Hacker News

I have been working on this tool for a while now as there is a clear gap in Developer workstation security. You must have seen how Github got hacked due to a malicious IDE Extension. This tool in it's current state can help collect IDEs and it's Extensions installed on end user machines, detect the permissions acquired by these extensions and whether there is a post install script. It also fetches the dependencies used by the extensions and any known vulnerabilities.

I'm continuously working on the tool to improve it. My objective is to add a lot of the features that usually an enterprise grade tools have.

Comments URL: https://news.ycombinator.com/item?id=48225861

Points: 1

# Comments: 0

Article URL: https://arcplane.ai/journal/software-is-not-solved

Comments URL: https://news.ycombinator.com/item?id=48225860

Points: 2

# Comments: 1

Article URL: https://arstechnica.com/gadgets/2026/05/us-government-takes-2-billion-equity-stake-in-nine-quantum-computing-firms/

Comments URL: https://news.ycombinator.com/item?id=48225858

Points: 1

# Comments: 1

Article URL: https://www.wsj.com/business/tobacco-giant-donated-5-million-to-maga-inc-shortly-before-vaping-decision-3318d5db

Comments URL: https://news.ycombinator.com/item?id=48225857

Points: 1

# Comments: 1

Article URL: https://ampcode.com/news/amp-labs

Comments URL: https://news.ycombinator.com/item?id=48225851

Points: 1

# Comments: 0

Article URL: https://techcrunch.com/2026/05/21/a-new-fragrance-company-raises-2-million-to-find-new-scent-molecules/

Comments URL: https://news.ycombinator.com/item?id=48225842

Points: 1

# Comments: 1

Article URL: https://www.niemanlab.org/2026/05/more-than-340-local-news-outlets-are-limiting-the-internet-archives-access-to-their-journalism/

Comments URL: https://news.ycombinator.com/item?id=48225838

Points: 2

# Comments: 0

Article URL: https://apnews.com/article/malaysia-tiktok-king-offensive-content-a9327060bdd4e4ce90c5e6021b8637c7

Comments URL: https://news.ycombinator.com/item?id=48225110

Points: 1

# Comments: 0

Article URL: https://www.cbsnews.com/news/jeff-bezos-zero-federal-income-tax-lower-earners/

Comments URL: https://news.ycombinator.com/item?id=48225108

Points: 1

# Comments: 0

Article URL: https://arstechnica.com/tech-policy/2026/05/fbi-seeks-us-wide-access-to-license-plate-cameras-wants-data-in-near-real-time/

Comments URL: https://news.ycombinator.com/item?id=48225067

Points: 1

# Comments: 0

Article URL: https://www.law.com/2026/05/21/public-vs-private-nuisance-emerging-litigation-deploys-time-tested-tactics-against-data-centers/

Comments URL: https://news.ycombinator.com/item?id=48225058

Points: 1

# Comments: 0

Article URL: https://ieeexplore.ieee.org/document/8721355

Comments URL: https://news.ycombinator.com/item?id=48225056

Points: 2

# Comments: 0

Article URL: https://sync-o.io/

Comments URL: https://news.ycombinator.com/item?id=48225034

Points: 1

# Comments: 1

Article URL: https://posthog.com/blog/ai-native-hiring

Comments URL: https://news.ycombinator.com/item?id=48225017

Points: 2

# Comments: 0

Article URL: https://thehill.com/homenews/administration/5885763-irs-trump-tax-returns-settlement-agreement/

Comments URL: https://news.ycombinator.com/item?id=48224999

Points: 2

# Comments: 0

I built this because my coding agent kept telling me he did complete the task, but when I verified it, it was not the case.

I made Proof Loop fairly light, intentionally. It’s basically a protocol helper script for AI agent tasks:

- set acceptance criteria before coding/implementation - keep the builder and verifier roles separate - each criteria tested with results PASS, FAIL or UNKNOWN - attach evidence of done - keep the proof evidence in the repo, so that the next agent / run can inspect it and see what was already done

You can try it via commandline from the cloned repo, go the the proof-loop directory and run make demo.

Teh demo creates a task, checks the proof bundle, fails if evidence is missing, then passes when acceptance criteria have evidence attached.

There is also an OpenClaw skill version now, so the easiest use is

openclaw skills install proof-loop

In the GitHub repo, there is harness-agnostic version and examples.

I would especially like criticism and/or any feedback from people who run Codex, Claude Code or OpenCode on long-running multi-step tasks.

Note this is a utility that I use myself, FoC, MIT Licensed, OpenSourced, with no intention of any commercialization.

Comments URL: https://news.ycombinator.com/item?id=48224992

Points: 1

# Comments: 0

Article URL: https://github.com/TheRealSavi/iOpenPod

Comments URL: https://news.ycombinator.com/item?id=48224991

Points: 1

# Comments: 0

Hi HN! Outside of the hackernews bubble we often find engineers who are barely using AI (aka using microsoft copilot) and we needed an easy way to show the latest capabilities in a non confusing UI.

So we dumbed down our product to a simple text box UI where you one-shot your feature and you get an email with a link to a PR in github. The backend is hosted in Cloudflare, spinning sandboxes in Daytona that run the Opencode harness.

Feel free to give it a try or share it with people who are skeptical of the latest models. You get a bunch of credits for anthropic, openai & opensource models during onboarding + you can connect your codex sub.

Comments URL: https://news.ycombinator.com/item?id=48224982

Points: 2

# Comments: 0

Article URL: https://npmfind.com

Comments URL: https://news.ycombinator.com/item?id=48224981

Points: 1

# Comments: 0

Article URL: https://metedata.substack.com/p/013-my-hermes-and-obsidian-set-up

Comments URL: https://news.ycombinator.com/item?id=48224966

Points: 1

# Comments: 0