Hacker News: nadis

Software Eng for Vibe Coders: Databases and Storage

nadis — Tue, 25 Aug 2026 19:11:32 +0000

Article URL: https://read.technically.dev/p/software-eng-for-vibe-coders-databases

Comments URL: https://news.ycombinator.com/item?id=49439084

Points: 4

# Comments: 0

New comment by nadis in "YC startups are abandoning .com"

nadis — Wed, 12 Aug 2026 15:10:16 +0000

Lest we forget, the PG essay: https://paulgraham.com/name.html

Free MIT Courses for When You're Craving Libraries, Lectures, and Big Ideas

nadis — Wed, 12 Aug 2026 15:07:02 +0000

Article URL: https://rakowwwski.substack.com/p/78-free-mit-courses-for-when-youre

Comments URL: https://news.ycombinator.com/item?id=49273568

Points: 6

# Comments: 0

New comment by nadis in "The Future Is for Everyone – The Path to a Positive AI Future"

nadis — Mon, 10 Aug 2026 13:50:29 +0000

> Invention, not automation, will be the greatest contribution of superintelligence. Early AI could answer questions and do routine work. Soon it will increasingly help discover new knowledge -- ranging from discovering new drugs to cure a family member's disease to finding new ways to improve your business. While the number of questions a person can ask in a day is limited, the number of valuable things superintelligence can invent to help achieve your goals is unlimited.

Sort of a half-baked tangent of a thought but is it really possible for an AI superintelligence to "invent"?

The possibilities are vibe coded

nadis — Fri, 07 Aug 2026 15:23:51 +0000

Article URL: https://mercury.com/blog/vibe-coding-startups-no-code

Comments URL: https://news.ycombinator.com/item?id=49211891

Points: 2

# Comments: 0

New comment by nadis in "How do we stop vibe coding?"

nadis — Fri, 31 Jul 2026 15:25:00 +0000

I'd agree with you then! I don't think that case was clearly laid out (or at least I didn't understand your argument to be as such). I'd also say that humans are historically quite bad at communicating intent (even if it comes more naturally and is communicated in natural-language), so I think tools that support human <> agent interaction and iteration are important.

New comment by nadis in "Bringing MCP 2026-07-28 to Claude"

nadis — Wed, 29 Jul 2026 16:11:13 +0000

> "Claude now lists over 950 MCP servers in the connectors directory, used by millions of people every day. This year we shipped support for new protocol extensions alongside features that make MCP easier to build on and deploy"

Where are all these MCP servers? I feel like if I explore the directory, I see the same subset over and over.

Separately, would love to see more love from Anthropic for MCPB. I think this is an exciting and underutilized variation and have been enjoying building MCPB servers.

New comment by nadis in "How Do We Stop Vibe Coding?"

nadis — Fri, 24 Jul 2026 13:45:56 +0000

This piece is more thoughtful than the title initially led me to believe. However, I feel like it's sort of like advocating for us all being able to read/write binary (using a bit of an extreme to prove a point). While there might certainly be benefits to understanding less abstract layers, I don't think it's necessary or even necessarily helpful. That said, I don't think the answer is "turn your brain off completely" but I think that there should be tools that facilitate thoughtful ways of vibe coding with natural language, which is basically another abstraction layer from writing the code and tests yourself.

Harvard's Dean Deming: AI Will Beat You at Everything. You'll Still Have a Job [video]

nadis — Thu, 23 Jul 2026 15:28:09 +0000

Article URL: https://www.youtube.com/watch?v=OWaq1rI4D6w

Comments URL: https://news.ycombinator.com/item?id=49023157

Points: 1

# Comments: 0

The AI Wrapper Is Dead: 3 Approaches to Verticalization for Early-Stage Startups

nadis — Thu, 09 Jul 2026 21:11:41 +0000

Article URL: https://www.nfx.com/post/ai-wrapper-dead-verticalization-startups

Comments URL: https://news.ycombinator.com/item?id=48852435

Points: 3

# Comments: 0

Trusting Your Agent Is Overrated

nadis — Wed, 24 Jun 2026 18:59:12 +0000

Article URL: https://blog.southparkcommons.com/p/trusting-your-agent-is-overrated

Comments URL: https://news.ycombinator.com/item?id=48664266

Points: 3

# Comments: 0

New comment by nadis in "The World-Building Doors Are Open, Again"

nadis — Tue, 23 Jun 2026 20:51:18 +0000

> "The models are finally ready. Costs of inference are getting optimized with open models, and even on-device models. And, when I first experienced OpenClaw earlier this year, I had the epiphany that it isn’t the models that matter, but the harnesses, loops, and context which will lead to so many new opportunities ahead. Just as we’re learning in enterprise, we can finally invent new products that allow users to do things more naturally, using simple language to express their needs."

This part resonated a lot, personally.

What If Creativity Was the Constraint?

nadis — Tue, 23 Jun 2026 18:55:26 +0000

Article URL: https://blog.nseldeib.com/p/what-if-creativity-was-the-constraint

Comments URL: https://news.ycombinator.com/item?id=48649660

Points: 2

# Comments: 0

Building apps using TanStack Start

nadis — Tue, 23 Jun 2026 17:06:58 +0000

Article URL: https://lovable.dev/blog/building-apps-using-tanstack-start

Comments URL: https://news.ycombinator.com/item?id=48648008

Points: 15

# Comments: 0

South Park Commons Requests for Curiosity Summer 2026

nadis — Wed, 17 Jun 2026 19:32:26 +0000

Article URL: https://blog.southparkcommons.com/p/requests-for-curiosity-summer-2026

Comments URL: https://news.ycombinator.com/item?id=48575603

Points: 1

# Comments: 0

New comment by nadis in "AI should earn its keep: Introducing the AI Productivity Guarantee"

nadis — Fri, 05 Jun 2026 01:51:29 +0000

Seems like a wild move from the Devin team. Very curious about the metrics going into their "estimator" and also that they compared it to human estimates as a measure of success.

AI should earn its keep: Introducing the AI Productivity Guarantee

nadis — Fri, 05 Jun 2026 01:51:29 +0000

Article URL: https://cognition.ai/blog/ai-guarantee

Comments URL: https://news.ycombinator.com/item?id=48407036

Points: 4

# Comments: 1

New comment by nadis in "We tore down our no-code site and went back to code"

nadis — Wed, 03 Jun 2026 17:48:54 +0000

This is a bit of a tangent but can you explain the Western gaming studios analogy a bit further? It's not something I'm familiar with but am curious (I get the idea and broad parallel, but actually would love to better understand the details).

New comment by nadis in "We tore down our no-code site and went back to code"

nadis — Wed, 03 Jun 2026 17:48:01 +0000

I wondered about this as well, but could also imagine AI tools (perhaps at the application layer and not root-LLM layer) helping to mitigate this - that's a world I've been exploring.

Don't think we're there yet, but it feels like there's a future dream of everyone being able to build and maintain custom software with AI, and not having to make the tradeoff of creativity vs. components that's historically been true with low/no code.

That said, where we are today, completely agree with what you're saying. LLMs like to generate code, and in my experience are pretty bad at iterating on or maintaining the prolific code they've created.

We tore down our no-code site and went back to code

nadis — Tue, 02 Jun 2026 22:31:53 +0000

Article URL: https://twitter.com/chrismuccioli/status/2061909833893257389

Comments URL: https://news.ycombinator.com/item?id=48377230

Points: 7

# Comments: 4