Hacker News: d_watt

New comment by d_watt in "AI Added 'Basically Zero' to US Economic Growth Last Year, Goldman Sachs Says"

d_watt — Tue, 24 Feb 2026 00:07:10 +0000

It took 20 years for computers to "add" to the economy.

https://en.wikipedia.org/wiki/Productivity_paradox

New comment by d_watt in "AI is killing B2B SaaS"

d_watt — Wed, 04 Feb 2026 17:20:29 +0000

I think one of the interesting things here is that AI doesn't need to be able build B2B SaaS to kill it. So much of the overhead of B2B SaaS companies is thinking about multitenancy, intergrating with many auth providers and mapping those concepts to the program's user system, juggling 100 features when any given customer only needs 10 of them, creating PLG upsell flows to optimize conversions, instrumenting A/B tests etc...

A given company or enterprise does not have to vibe code all this, they just need to make the 10 features with the SLA they actually care about, directly driven off the systems they care about integrating with. And that new, tight, piece of software ends up being much more fit for purpose with full control of new features given to company deploying it. While this was always the case (buy vs build), AI changes the CapEx/OpEX for the build case.

New comment by d_watt in "Flux 2 Klein pure C inference"

d_watt — Sun, 18 Jan 2026 18:57:28 +0000

Regarding the meta experiment of using LLMs to transpile to a different language, how did you feel about the outcome / process, and would you do the same process again in the future?

I've had some moments recently for my own projects as I worked through some bottle necks where I took a whole section of a project and said "rewrite in rust" to Claude and had massive speedups with a 0 shot rewrite, most recently some video recovery programs, but I then had an output product I wouldn't feel comfortable vouching for outside of my homelab setup.

New comment by d_watt in "Git Rebase for the Terrified"

d_watt — Tue, 13 Jan 2026 15:08:15 +0000

Once we had a slowdown in our application that went unadressed for a couple of months. Using git bisect to binary search across a bunch of different commits and run a perf test, every commit being a "good" historical commit allowed that to be much easier, and I found the offending commit fast.

New comment by d_watt in "Apple releases open-source model that instantly turns 2D photos into 3D views"

d_watt — Sat, 27 Dec 2025 14:45:19 +0000

I’ve been using some time off to explore the space and related projects StereoCrafter and GeometryCrafter are fascinating. Applying this to video adds a temporal consistency angle that makes it way harder and compute intensive, but I’ve “spatialized” some old home videos from the Korean War and it works surprisingly well.

https://github.com/TencentARC/StereoCrafter https://github.com/TencentARC/GeometryCrafter

New comment by d_watt in "Advent of Code 2025"

d_watt — Sun, 30 Nov 2025 13:40:18 +0000

Looks like after the AI automation rush last year, the leaderboard has been removed. Makes sense, a little sad that it was needed though.

New comment by d_watt in "Using Devcontainers to Fix Coding Agent's Foibles"

d_watt — Thu, 21 Aug 2025 14:30:17 +0000

I've released a templatized local development setup using devcontainers that I've crafted over the last year, that I use on all projects now. This post explains the why and links to the project.

Using Devcontainers to Fix Coding Agent's Foibles

d_watt — Thu, 21 Aug 2025 14:30:17 +0000

Article URL: https://dylanwatt.com/posts/2025-08-20-template/

Comments URL: https://news.ycombinator.com/item?id=44973257

Points: 1

# Comments: 1

New comment by d_watt in "Vibe coding creates a bus factor of zero"

d_watt — Wed, 20 Aug 2025 23:06:18 +0000

It's potentially the opposite. If you instrument a codebase with documentation and configuration for AI agents to work well in it, then in a year, that agent will be able to do that same work just as well (or better with model progress) at adding new features.

This assumes your adding documentation, tests, instructions, and other scaffolding along the way, of course.

New comment by d_watt in "Building MCP servers for ChatGPT and API integrations"

d_watt — Thu, 24 Jul 2025 21:45:03 +0000

They're not directly solving the same problem. MCP is for exposing tools, such as reading files. a2a is for agents to talk to other agents to collaborate.

