Dude. Not even your blog post is clear enough. I had to right click one of the images and open it in another tab in order to be able to discern _anything_ on the image.
I don't think that works at all times; actually I think it only works when starting a conversation. In the middle, "Why ~did you~ while action as an export in Lisp <this happened>?" needs a certain level of mind gynmastics that is not worth it. I'd rather curse at it.
As a matter of fact, for the line of work I do (programming, devops, the works) being conscious about the fact that I am just getting an algorithm outputting text that is probabilistically related to the input I gave it would actually be healthy for me and my mental state.
I HATE having to say "you" when working with an LLM.
What is means is that now hiring is symmetrically broken.
Hiring has always been broken. May be not completely at the FAANG level, but below that, and more importantly across the globe it's seriously broken, and there's a high variance when it comes to hiring consultants quality.
The widespread use of AI vy applicants is very likely surfacing how comfortable consultants were doing the bare minimum when hiring.
Source: I've been working for 10+ years for a company that has an ATS for mostly European clients.
I know for a fact how crappy work around hiring is.
P.S.: the article focuses mostly on one direction of hiring. The opposite direction is also suffering from this (briefly explained in the article about AI fueled hiring bias). In my opinion, that is an even greater problem.
"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."
> No headers per element. No pointers. No jumping around the heap.
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.
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.
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.
if "git versioned" means the .md files themselves, I'm sold. I am actually processing files using a git based workflow in order to tell claude what to look at.
Books _are_ expensive. This article only looks at the monetary side of it.
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.
> I don't know if you're giving this as something you've actually given Claude, but I don't think it's a good way of using Claude.
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.