Hacker News: nojito

New comment by nojito in "Codex pricing to align with API token usage, instead of per-message"

nojito — Sun, 05 Apr 2026 16:48:53 +0000

So many folks are just burning tokens just to burn them.

The infrastructure build out just can't keep up with it.

New comment by nojito in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

nojito — Sat, 04 Apr 2026 00:24:41 +0000

>Make a better product/alternative to Openclaw and start eating their userbase.

There's a good chance they do not have the infrastructure to do that.

New comment by nojito in "New York City hospitals drop Palantir as controversial AI firm expands in UK"

nojito — Thu, 26 Mar 2026 23:56:44 +0000

Not for org/enterprise licenses.

Attributed Claude activity over the last 90 days on GitHub

nojito — Wed, 25 Mar 2026 23:38:46 +0000

Article URL: https://www.claudescode.dev/?window=90d

Comments URL: https://news.ycombinator.com/item?id=47524812

Points: 5

# Comments: 0

New comment by nojito in "Chrome DevTools MCP"

nojito — Mon, 16 Mar 2026 02:32:19 +0000

I have dozens of clis that are custom built for codex to use.

New comment by nojito in "Let your Coding Agent debug the browser session with Chrome DevTools MCP"

nojito — Sun, 15 Mar 2026 21:39:57 +0000

all you need is a simple skills.md and maybe a couple examples and codex picks up my custom toolkit and uses it.

New comment by nojito in "Claude March 2026 usage promotion"

nojito — Sun, 15 Mar 2026 00:32:00 +0000

It's eerie how similar these trends are to early phone/text usage limits.

New comment by nojito in "Agents that run while I sleep"

nojito — Wed, 11 Mar 2026 01:45:26 +0000

I do do TDD but using skills in this way is an anti-pattern for a multitude of reasons.

New comment by nojito in "Agents that run while I sleep"

nojito — Wed, 11 Mar 2026 00:38:52 +0000

This is just ai slop. If you follow what the actual designers of Claude/GPT tell you it flys in the face of building out over engineered harnesses for agents.

OpenAI – Symphony

nojito — Fri, 06 Mar 2026 01:38:49 +0000

Article URL: https://github.com/openai/symphony

Comments URL: https://news.ycombinator.com/item?id=47269722

Points: 1

# Comments: 0

New comment by nojito in "Verified Spec-Driven Development (VSDD)"

nojito — Sun, 01 Mar 2026 03:07:48 +0000

>THe AI won't get the perfect system in one shot, far from it! And especially not from sloppy initial requirements that leave a lot of edge (or not-so-edge) cases unadressed. But if you have a good requirement to start with, you have a chance to correct the AI, keep it on track; you have something to go back to and ask other AI, "is this implementation conforming to the spec or did it miss things?"

This is an antiquated way of thinking. If you ramp up the number of agents you're using the auto-correcting and reviewing behavior kicks in which makes for much less human intervention until the final code review.

New comment by nojito in "Minions: Stripe’s one-shot, end-to-end coding agents"

nojito — Sun, 22 Feb 2026 17:21:13 +0000

>how do you expect to stay good at reviewing code if you never write it?

What exactly does "writing code" mean?

Are you telling me I have to write for loops and if elses forever?

New comment by nojito in "How I use Claude Code: Separation of planning and execution"

nojito — Sun, 22 Feb 2026 01:52:09 +0000

>I've never seen it develop something more than trivial correctly.

This is 100% incorrect, but the real issue is that the people who are using these llms for non-trivial work tend to be extremely secretive about it.

For example, I view my use of LLMs to be a competitive advantage and I will hold on to this for as long as possible.

Build an LLM from Scratch in Max

nojito — Sat, 21 Feb 2026 16:23:43 +0000

Article URL: https://llm.modular.com/

Comments URL: https://news.ycombinator.com/item?id=47102172

Points: 1

# Comments: 0

New comment by nojito in "Kimi Claw"

nojito — Sun, 15 Feb 2026 15:33:40 +0000

Building on OpenClaw is a mistake.

The real advantage is https://github.com/badlogic/pi-mono

New comment by nojito in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

nojito — Fri, 13 Feb 2026 00:22:05 +0000

Context.

Why would I use an MCP when I can use a cli tool that the model likely trained on how to use?

New comment by nojito in "We mourn our craft"

nojito — Sat, 07 Feb 2026 19:53:05 +0000

>You get to think through a problem and figure out why decision A is better than B. Learning about various domains and solving difficult problems is in itself a reward.

So just tell the LLM about what you're thinking about.

Why do you need to type out a for loop for the millionth time?

The logs I never read

nojito — Sat, 07 Feb 2026 19:31:21 +0000

Article URL: https://pydantic.dev/articles/the-logs-i-never-read

Comments URL: https://news.ycombinator.com/item?id=46926829

Points: 2

# Comments: 0

New comment by nojito in "Coding agents have replaced every framework I used"

nojito — Sat, 07 Feb 2026 16:38:37 +0000

>A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future.

Correct. Those who wave away coding agents and refuse to engrain them into their workflows are going to be left behind in the dust.

New comment by nojito in "What I learned building an opinionated and minimal coding agent"

nojito — Sun, 01 Feb 2026 19:08:11 +0000

Most likely.

See here OpenCode.

https://x.com/thdxr/status/2009742070471082006?s=20