Feed aggregator

What if hacker news was structured like an IRC client. Utilizes the Firebase API and has full keyboard navigation support.

Hope someone enjoys it, feedback welcome.

Comments URL: https://news.ycombinator.com/item?id=47347289

Points: 1

# Comments: 0

Article URL: https://chromewebstore.google.com/detail/dopamine-detox/emohipjjikifpmfibhnjbfeklbnjkica

Comments URL: https://news.ycombinator.com/item?id=47347279

Points: 1

# Comments: 1

I want to share what we’ve achieved working with architectural drift. Linters and tests help check code correctness and style, but they can’t effectively identify structural deviations that may accumulate over time and affect the long-term stability of a project. So, we asked ourselves how we can proactively manage such risks.

In the search for an answer, we came across an approach that takes into account not only the syntax and functionality but also the code structure. It’s based on analyzing changes in a project’s architecture by modeling its structural integrity. This method allows us to track deviations from the historical code structure, which is critical for long-term maintainability and scalability.

The foundation for this approach is the theoretical model PhaseBrain, which uses a toroidal representation to analyze the dynamics of structural changes. This allows us to capture deviations that are not visible to standard tools but can significantly impact the project’s architecture.

The translation of this theory into practice led to the creation of a tool that integrates into the code review process and analyzes changes in pull requests. This tool works with the code in the context of its historical structure, highlighting areas that may affect the architectural integrity of the project.

As a result, each PR is analyzed, and hidden dependencies and changes are identified that could be missed in traditional analysis. The system flags these changes as potentially dangerous to the structure and provides a report for further analysis. All of this happens within the familiar code review process.

The technology was implemented as a GitHub App, which is available on the GitHub marketplace.

We invite developers interested in this topic to test the proposed tool and share their experiences. Feedback would be very helpful for us.

Thank you for reading, and have a great day!

Comments URL: https://news.ycombinator.com/item?id=47347273

Points: 1

# Comments: 1

Article URL: https://arstechnica.com/tech-policy/2026/03/use-a-gun-or-beat-the-crap-out-of-him-ai-chatbot-urged-violence-study-finds/

Comments URL: https://news.ycombinator.com/item?id=47347259

Points: 1

# Comments: 0

Article URL: https://www.fasterhorses.md/articles/cartown

Comments URL: https://news.ycombinator.com/item?id=47347243

Points: 1

# Comments: 0

Article URL: https://substack.com/home/post/p-190315082

Comments URL: https://news.ycombinator.com/item?id=47347236

Points: 1

# Comments: 0

Article URL: https://www.theverge.com/cs/features/877388/white-collar-workers-training-ai-mercor

Comments URL: https://news.ycombinator.com/item?id=47347216

Points: 2

# Comments: 0

Hi HN,

The problem that led to this: I'd ask an AI to find flights London → Tokyo in April under £800, get good results, then ask "what if I fly a week later?" — and it would lose everything. Dates, budget, origin, all of it. Back to re-entering the whole query.

That's not a prompt engineering problem. It's a stateless architecture problem. Every follow-up reconstructs context from scratch.

JetSet AI runs each session on a persistent VM via SuperNinja rather than a stateless serverless function. The full runtime state stays in memory — "show me the cheapest of those on a Tuesday" or "what if I fly into Osaka instead?" resolves to exactly the results from 3 turns ago, not a semantic approximation.

What it does: — Real-time flight pricing (live API, not cached) — Natural language queries ("something direct, not too early, under £600, flexible by a few days") — Full conversation memory within a session — Direct booking deep-links to Skyscanner/Kayak with your search pre-filled

What it doesn't do yet: — Cross-session memory (each conversation starts fresh) — Hotel/car search — Automatic booking (links out to booking platforms)

Try it (free, no login): https://bit.ly/4besn7l

The trade-off: persistent VMs cost more per session than serverless. For single-turn lookups it wouldn't be worth it. For multi-turn transactional flows where follow-up accuracy matters, it is.

Curious whether anyone else has hit this problem building conversational agents — and whether persistent VMs vs stateless + RAG is the right trade-off for your use case.

Comments URL: https://news.ycombinator.com/item?id=47347214

Points: 1

# Comments: 0

Article URL: https://brunelly.com/

Comments URL: https://news.ycombinator.com/item?id=47347206

Points: 1

# Comments: 1

Article URL: https://www.youtube.com/watch?v=WpbGF7l-t2w

Comments URL: https://news.ycombinator.com/item?id=47347198

Points: 3

# Comments: 1

In this podcast interview, we speak to Seth Ravin, CEO of Rimini Street about how AI improves support call handling

Article URL: https://mayberay.bearblog.dev/my-favourite-thing-about-rust-is-the-compiler/

Comments URL: https://news.ycombinator.com/item?id=47347174

Points: 2

# Comments: 0

What's the best DNS adblocker?

Comments URL: https://news.ycombinator.com/item?id=47347170

Points: 2

# Comments: 0

Article URL: https://github.com/msitarzewski/agency-agents

Comments URL: https://news.ycombinator.com/item?id=47347158

Points: 2

# Comments: 0

Article URL: https://blog.replit.com/introducing-agent-4-built-for-creativity

Comments URL: https://news.ycombinator.com/item?id=47347155

Points: 3

# Comments: 0

Article URL: https://dashbit.co/blog/distributed-python-livebook

Comments URL: https://news.ycombinator.com/item?id=47347139

Points: 2

# Comments: 0

Article URL: https://xeiaso.net/blog/2026/ai-abstraction/

Comments URL: https://news.ycombinator.com/item?id=47347137

Points: 2

# Comments: 0

Article URL: https://www.abc.net.au/news/2026-03-12/us-behind-iran-girls-school-strike-media-reports/106444554

Comments URL: https://news.ycombinator.com/item?id=47346998

Points: 1

# Comments: 1

Article URL: https://www.wsj.com/tech/ai/ai-isnt-lightening-workloads-its-making-them-more-intense-e417dd2c

Comments URL: https://news.ycombinator.com/item?id=47346996

Points: 1

# Comments: 0

Article URL: https://discord.com/blog/tracing-discords-elixir-systems-without-melting-everything

Comments URL: https://news.ycombinator.com/item?id=47346990

Points: 1

# Comments: 0