Hacker News: asdev

New comment by asdev in "Cloudflare OS: an open platform for agents, apps, and work"

asdev — Wed, 05 Aug 2026 14:52:29 +0000

Everyone is building these same looking apps that look like Codex, Claude desktop. We don't need these. Slackbots work more than well enough to collaborate with agents.

New comment by asdev in "Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents"

asdev — Mon, 03 Aug 2026 20:05:00 +0000

Building from ground up using OpenAI Agents SDK. We already have custom in house Cloud Development Environment, so the effort is just to "agent-ize" though which is not small. That's why I feel any team with any sort of infra support likely won't buy your product, since they already have the tribal knowledge to set this up. Newer teams might. But overall porting people's dev envs into the cloud is a tarpit problem(IMO), I was interested in this space too but decided against it for that reason. Happy to be proven wrong though!

New comment by asdev in "Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents"

asdev — Mon, 03 Aug 2026 19:52:07 +0000

just a data point, at my company we are building this internally. if you're targeting people building from scratch it might work, but there's no way you can port any somewhat mature infra stack, nor will the org want to. you'll need to deal with the variable complexity of everyone's dev environment which already doesn't work locally for thousands of different reasons.

New comment by asdev in "Jack Dorsey launches Buzz to combine team chat, AI agents and Git hosting"

asdev — Tue, 21 Jul 2026 18:42:41 +0000

No one is going to churn Slack for this just because it is "Agent First". Slack is more than good enough to tag Agents and will fill in the missing pieces slowly

New comment by asdev in "[dead]"

asdev — Mon, 20 Jul 2026 17:13:13 +0000

This is an ad FYI

New comment by asdev in "Launch HN: Context.dev (YC S26) – API to get structured data from any website"

asdev — Thu, 09 Jul 2026 15:49:24 +0000

So basically web scraping as a service with an API on top?

New comment by asdev in "Show HN: Smart model routing directly in Claude, Codex and Cursor"

asdev — Fri, 26 Jun 2026 23:13:01 +0000

They'll route traffic to Haiku or one of their cheaper models, not third parties. Overall cost will end up being cheaper than whatever you are doing

New comment by asdev in "Show HN: Smart model routing directly in Claude, Codex and Cursor"

asdev — Fri, 26 Jun 2026 20:00:44 +0000

Large model companies will likely build this and make it better. It'll also be cheaper overall since they'll be subsidizing token cost if you use them directly vs third party router paying API costs

New comment by asdev in "Ask HN: Is anyone using the A2A protocol?"

asdev — Thu, 18 Jun 2026 20:48:51 +0000

Seems like over engineering just build an API in front of your agent, give the other agent the spec in a markdown file.

New comment by asdev in "SPECS Augmented Reality Glasses"

asdev — Tue, 16 Jun 2026 17:47:42 +0000

>Every important computing platform has been defined by what people built with it. The PC became meaningful because developers built software. The web became meaningful because developers built websites. Smartphones became meaningful because developers built apps. We believe augmented reality will be no different.

At a $2195 price point, it just won't be possible to have an ecosystem. All the other platforms mentioned were orders of magnitude cheaper. That being said, I do think AR has real utility, but the price discovery will take a while

New comment by asdev in "Launch HN: Intuned (YC S22) – Build and run reliable browser automations as code"

asdev — Mon, 08 Jun 2026 14:31:53 +0000

Is this a bet that Computer Use models don't get better and cheaper?

New comment by asdev in "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"

asdev — Thu, 04 Jun 2026 18:09:05 +0000

how can I short the we won't read code anymore bet?

New comment by asdev in "Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)"

asdev — Wed, 03 Jun 2026 22:11:14 +0000

I haven't seen one unique product in AI, everyone is building the same thing

New comment by asdev in "Launch HN: Hyper (YC P26) – Company brain to power agentic development"

asdev — Wed, 03 Jun 2026 22:08:12 +0000

aren't the edge cases not generalizable and specific to the business? It doesn't seem like a one size fits all solution would work

New comment by asdev in "Launch HN: Rudus (YC P26) – AI for concrete contractors"

asdev — Tue, 02 Jun 2026 22:23:32 +0000

Those were consumer apps, not B2B. No deep niche experience needed, Uber had to fight regulations but wasn't something industry knowledge would've helped with a ton

New comment by asdev in "Launch HN: Rudus (YC P26) – AI for concrete contractors"

asdev — Tue, 02 Jun 2026 20:56:54 +0000

I wonder if this approach to starting a vertical business the founders have 0 experience in has ever panned out. I know YC pushes the B2B SaaS angle as hard as possible, searching for "underserved" niches, but seems like if you don't have true industry experience, it can't possibly work out.

New comment by asdev in "Ask HN: Entrepreneurs, how long did it take you to succeed?"

asdev — Fri, 29 May 2026 00:28:58 +0000

where did you get your ideas from then? did you have domain knowledge already? can DM you if you want

New comment by asdev in "Ask HN: Entrepreneurs, how long did it take you to succeed?"

asdev — Thu, 28 May 2026 22:06:40 +0000

what a cool business. were you in the music world before starting this?

New comment by asdev in "Ask HN: Entrepreneurs, how long did it take you to succeed?"

asdev — Thu, 28 May 2026 22:03:34 +0000

Why didn't you found yourself at any point? I understand gaining experience as a founding engineer, but after a certain point, you need to work as hard as the technical founder, take the same career risk, for way less payout

New comment by asdev in "Ask HN: Entrepreneurs, how long did it take you to succeed?"

asdev — Thu, 28 May 2026 22:02:04 +0000

I would define that as success. My definition is the feeling of success in the eyes of the founders, not millions of dollars or whatever hyped up benchmark