Hacker News: d0100

New comment by d0100 in "Ask HN: What is your (AI) dev tech stack / workflow?"

d0100 — Fri, 05 Jun 2026 19:38:24 +0000

My workflow for production code:

1. Pick the most complete project boilerplate (fullstack JS can easily introduce security bugs, SPA + API is best as cheap linting solves most problems)

2. Project skills (how to CRUD without mess)

3. Use worktrees for concurrent features, local session for conflicts

4. Local session for QA and refinement

I use Copilot and GPT 5.4

Managed to shorten pre-AI priced ongoing projects to 2 weeks or a month

New comment by d0100 in "AI is too expensive"

d0100 — Tue, 19 May 2026 16:33:05 +0000

> GPT 5.4 instead of 5.5.

I am exclusively using 5.4 because its only 1x and very good, but the github calculation showed my once $40 become a $680 billing

That is too expensive and not worth paying

New comment by d0100 in "If AI writes your code, why use Python?"

d0100 — Tue, 12 May 2026 15:21:09 +0000

> Python is, thus, clearly superior to other languages in terms of ease of review.

Do we get visual comparisons along with this bold claim?

New comment by d0100 in "Show HN: I built an open-source email builder, alternative to Beefree/Unlayer"

d0100 — Thu, 07 May 2026 01:31:43 +0000

I remember doing a MailChimp "clone" in Laravel some 12 years ago and implementing an email builder using their templates

New comment by d0100 in "Flue is a TypeScript framework for building the next generation of agents"

d0100 — Sun, 03 May 2026 00:30:23 +0000

I am using TS sandboxed in deno for all our agent code generated from a UI builder (inspired by OpenAI's own agent builder, and spits out the same code output)

New comment by d0100 in "Does Postgres Scale?"

d0100 — Fri, 01 May 2026 06:30:33 +0000

Are you using Temporal with distributed workers?

We have a simple worker setup and temporal is pretty easy to setup

Out only issue is really needing an intermediary data store for task result storage

We are using DBOS in new projects as it's even simpler and the downside (task log interface behind saas) is easily remedied with a copilot generated task viewer

New comment by d0100 in "Zed 1.0"

d0100 — Wed, 29 Apr 2026 17:09:37 +0000

Tried using Zed but for some reason the AI can't open the browser?

New comment by d0100 in "Who owns the code Claude Code wrote?"

d0100 — Wed, 29 Apr 2026 04:05:57 +0000

The trick is to constrain the LLM to program in a very defined coding style

If I make the LLM generate code that follows my own code architecture and style, that should be enough creative input

New comment by d0100 in "Measuring Claude 4.7's tokenizer costs"

d0100 — Fri, 17 Apr 2026 21:15:15 +0000

I went from plan with opus, implement with claude, to simply plan and implement with GPT 5.4

It's a very good model for a very good price

New comment by d0100 in "Claude.ai down"

d0100 — Mon, 13 Apr 2026 17:11:17 +0000

GPT 5.4 is working pretty well for me, both in Copilot and Codex vscode extensions

If you create a plan it follows it closely

New comment by d0100 in "Instant 1.0, a backend for AI-coded apps"

d0100 — Fri, 10 Apr 2026 02:29:34 +0000

Any example more complex in the backend?

Are we supposed to expose all entities and relationships and rely on row level security?

New comment by d0100 in "Code Is Cheap Now, and That Changes Everything"

d0100 — Thu, 09 Apr 2026 13:50:50 +0000

AI assisted development is the generalists dream

Althought it still hasn't solved procrastinating the next plan prompt

New comment by d0100 in "'The Secret Agent': Exploring a Vibrant, yet Violent Brazil (2025)"

d0100 — Wed, 18 Mar 2026 02:56:15 +0000

> In a certain way, that's how Brazilian culture works

That's how Brazilian media conglomerate culture works

New comment by d0100 in "Edge.js: Run Node apps inside a WebAssembly sandbox"

d0100 — Wed, 18 Mar 2026 02:46:00 +0000

I still prefer Deno because I don't need a separate npm install command, which makes running code that much easier

Being able to import from "https://my-vpn.com/mypackage@1.2.3" or "npm:package@1.2.3" and just running code without having to worry about scaffolding node_modules makes sandboxing code much easier

New comment by d0100 in "Bus travel from Lima to Rio de Janeiro"

d0100 — Mon, 16 Mar 2026 02:17:09 +0000

In pt-br it's "leito", "semi-leito", "executivo" and "convencional"

"Leito" sounds more premium than "cama", despite being both valid words for "bed"

New comment by d0100 in "Can I run AI locally?"

d0100 — Sat, 14 Mar 2026 01:40:17 +0000

Why is there no RTX 5060ti?

New comment by d0100 in "Show HN: How I Topped the HuggingFace Open LLM Leaderboard on Two Gaming GPUs"

d0100 — Tue, 10 Mar 2026 18:45:16 +0000

I wonder if joining layers from the "organs" of different models could further enhance the results

New comment by d0100 in "Better JIT for Postgres"

d0100 — Wed, 04 Mar 2026 19:08:28 +0000

I've shaved off 30s of queries by transforming json columns into a string after the first CTE is done with it

New comment by d0100 in "Layoffs at Block"

d0100 — Fri, 27 Feb 2026 00:57:24 +0000

If you apply Pareto to productivity, you can fire a lot of people and still manage

New comment by d0100 in "The Sideprocalypse"

d0100 — Mon, 16 Feb 2026 21:45:44 +0000

I haven't had much success using LLM's in Unity as there is a lot of work that goes into the editor and cannot be done via code, especially if you are using several different assets