Hacker News Reader

8cvor6j844qw_d6on Stop Making TUIs

Bubble Tea [1] is my favorite for one-off throwaway stuff in terminal. Wish [2] to make it available over SSH.

[1] https://github.com/charmbracelet/bubbletea

[2] https://github.com/charmbracelet/wish

8cvor6j844qw_d6on The August 17 outage

> 5k PRs

Wow, is Bun the record holder for number of PRs?

I recall GitHub recommends to keep the number of PR to a certain level due things such as GitHub Actions slowing down.

8cvor6j844qw_d6on Vomit: Clean up Claude 5's token output with a separate LLM

A separate /clear and /code-comment-hygiene works much better than including instructions related to comment verbosity after carrying out a task.

Claude somehow is unable to stop writing excessive comments when carrying out a task.

8cvor6j844qw_d6on The August 17 outage

"You can't seriously tell me that the unhappy leg of the code path has no test coverage."

Cloudflare outage on December 5, 2025 [1]:

> However, we have never before applied a killswitch to a rule with an action of “execute”.

[1]: https://blog.cloudflare.com/5-december-2025-outage/

8cvor6j844qw_d6on Anti-AI fonts are useless and harmful

Same thoughts. The black hole concerns are overstated for personal stuff when nothing is at stake. Planning to adopt one of the fonts and see how it goes.

8cvor6j844qw_d6on Feature Request: Support AGENTS.md

New guidelines that I have seen in a certain place is to configure and update existing CC setups to be CC/Codex agnostic. Plus setting up both allows Claude Code to delegate tasks [1] to Codex to reduce usage.

Most are easy to share with symlinks and @agents.

https://github.com/openai/codex-plugin-cc

8cvor6j844qw_d6on Why does Opus 5 feel worse to work with?

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

8cvor6j844qw_d6on Advancing the price-performance frontier with GPT‑5.6

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

8cvor6j844qw_d6on We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447

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

8cvor6j844qw_d6on Show HN: Sx 2.0 – Share AI skills with your team through a Dropbox folder

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

8cvor6j844qw_d6on Claude Code May–July 2026 weekly limits promotion

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.

8cvor6j844qw_d6on Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

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.

8cvor6j844qw_d6on FCC approves test of space mirror to light night sky

> 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

8cvor6j844qw_d6on Companies are scrambling to curtail soaring AI costs

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

8cvor6j844qw_d6on A new way to reflect on how you use Claude

> 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

8cvor6j844qw_d6on We're extending access to Fable 5 on all paid plans through July 12

> 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.

8cvor6j844qw_d6on Microsoft Can Track Users via a Windows Device ID

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.

8cvor6j844qw_d6on OfficeCLI: Office suite for AI agents to read and edit Microsoft Office files

> 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.

8cvor6j844qw_d6on Shadcn/UI now defaults to Base UI instead of Radix

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.

8cvor6j844qw_d6on Better Models: Worse Tools

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

8cvor6j844qw_d6on Leaking YouTube creators' private videos

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

Glad to see human-written text.

8cvor6j844qw_d6on Show HN: QUALITY.md – open format/specification, agent skill, and CLI

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.

8cvor6j844qw_d6on .gitignore Isn't the only way to ignore files in Git

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.

8cvor6j844qw_d6on I found 10k GitHub repositories distributing Trojan malware

> 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.

8cvor6j844qw_d6on Statement on US government directive to suspend access to Fable 5 and Mythos 5

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.

8cvor6j844qw_d6on Anthropic apologizes for invisible Claude Fable guardrails

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?

8cvor6j844qw_d6on Show HN: DomainTasker – avoid losing domains and surprise renewals

Porkbun early auto renew (45 days if I'm not mistaken) works better instead, and various domain name providers should have similar features.

8cvor6j844qw_d6on Bot vs human traffic

> One funny thing I've discovered as a result of certificate transparency logs is that the second your host gets given an SSL cert

I've been thinking of using wildcard certs for Caddy in regards to this.

8cvor6j844qw_d6on Age verification for social media, the beginning of the end for a free internet?

Just wishful thinking, but I hoped more will move to IRC and GPG emails.

8cvor6j844qw_d6on The newest Instagram “exploit” is the goofiest I've seen

Interesting article.

A few hours back, I was spammed with ig.me links insisting I click it to check it out.

I did not have the opportunity to visit the link, but it appears to be related to belong to some Instagram password reset flow.