MCP servers can expose tools that are agents, but don't have to, and usually don't.

That being said, I can't say I've come across an actual implementation of a2a outside of press releases...

New comment by d_watt in "Facebook is asking to use Meta AI on photos you haven’t yet shared"

d_watt — Sat, 28 Jun 2025 02:43:11 +0000

Perhaps naive to say, but I think there was the briefest moment where your status updates started with "is", feeds were chronological, and photos and links weren't pushed over text, that it was not an adversarial actor to one's wellbeing.

New comment by d_watt in "Essentials for getting the most from Coding Agents"

d_watt — Fri, 13 Jun 2025 13:43:24 +0000

After converting many of my projects, and helping a couple startups tool their codebases and teams for using AI agents better, these 5 things are what I now do on every codebase I work on.

Essentials for getting the most from Coding Agents

d_watt — Fri, 13 Jun 2025 13:42:22 +0000

Article URL: https://dylanwatt.com/posts/2025-06-12-5-things/

Comments URL: https://news.ycombinator.com/item?id=44268443

Points: 1

# Comments: 1

New comment by d_watt in "My AI skeptic friends are all nuts"

d_watt — Tue, 03 Jun 2025 00:35:07 +0000

What do you think the "mistake" is here?

It seems like you're pointing out a consequence, not a counter argument.

New comment by d_watt in "Terraform MCP Server"

d_watt — Tue, 20 May 2025 00:52:06 +0000

I'd think this would work, as the 4 tools listed are about retrieving information to give agents more context of correct providers and modules. Given terragrunt works with terraform directly, I'd think that it would help with it as well, just add rules/prompts that are explicit about the code being generated being in terra grunt file structure / with terragrunt commands.

New comment by d_watt in "Claude Code SDK"

d_watt — Mon, 19 May 2025 21:46:43 +0000

Aider is definitely in the same camp. Last time I checked, they weren't optimizing for the full "agent infinitely looping until completion" usecase, and didn't have MCP support.

But it's 100% the same class of tool and the awesome part of the unixy model is hopefully agents can be substituted in for each other in your pipeline for whichever one is better for the usecase, just like models are interoperable.

New comment by d_watt in "Claude Code SDK"

d_watt — Mon, 19 May 2025 19:48:09 +0000

It totally is!

I bias a bit to wanting the agent to be a pluggable component into a flow I own, rather than a platform in a box.

It'll be interesting to see where the different value props/use cases of a Delvin/v0 vs a Codex Cloud vs Claude Code/Codex CLI vs Cursor land.

New comment by d_watt in "Claude Code SDK"

d_watt — Mon, 19 May 2025 18:49:52 +0000

I personally find figuring out what the product should be is the fun part. There still a need for architecting a plan, but the actual act of writing code isn't what gives me personal joy, it's the building of something new.

I understand the craft of code itself is what some people love though!

New comment by d_watt in "Claude Code SDK"

d_watt — Mon, 19 May 2025 18:44:52 +0000

Claude max plan has Claude code bundled into the price. $100/month isn't cheap, but the RoI is there for me personally.

New comment by d_watt in "Claude Code SDK"

d_watt — Mon, 19 May 2025 18:43:35 +0000

The way Claude Code is going is exactly what I want out of a agentic coding tool with this "unix toolish" philosophy. I've been using Claude code since the initial public preview release, and have seen the direction over time.

The "golden" end state of coding agents is that you give it a Feature Request (EG Jira ticket), and it gives you a PR to review and give feedback on. Cursor, windsurf, etc, are dead ends in that sense as they are local editors, and can not be in CI.

If you are tooling your codebase for optimal AI usage (Rules, MCP, etc), you should target a technology that can bridge the gap to headless usage. The fact Claude Code can trivially be used as part of automation through the tools means it's now the default way I thinking about coding agents (Codex, the npm package, is the same).

Disclaimer, I focus on helping companies tool their codebases for optimal agent usage, so I might have a bias here to easily configurable tools.