Feed aggregator

Article URL: https://www.wsj.com/us-news/americans-leaving-the-us-migration-a5795bfa

Comments URL: https://news.ycombinator.com/item?id=47161219

Points: 13

# Comments: 2

Here are hints and the answers for the NYT Connections: Sports Edition puzzle for Feb. 26, No. 521.

I built OpenSwarm because I wanted an autonomous “AI dev team” that can actually plug into my real workflow instead of running toy tasks. OpenSwarm orchestrates multiple Claude Code CLI instances as agents to work on real Linear issues. It: • pulls issues from Linear and runs a Worker/Reviewer/Test/Documenter pipeline • uses LanceDB + multilingual-e5 embeddings for long‑term memory and context reuse • builds a simple code knowledge graph for impact analysis • exposes everything through a Discord bot (status, dispatch, scheduling, logs) • can auto‑iterate on existing PRs and monitor long‑running jobs Right now it’s powering my own solo dev workflow (trading infra, LLM tools, other projects). It’s still early, so there are rough edges and a lot of TODOs around safety, scaling, and better task decomposition. I’d love feedback on: • what feels missing for this to be useful to other teams • failure modes you’d be worried about in autonomous code agents • ideas for better memory/knowledge graph use in real‑world repos Repo: https://github.com/Intrect-io/OpenSwarm Happy to answer questions and hear brutal feedback.

Comments URL: https://news.ycombinator.com/item?id=47160980

Points: 1

# Comments: 0

I reset the structure hundreds of times to get here. Each time I was sure, I tore it down to zero again. Failure was the only friend that kept giving direction.

What remained after all that:

- Don't Trust, Verify - Not a single byte changes - If it cannot be reproduced, it is not evidence

EV424 is just deterministic byte-sameness receipts. No interpretation. No truth claims. No hosting originals. Only G1–G5 closed gates → reproducible PASS/FAIL.

Still early. Mostly spec, not much code yet. But the question that keeps coming back is: In a world where AI makes everything look convincing fast, is "reproducible only" still enough?

https://github.com/ev424verify/ev424-hub

Comments URL: https://news.ycombinator.com/item?id=47160976

Points: 1

# Comments: 0

Article URL: https://im.not.ci/echo-mini-rse/

Comments URL: https://news.ycombinator.com/item?id=47160972

Points: 1

# Comments: 0

Article URL: https://usplus.ai:443/

Comments URL: https://news.ycombinator.com/item?id=47160962

Points: 1

# Comments: 0

Article URL: https://arenamag.com/articles/the-lives-of-secrets

Comments URL: https://news.ycombinator.com/item?id=47160918

Points: 1

# Comments: 0

Article URL: https://www.axios.com/2026/02/25/anthropic-pentagon-blacklist-claude

Comments URL: https://news.ycombinator.com/item?id=47160897

Points: 1

# Comments: 0

Is the Mini Crossword too easy, but the original one just too time-consuming? Here's your new puzzle.

Article URL: https://github.com/w3c/csswg-drafts/issues/13271

Comments URL: https://news.ycombinator.com/item?id=47160864

Points: 1

# Comments: 0

Article URL: https://twitter.com/fitly_ai/status/2026832485804384576

Comments URL: https://news.ycombinator.com/item?id=47160862

Points: 1

# Comments: 0

Article URL: https://www.ade.pt/the-glass-transition-problem/

Comments URL: https://news.ycombinator.com/item?id=47160859

Points: 1

# Comments: 0

Just talk to it like a person. No scanning, no searching. It tracks everything, coaches based on goals, and surfaces insights. Built solo with agentic tools. Real model + orchestration + tooling behind the scenes. BETA testing now.

Comments URL: https://news.ycombinator.com/item?id=47160857

Points: 1

# Comments: 0

Are there any ways that coordinated activity by large numbers of users could take down a major website? (And if there are, how large would the number of users need to be, and what would they have to do?)

Comments URL: https://news.ycombinator.com/item?id=47160853

Points: 1

# Comments: 2

Article URL: https://github.com/DatanoiseTV/aigateway

Comments URL: https://news.ycombinator.com/item?id=47160828

Points: 1

# Comments: 3

Article URL: https://techcrunch.com/2026/02/24/its-time-to-pull-the-plug-on-plug-in-hybrids/

Comments URL: https://news.ycombinator.com/item?id=47160812

Points: 1

# Comments: 0

ADT's acquisition of Origin AI brings presence-sensing technology under the home security company's umbrella.

Article URL: https://en.wikipedia.org/wiki/Braided_river

Comments URL: https://news.ycombinator.com/item?id=47160758

Points: 1

# Comments: 0

I've been a developer for 20+ years and reviewer selection has been a recurring problem at every company I've worked at. Either you're a CODEOWNER getting spammed on every PR, or you're in Slack trying to find someone who actually knows the code you changed. CODEOWNERS is too coarse — it maps paths to people, but doesn't account for who's available, who reviewed this author before, or who actually touched these files recently.

I built PullMaster to fix this. It's a GitHub App that analyzes your repo's actual history and recommends the best reviewer for each PR. It adapts to the risk level of each change, so critical PRs surface experienced reviewers while routine ones get distributed across the team.

Install the GitHub App and comment `@pullmaster-ai suggest` on a PR to get a recommendation with an explanation, or `@pullmaster-ai assign` to also request the review automatically. No configuration needed — it learns from your repo as soon as it's installed.

It's free. I'd use it at my day job but being in a heavily regulated industry without SOC 2 makes that a non-starter, so I'm looking for early users and feedback. Happy to answer questions about how it works.

https://www.pullmaster.ai

Comments URL: https://news.ycombinator.com/item?id=47160745

Points: 1

# Comments: 0