HackerTrans
TopNewTrendsCommentsPastAskShowJobs

d0100

no profile record

comments

d0100
·bulan lalu·discuss
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
d0100
·2 bulan yang lalu·discuss
> 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
d0100
·2 bulan yang lalu·discuss
> Python is, thus, clearly superior to other languages in terms of ease of review.

Do we get visual comparisons along with this bold claim?
d0100
·2 bulan yang lalu·discuss
I remember doing a MailChimp "clone" in Laravel some 12 years ago and implementing an email builder using their templates
d0100
·2 bulan yang lalu·discuss
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)
d0100
·2 bulan yang lalu·discuss
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
d0100
·2 bulan yang lalu·discuss
Tried using Zed but for some reason the AI can't open the browser?
d0100
·2 bulan yang lalu·discuss
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
d0100
·3 bulan yang lalu·discuss
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
d0100
·3 bulan yang lalu·discuss
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
d0100
·3 bulan yang lalu·discuss
Any example more complex in the backend?

Are we supposed to expose all entities and relationships and rely on row level security?
d0100
·3 bulan yang lalu·discuss
AI assisted development is the generalists dream

Althought it still hasn't solved procrastinating the next plan prompt
d0100
·4 bulan yang lalu·discuss
> In a certain way, that's how Brazilian culture works

That's how Brazilian media conglomerate culture works
d0100
·4 bulan yang lalu·discuss
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/[email protected]" or "npm:[email protected]" and just running code without having to worry about scaffolding node_modules makes sandboxing code much easier
d0100
·4 bulan yang lalu·discuss
In pt-br it's "leito", "semi-leito", "executivo" and "convencional"

"Leito" sounds more premium than "cama", despite being both valid words for "bed"
d0100
·4 bulan yang lalu·discuss
Why is there no RTX 5060ti?
d0100
·4 bulan yang lalu·discuss
I wonder if joining layers from the "organs" of different models could further enhance the results
d0100
·4 bulan yang lalu·discuss
I've shaved off 30s of queries by transforming json columns into a string after the first CTE is done with it
d0100
·4 bulan yang lalu·discuss
If you apply Pareto to productivity, you can fire a lot of people and still manage
d0100
·5 bulan yang lalu·discuss
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