Hacker News: 8cvor6j844qw_d6

New comment by 8cvor6j844qw_d6 in "Why does Opus 5 feel worse to work with?"

8cvor6j844qw_d6 — Fri, 14 Aug 2026 11:24:19 +0000

It's bad enough that I've seen dedicated skills to do comment hygiene scrubbing and consolidation.

New comment by 8cvor6j844qw_d6 in "Advancing the price-performance frontier with GPT‑5.6"

8cvor6j844qw_d6 — Thu, 30 Jul 2026 18:52:50 +0000

I'd like to imagine the things that can be done with this speed and the current frontier models.

New comment by 8cvor6j844qw_d6 in "We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447"

8cvor6j844qw_d6 — Thu, 30 Jul 2026 18:44:29 +0000

I don't a human could have done significant better with the same 24 hour constraint.

New comment by 8cvor6j844qw_d6 in "Show HN: Sx 2.0 – Share AI skills with your team through a Dropbox folder"

8cvor6j844qw_d6 — Tue, 14 Jul 2026 05:13:54 +0000

Same thoughts. Get a team github repository and add the marketplace.

New comment by 8cvor6j844qw_d6 in "Claude Code May–July 2026 weekly limits promotion"

8cvor6j844qw_d6 — Mon, 13 Jul 2026 02:05:02 +0000

I recently swapped to Codex and its pretty great after a day or so of migrating configs and wrangling Codex's bubblewrap and finetuning the auto mode classifier prompt.

Claude is now mostly demoted to Claude Design.

I liked the fact that ChatGPT web chat usage is separate from Codex usage.

New comment by 8cvor6j844qw_d6 in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

8cvor6j844qw_d6 — Mon, 13 Jul 2026 00:47:03 +0000

I like Codex for allowing auto_review.policy (basically a prompt to the classifier on what to allow/disallow) to be configured rather than the opaque auto mode in Claude.

New comment by 8cvor6j844qw_d6 in "FCC approves test of space mirror to light night sky"

8cvor6j844qw_d6 — Sat, 11 Jul 2026 14:06:52 +0000

> relatively easy to redesign as weapons

There is a fiction I've read years ago that mentioned satellites becoming makeshift weapons by overheating exposed objects (think reactors, gas trucks, oil refineries) by acting as a solar furnace [1] via mirrors.

Not sure/don't recall how it deals with practical issues such as clouds and distance/intensity, but good enough for a story I guess.

[1]: https://en.wikipedia.org/wiki/Solar_furnace

New comment by 8cvor6j844qw_d6 in "Companies are scrambling to curtail soaring AI costs"

8cvor6j844qw_d6 — Sat, 11 Jul 2026 08:45:27 +0000

For those that recently switched from Claude, does Codex gives you more usage than Claude Code on the highest personal plan?

I frequently max out my weekly usage, and given this [1], hopefully Codex might give me more milage.

[1]: https://news.ycombinator.com/item?id=48126429

New comment by 8cvor6j844qw_d6 in "A new way to reflect on how you use Claude"

8cvor6j844qw_d6 — Thu, 09 Jul 2026 16:02:19 +0000

> I found Opus's 4.8 memories largely lacking value.

Similar thoughts, I disabled memory for the web UI.

> I've been holding "retros" with the agent immediately after a session, and _those_ responses have been typically fantastic.

I used a skill instead to update a ai docs directory as needed.

In any case, I'm moving coding tasks to Codex, Claude will be demoted to frontend design only. I will not entertain the idea of API billing/extra usage or a 2nd Max account once the extra 50% Claude Code usage limits ends on 13 July [1].

[1]: https://news.ycombinator.com/item?id=48126429

New comment by 8cvor6j844qw_d6 in "We're extending access to Fable 5 on all paid plans through July 12"

8cvor6j844qw_d6 — Wed, 08 Jul 2026 12:21:36 +0000

> I really hope people cancel their subs once GPT 5.6 drops.

