Hacker News Reader

no_no_no_yeson Ask HN: What are you reading?

> - The Name of The Rose, Umberto Ecori

I think I've tried to read this twice, either this or Foucalt's Pendulum, either way I gave up early, Umberto Eco is difficult to read. Does it pick up and get easier?

no_no_no_yeson AI-generated posters don’t have to be horrible

> I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models.

That makes sense given they're on Fiverr. However, Fiverr freelancers are now just AI prompters :) doesn't matter whether it's code or art.

no_no_no_yeson Claude Cowork and chat are now one Claude

This is my main reason for not using Work. I was tempted to use a few "scheduled tasks" in ChatGPT, but once I found out they used Codex tokens I stopped creating new ones.

I already burn through Codex too fast.

no_no_no_yeson ElevenLabs, TwelveLabs, ThirteenLabs

Wow, haha I just created an LLC that is a "<number> Labs" company. I don't plan on raising VC or anything public with it, it's just a name to release apps on the app store under.

I was trying to come up with a name and it was exhausting, everything was taken, I was trying "clever names", eventually after strategizing with ChatGPT it gave me the suggestion along the lines of:

"Many people just use their initials, birthdate, or area code, plus the word 'software', 'tech', or 'labs'"

And I went ahead with that and called it a day!

no_no_no_yeson Claude Code May–August 2026 weekly limits promotion

I'm seeing a lot of that too.

I was working on a project recently that required the attribution of a data source, and it added to the "licenses" page of the project something like "We use <blah> and per their terms we owe an acknowledgement of attribution to you, the user."

So in addition to the stuff it says in a session there's gobbledy gook that it prints out in copy as well.

no_no_no_yeson Degraded performance for multiple models

I completely forgot about this, I'm already budgeting usage until my reset haha

no_no_no_yeson GPT-5.6 Sol Pricing Cut by 50%

Yes it can, it's called "output style" under `/config`:

```

This changes how Claude Code communicates with you

  1. Default     Claude completes coding tasks efficiently and provides concise responses

  2. Proactive    Claude executes immediately, minimizes interruptions, and prefers action over planning

  3. Explanatory  Claude explains its implementation choices and codebase patterns

  4. Learning     Claude pauses and asks you to write small pieces of code for hands-on practice

```

You can set up a custom one under `vi ~/.claude/output-styles/eli5.md` and `eli5` would show up in the list above:

```

---

name: ELI5

description: keep it simple please

keep-coding-instructions: true

---

I can't process lengthy text, talk to me like I'm 5.

Small words, short sentences, short paragraphs. If you have to use a big word, explain it right after. Only return what's actually necessary. Just tell me what you did, did it work, what do I do now.

If I have to decide something: show 3 options max, the context I need to pick fast, and which one you'd go with.

Keep paths and commands exact. I have no brain cells left for the rest.

```

I'm not sure if it's a good thing that there's a config option for this, it kinda means they know there's issues with verbosity.

no_no_no_yeson Choosing an AI model: one prompt, 11 models, different results

It's impossible to NOT get the beige/orange/cream/paper combo.

You basically have to explicitly say not to use those colors/themes.

no_no_no_yeson OpenAI reduces Codex Model Context Size from 372k to 272k

Claude does the same?

It asks you to create new chats (Claude Design) and Claude Code nudges you to start over too, I think `/compact` is optional though?

no_no_no_yeson Codex Resets

Why does Fable usage end today?!

Anthropic won't have anything competitive with OpenAI Sol and Kimi K3?

no_no_no_yeson Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

In general I just don't like not using a cross platform architecture of some kind.

MLX is fine, but the cross platform alternatives (ONNX) are terrible, GGUF often lacks and doesn't have the "easy convert" that some of the commenters below say MLX has.

no_no_no_yeson Amazon without the knockoffs

> Knockoff filters the trademark-squat pseudo-brands (the SZHLUXes and HORUSDYs)

I see "HORUSDY" type brand names all the time. It's crazy that any shirt/pants/etc results in one of these.

no_no_no_yeson The Great Blogging Collapse: What Happened to 100 Successful Blogs?

Wow following the Digg playbook

no_no_no_yeson Ask HN: What are you working on? (June 2026)

> I've also been working on an open source protocol / reference implementation for user-owned AI memory

I've thought about how to fix this too. I'm "locked in" to OpenAI because of what it knows about me. Literally it's told me things like "blah blah but you shouldn't do that because you take X medication which has Y in it" and I'm like "...really? can you reference that?" and it gives me some old thread where I chatted about it and unbeknownst to me I completely forgot.

In other words it's legit helpful as my "second brain", but I also don't like that I'm locked in and can't bring all this shared memory/context over.

no_no_no_yeson The desperation of NYTimes

It's 3 days through mine.

What's your library's page?

I have a few library cards so I'm curious as to which ones have better or worse terms.

no_no_no_yeson The desperation of NYTimes

You can subscribe with your library card and get access to all NYTimes (games/crosswords too).

One caveat is the subscription "rental" is for only a 3 day period, so you have "renew" your subscription every 3 days. This only takes 2 clicks though. For San Francisco public library: https://ezproxy.sfpl.org/login/nyt.

no_no_no_yeson Is "colorectal cancer" rising in "young people"?

yes I've had both a colonoscopy and a sigmoidoscopy (less invasive colonoscopy).

I'm not sure what the botches are here. In the sigmoidoscopy they took out a couple of polyps, in the colonoscopy (more recently than the sigmoidoscopy) they just did a cancer check-up given family history.

I wish those articles discusses the "botches", I'd like to know since from my understanding these are pretty safe procedures

no_no_no_yeson Singapore introduces caning for boys who bully others at school

Point taken on the power being abused point.

But to the first point, it seems like Singapore has a strong reputation for being low in crime while high in severity of punishment.

William Gibson's "Disneyland with the Death Penalty" and all that.

no_no_no_yeson Today I've made the difficult decision to reduce the size of Coinbase by ~14%

It's amazing how the crypto-bro influencers became AI-bro influencers over the past 2 years.

no_no_no_yeson Anthropic's Champion Kit for engineers pushing Claude Code at their company

> Share what you discover

Hate this

My current company (and other companies from speaking to colleagues) are all requiring employees to do some AI "lunch and learn" or AI "share out" or AI "show and tell".

It's meeting inflation, a weekly meeting where each employee has to add an item to a doc and talk about it. And every employee has to take part, even if they have nothing.

So half the employees just come up with some BS: "Uhhh I tried this Claude Code skill I hadn't tried before...", "Read this article about X...interesting, may be what's coming in the future..."