Comments URL: https://news.ycombinator.com/item?id=47805680

Points: 3

# Comments: 0

We do have a AI assistant to help build on top of platform but the primary appeal of low code was don’t bother about code and care about the app which with agentic sw development may also be achieved.

Comments URL: https://news.ycombinator.com/item?id=47619720

Points: 10

# Comments: 9

why language would evolve ? Let’s say to make it easier and better ? And if such a case then wouldn’t that be applicable to all languages? If yes then I am a native kutchi speaker and it just a dialect. How would its history of change could even be found? But I do speak other languages like Gujarati and Hindi and I wonder if there was any evolution if those languages which have a

Comments URL: https://news.ycombinator.com/item?id=47013256

Points: 10

# Comments: 11

My config: There are three agents working in silos.

1) comet ( I will mostly replace this with clawdebot) to work on Sending Friend request on LinkedIn and push the prospects in a Google sheet 2) Dronahq agent (disclaimer: this is the platform I am building and dog fooding for this use case) : Here the agent will - pick the lead from Google sheet and look up Apollo and find more details - shoot an intro email basis a complex algo

3) voice agent ( made with twilio and vapi): this will call the customer and update the records and set up Google Calendar for appointment. I must mention that setting up voice agent with vapi was incredible experience. I was able to set up a working one in under 10 mins.

Next steps: 1) glue all the three agents via some super agent so they can work seamlessly and autonomously 2) bring in a cadence agent so outreach cadence will be achieved by the agent

Comments URL: https://news.ycombinator.com/item?id=46832088

Points: 1

# Comments: 0

However underlying principles haven’t changed.

-Engineering bandwidth is minimally available for Internal tools. -Enterprise controls/guardrails are important needs - bringing in data to your app is a must have - maintaining code vs low code apps — low code has been a lot easier

In a conversation with a CTO at VC fund - he predicts that 4-6 quarters and you shall see demand back to peak in low code segment!

In a customer conversation— customer made one tool with cursor and he was very successful but by the time he started adding features for 2.0 everything started breaking and he wanted to move back to lowcode.

As a low code vendor- we just added internal tool building agent that underneath writes react code and leverages the other core capability of the platform thereby giving users best of both the worlds.

But surely interesting times ahead for the category. Let’s see if it survives or dies!

My personal take— it will survive and converge with agentic ai!

Comments URL: https://news.ycombinator.com/item?id=46518965

Points: 3

# Comments: 0

My picks: 1. How did life originate from non-life? 2. What truly exists at the center of the Earth? 3. What (if anything) is the next evolutionary step beyond humans?

What would you ask, and what made you choose those three?

Comments URL: https://news.ycombinator.com/item?id=46502061

Points: 4

# Comments: 5

Sub-1500 Elo players may actually be doing more real-time thinking during a game compared to Grandmaster-level players.

At elite levels, many positions are instantly recognized. Years of pattern recognition, theory, and experience allow GMs to play large portions of a game almost automatically. Their brilliance lies in what they’ve internalized.

For sub-1500 players, however, most positions are unfamiliar. There’s less reliance on memorized structures and far more active calculation, questioning, and exploration: • What is my opponent threatening? • Is this move safe? • What happens if I try something different?

This isn’t to say sub-1500 players play better chess—clearly they don’t. But they may be engaging in a more conscious, effortful thinking process move by move.

It makes me wonder: • Is chess mastery about thinking more—or thinking less, but better? • At what point does intuition replace deliberate reasoning?

Would love to hear thoughts from players, coaches, and fellow chess enthusiasts.

Comments URL: https://news.ycombinator.com/item?id=46408729

Points: 2

# Comments: 2

Given how I have seen different patients and varying pace of dementia growth - I somehow think Alzheimer’s must have multiple sub families & may appear same but must be behaving differently from their onset.

I know this isn’t the usual kind of letter you get, but it felt like a good moment to pause and reflect.

Ever since AI entered the app development space in full swing, things have changed quickly. I’ve watched customers’ PMs prototype in tools like Lovable or Replit, then hand things off to engineers using Cursor to build internal apps. It mostly works. There are loose ends, but people seem happy.

The flip side is that not all new internal apps are being built on my low-code platform anymore.

So over the past three months, my team and I have been building two things on DronaHQ.

First, a vibe-code tool for internal software. It takes a different approach from Cursor, Replit, or Retool—focused on letting teams build production-ready internal apps quickly, without losing structure or clarity.

Second, an AI agent builder—an orchestrator that makes it possible to build RAG, chat, voice, and autonomous agents without writing code.

The important part is that these tools interoperate. You can move between them easily and build real systems, not disconnected demos.

What I’m wishing for isn’t hype or virality. I’m hoping for posts that reach the right people—the ones who read carefully, try things out, and decide whether it actually solves a problem they have.

Specifically: • A Show HN that gets a fair look • Comments that challenge the ideas, not the intent • Traffic driven by curiosity, not outrage • A few users who stick around and push the product forward

I’ll do my part: clear docs, honest positioning, and steady shipping.

If a bit of good timing or luck helps along the way, I’ll take it.

Thanks for rooting for builders, even the ones shipping close to the holidays.

— A builder

Comments URL: https://news.ycombinator.com/item?id=46383491

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46381896

Points: 15

# Comments: 4

The idea is a fully serverless service where you can: • Bring in data from REST, GraphQL, gRPC, Databricks, Snowflake, MongoDB, MySQL, etc. • Write (or vibe) lightweight JavaScript scripts • Quickly build internal APIs or orchestrate existing APIs

No infra to manage, no services to deploy—just connect sources and ship.

Core use cases: 1. Building internal APIs on top of existing data sources 2. API orchestration (fan-out, stitching, transformations)

Current status: • Pre-beta • Focused on speed and minimal code • Private beta access available in ~2 weeks

I’d love feedback on: • Would you actually use something like this? • What would be a deal-breaker? • Who do you think this is most useful for?

Not selling—just validating whether this solves a real problem.

Comments URL: https://news.ycombinator.com/item?id=46334596

Points: 1

# Comments: 0