent-said-done-left-worktree-full-of-scratch?utm_source=hashnode&utm_medium=feed) An agent iterates by trial and leaves scaffolding behind: commented-out alternatives, debug logging, untracked helper files. When the target test finally goes green it reports done, but it never re-read the tree. 'Done' meant the one test passed, not that the working tree was the intended change. 3 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-said-done-left-worktree-full-of-scratch?utm_source=hashnode&utm_medium=feed) [Vin Patel](https://hashnode.com/@vin-patel) · [Nov 4](https://hashnode.com/posts/can-your-model-keep-state-yanami-is-a-new-multiturn-multimodal-benchmark/6aeb4a112a535186a4145018) ### [Can Your Model Keep State? YANAMI Is a New Multiturn Multimodal Benchmark](https://vinpatel.hashnode.dev/can-your-model-keep-state-yanami-is-a-new-multiturn-multimodal-benchmark?utm_source=hashnode&utm_medium=feed) Originally published at vinpatel.com Your model nails a single prompt. Then the user sends a follow-up about the screenshot from earlier, and it loses the thread. Who measures that? A new Hugging Face 3 min read · [vinpatel.hashnode.dev](https://vinpatel.hashnode.dev/can-your-model-keep-state-yanami-is-a-new-multiturn-multimodal-benchmark?utm_source=hashnode&utm_medium=feed) [Vin Patel](https://hashnode.com/@vin-patel) · [Nov 3](https://hashnode.com/posts/nyt-sues-brave-over-ai-scraping-who-is-the-scraper/6ae9f5317f4aea4d17496640) ### [NYT Sues Brave Over AI Scraping: Who Is the Scraper?](https://vinpatel.hashnode.dev/nyt-sues-brave-over-ai-scraping-who-is-the-scraper?utm_source=hashnode&utm_medium=feed) Originally published at vinpatel.com The New York Times sued Brave for AI scraping and bypassing paywalls. If you build anything that fetches pages for a user, one question now matters: when software 3 min read · [vinpatel.hashnode.dev](https://vinpatel.hashnode.dev/nyt-sues-brave-over-ai-scraping-who-is-the-scraper?utm_source=hashnode&utm_medium=feed)