Modern NewsTopAskShowBestNew

New

Windscribe partners with Kagi and others to create a Privacy-Focused Alliance

by wasmitnetzen · 2 minutes ago

1|windscribe.com|0 comments

Scott Adams, 'Dilbert' Creator Who Courted Controversy, Dead at 68

by mellosouls · 2 minutes ago

1|www.rollingstone.com|0 comments

Taiwan Issues Arrest Warrant for OnePlus CEO for China Hires

by MallocVoidstar · 3 minutes ago

2|www.bloomberg.com|1 comments

I built a free URL shortener with QR codes and tracking – looking for feedback

by johnvonoakland · 5 minutes ago

1|mnml.ink|1 comments

Is "AI vibe coding" making prototyping worse inside real companies?

by arapkuliev · 5 minutes ago

I keep hearing that prototyping is “solved” now — just use Cursor, Claude, Lovable, etc.

But when I talk to people inside real organizations (healthcare, regulated industries, even large non-tech companies), I keep seeing the opposite:

There’s no shortage of ideas. There’s a constant backlog of things people want to test — new workflows, internal tools, patient-facing flows, decision support UIs.

The bottleneck isn’t creativity. It’s: – internal IT teams focused on maintenance – engineers already overloaded – AI tools that still require time, context, and ownership – agencies/freelancers that are too slow or heavyweight for “just a prototype”

My hot take: AI didn’t eliminate the prototyping problem — it shifted it to the people who have the least time to deal with it.

Curious how this matches your experience: – Do you actually prototype continuously, or is it mostly one-off? – Have AI tools fully replaced the need for external help for you? – If you could get realistic prototypes in days (not months), how often would you use that?

Genuinely trying to understand whether I’m seeing a real pattern — or just a biased slice of the world.

1||0 comments

Wine 11.0 Released

by midzer · 5 minutes ago

1|www.winehq.org|0 comments

Scott Adams Dead: Dilbert Creator Was 68

by ohjeez · 5 minutes ago

1|variety.com|0 comments

Dilbert creator Scott Adams dies at 68

by dctoedt · 6 minutes ago

2|www.nytimes.com|0 comments

The Passwords I Memorise

by 7777777phil · 7 minutes ago

1|alexwlchan.net|0 comments

Community over Code EU 2026 Announced for Glasgow, Scotland

by meonkeys · 8 minutes ago

1|news.apache.org|0 comments

A protein found in the GI tract can neutralize many bacteria

by chmaynard · 8 minutes ago

1|news.mit.edu|0 comments

Why MCP-based ChatGPT Apps fail in practice (and a minimal working starter)

by shuddha7435 · 8 minutes ago

1|github.com|1 comments

Streets are making it easy (or hard) to make friends

by speckx · 9 minutes ago

1|weshouldgettogether.com|0 comments

Typeclasses Prototype Java

by joe_mwangi · 9 minutes ago

1|mail.openjdk.org|0 comments

Minions of the Fuhrer

by jjgreen · 9 minutes ago

1|cinemasojourns.com|0 comments

End-to-End Encrypted RCS Messages Referenced in Latest iOS 26.3 Beta

by throw0101d · 10 minutes ago

1|www.macrumors.com|0 comments

GameAgora – multiplayer gaming platform for public spaces

by zenin · 11 minutes ago

1|www.gameagora.com|1 comments

Show HN: Memovee – An agentic movie database

by zacksiri · 11 minutes ago

Hi HN

Memovee is an agentic movie database that lets you explore movies using natural language instead of filters or rigid queries.

You can ask things like:

- “Movies that take place in someone’s mind”

- “Top mystery films on Netflix released in the last 5 years”

- “Slow-burn sci-fi movies with strong world-building”

Under the hood, this isn’t just an LLM wrapper. Memovee uses a structured movie database and an agent layer that translates natural-language intent into deterministic queries and aggregations, then reflects on the results before responding.

The agent implementation used by Memovee is open source: https://github.com/upmaru/memovee-tama

This repository shows how intent parsing, query planning, execution, and result refinement are handled step-by-step, rather than relying on opaque prompt chains.

The core engine itself is not open-sourced yet. Memovee is one concrete application built on top of a more general engine whose goal is to make it possible to build systems like this for any enterprise domain — not just movies.

Engine project: https://kritama.com

This is still early and focused purely on movies (not TV yet). Coverage and regional availability vary, and there’s a lot left to improve — especially around reasoning depth, evals, and edge cases.

Happy to answer questions about:

- The agent architecture

- How natural-language intent is mapped to structured data

- Agentic vs deterministic tradeoffs

- The path toward a reusable enterprise engine

Looking forward to feedback — especially critical ones.

1|memovee.com|0 comments

Show HN: Verdic Guard – Deterministic guardrails to prevent LLM hallucinations

by kundan_s__r · 13 minutes ago

1|www.verdic.dev|0 comments

Building iOS UI with Coding Agents Is Slow

by chw9e · 13 minutes ago

1|qckfx.com|0 comments