"You got your cold brew, your Japanese iced coffee, your iced americano. Then there's your mazagran, that's coffee with lemon juice, real refreshing. Your espresso tonic. Your iced latte, iced cappuccino, iced macchiato. You got your iced mocha, your frappuccino, your Greek frappé. Vietnamese iced coffee with the condensed milk dripping down real slow. Affogato, that's espresso poured right over ice cream. That's... that's about it."

that smells of AI [1], and thus lazy writing. I'm all in for using AI to help you write, but if you don't put your voice to it then there's no reason to read it.

[1] https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing#...

But, work IS exciting now - not sure for how long - because AI allows me to work almost at the speed of thought.

Nothing more, nothing less. It's FUN to be able to _just_ think.

Growing up in Argentina, back in the day these were all dubbed. The version I watched on tv had a voice and personality of its own - Latin American "neutral" Spanish - and for the life of me I could never find that same version, only the Spain-dubbed one.

Comments URL: https://news.ycombinator.com/item?id=47910925

Points: 4

# Comments: 1

It doesn't seem to be burning much tokens (MAX x1)

But boy is it slow. Thinking mode [1] (Yeah, I know) takes MINUTES per turn.

This is SERIOUSLY costly, token wise or otherwise.

[1] My bad, but compared to 4.6 is a disaster.

Comments URL: https://news.ycombinator.com/item?id=47896678

Points: 2

# Comments: 0

I recently went on a deep dive about them with sonnet / opus.

I wanted to detect if a file or an analysis was the result of the last turn and act upon that.

From my experience, 2 things stand out by looking at the data above:

1. They have changed the schema for the hook reply [1] if this is real stop hook users (And may be users of other hooks) are in for a world of pain (if these schema changes propagate)

2. Opus is caring f*ck all about the response from the hook, and that's not good. Sonnet / Opus 4.6 are very self conscious about the hooks, what they mean and how they should _ act / react_ on them, and because of how complex the hook I set up is I've seen turns with 4 stop hooks looping around until Claude decides to stop the loop.

[1] My comment is in the context of claude code. I cannot make if the post is about that or an API call.

I'll definitely give this a spin.

The cost goes beyond the price tag. Books take up space, and that space compounds as you keep acquiring them. It's space you can't use for anything else, dedicated entirely to objects most people open once or twice and never touch again. And that cost doesn't stay abstract: at some point you're buying more bookshelves, upgrading to a larger one, or worst of all, dragging everything through a move. That last one hits harder the less stable your living situation is, and less stable living situations track pretty closely with lower salaries.

I'm talking about physical books specifically, since that's what the article seems to cover. Ebooks are a different matter.

That wasn't the full prompt, I trimmed it for clarity, but I agree with everything you said and that's how I actually use it.

I have a proxy logging everything sent to and from Claude in a structured way, which is precisely what let me do that compaction analysis in the first place.

When Claude goes off track, I don't tell it "you did something wrong". I ask it to analyze the tool outputs and the exchange so far and let it reconcile the discrepancy itself. That tends to work better than narrating the error to it.

The venting messages like that one are honestly for me, not for Claude. I know it's a tool. But it also behaves and communicates like a person, and that's a design choice that comes from Anthropic, not from me. What I've found is that writing something like that and then following it with proper instructions works fine in practice: Claude either ignores the venting or briefly acknowledges it and moves on. The actual output isn't affected. It's just how I process frustration without breaking the workflow.

The weird stuff is yesterday I asked it to test and report back on a 30+ commit branch for a PR and it did that flawlessly.

Today we are almost on non-speaking terms. I'm asking it to do some simple stuff and he's making incredible stupid mistakes:

    This is the third time that I have to ask you to remove the issue that was there for more than 20 hours. What is going on here?

  | # | Time     | Gap before | Session span | API calls |
  |---|----------|-----------|--------------|-----------|
  | 1 | 15:51:13 | 8s        | <1m          | 1         |
  | 2 | 15:54:35 | 48s       | 37m          | 51        |
  | 3 | 16:33:33 | 2s        | 19m          | 42        |
  | 4 | 16:53:44 | 1s        | 9m           | 30        |
  | 5 | 17:04:37 | 1s        | 17m          | 30        |
  # — sequential compaction event number, ordered by time.

  Time — timestamp of the first API call in the resumed session, i.e. when the new context (carrying the compaction summary) was first sent to the
  model.

  Gap before — time between the last API call of the prior session and the first call of this one. Includes any compaction processing time plus user
   think time between the two sessions.

  Session span — how long this compaction-resumed session ran, from its first API call to its last before the next compaction (or end of session).

  API calls — total number of API requests made during this resumed session. Each tool use, each reply, each intermediate step = one request.

https://status.claude.com/

But: I was logged off, can't login, and code returns 500

    API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server
     error"},"request_id":"req_STRING"}

Comments URL: https://news.ycombinator.com/item?id=47753627

Points: 6

# Comments: 1

BTW, the claude app kind supports this with the /remote-control command, and that was what made me move away from cmux (I still have to start the sessions there)

I tried to search for it, but even the 2 documents that superseded the one from around the time my daughter was at school at not available.

I mean, the site doesn't even have a valid secure certificate so...

In the site below (In Spanish) you can search for 10/2019 and a cursory translation of the document title will show that this is the proper document (For 2019 onwards, the replaced doc 04/2014 isn't available either)

https://koha.chubut.edu.ar/cgi-bin/koha/opac-search.pl?idx=k...

The resulting situation here was that she was constantly bullied into underperforming. Both cases are actually similar in that each individual has a personal incentive to underperform - the difference is that in your friend's case the policy is granted at the company level so no single employee can defect and break it for the rest, while in my daughter's case one high scorer could invalidate the reassessment for everyone, which is exactly what made defection punishable and the bullying emerge naturally.