I'm planning to subscribe to OpenAI after exhausting weekly usage with Fable. Good timing with GPT new models and might as well take a look at Codex.

While skills can be copy pasted, I'm not sure if the hooks are transferable.

New comment by 8cvor6j844qw_d6 in "Microsoft Can Track Users via a Windows Device ID"

8cvor6j844qw_d6 — Tue, 07 Jul 2026 10:22:15 +0000

I was under the impression Windows is unreliable for these kind of activities as they are "leakish".

I imagine it's not too difficult to narrow down the potential suspects with how much data points you'd get from ISP, Windows telemetry, and whatever.

New comment by 8cvor6j844qw_d6 in "OfficeCLI: Office suite for AI agents to read and edit Microsoft Office files"

8cvor6j844qw_d6 — Tue, 07 Jul 2026 10:08:15 +0000

> so wasn’t sure what license to use as MIT didn’t feel right to me at the moment

You're onto the right track if you have plans for commercialisation.

Thanks for building this, I've tested it out and it's useful.

New comment by 8cvor6j844qw_d6 in "Shadcn/UI now defaults to Base UI instead of Radix"

8cvor6j844qw_d6 — Sun, 05 Jul 2026 07:00:21 +0000

What is the shadcn/ui equivalent for Angular?

PrimeNG had a licensing change recently and I'm looking at a suitable alternatives for a fresh project.

New comment by 8cvor6j844qw_d6 in "Better Models: Worse Tools"

8cvor6j844qw_d6 — Sun, 05 Jul 2026 04:37:31 +0000

May I know when should skills be used over hooks and vice versa?

New comment by 8cvor6j844qw_d6 in "Leaking YouTube creators' private videos"

8cvor6j844qw_d6 — Sun, 05 Jul 2026 01:41:27 +0000

> YouTube Studio's own suggested prompts automatically feed all comments ot the AI the moment they're clicked.

Glad to see human-written text.

New comment by 8cvor6j844qw_d6 in "Show HN: QUALITY.md – open format/specification, agent skill, and CLI"

8cvor6j844qw_d6 — Thu, 02 Jul 2026 17:37:19 +0000

QUALITY.md feels similar to CONSTITUTION.md

Looks like unless something better comes up, we'll be stuck with it for a while.

I find markdown useful for repo-specific conventions, especially skills.

New comment by 8cvor6j844qw_d6 in ".gitignore Isn't the only way to ignore files in Git"

8cvor6j844qw_d6 — Thu, 18 Jun 2026 18:14:27 +0000

I prefer gitignore since it survives dev container rebuilds.

I can set a creation script or volume to restore/persist configs if I must avoid gitignore. However, that's an extra script or devcontainer mounts config over a gitignore line.

New comment by 8cvor6j844qw_d6 in "I found 10k GitHub repositories distributing Trojan malware"

8cvor6j844qw_d6 — Thu, 18 Jun 2026 17:57:21 +0000

> Strong support for the strategy of not putting your TOTP/MFA in your password manager

Agreed, but I think using the same device to access your password manager and for dev is asking for trouble in the first place.

Password managers assumes a non-compromised device. I don't think there exist a password manager that is explicitly designed for a compromised/hostile device.

A password manager + built-in TOTP on a dedicated device is fine for most general usage. Important TOTPs can go to Yubikeys.

New comment by 8cvor6j844qw_d6 in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

8cvor6j844qw_d6 — Sat, 13 Jun 2026 03:27:34 +0000

Likely models by Anthopic can no longer be reliably trusted as it'll subtly sabotage your codebase you're working on.

Gov just need some national security orders for Anthopic not disclose it to the public and to implement whatever they've done to Fable 5 to existing models.

New comment by 8cvor6j844qw_d6 in "Anthropic apologizes for invisible Claude Fable guardrails"

8cvor6j844qw_d6 — Fri, 12 Jun 2026 00:48:14 +0000

Feels malicious that Anthropic can silently sabotage your codebase.

Refusing prompts I one thing, silently sabotaging is another.

I wonder if some sort of honeypot code can work?