> I have been experimenting with AI-assisted drafting for HN comments

forgive the hyperbole but this seems completely insane to me. like is the purpose of a forum not to share our collective human experiences? or do you get off on some internetpointmaxxing side game instead

i just don't get it, what are you optimizing for here exactly. are you trying to remove every ounce of autonomy from your life or what

Seriously people, type out your own thoughts. If I want to chat with a clanker I can do that on my own time.

i think it's very hard to sing all the way up to the high C5 as a male, this doesn't surprise me at all

i've never had to use control + o before but with the latest changes, i give Opus a simple task that should take a few seconds and it's like "used 15k tokens" and "thinking" for three minutes with absolutely zero indication or visibility as to what it's actually doing and i have to ESC ESC it to stop and ask what the FUCK are you actually doing claude?

Yes, I’ve been evaluating since the start of the year and since 4.6 suddenly the most innocuous requests will sit there “thinking” for 5+ minutes and if I can get it to show me the thinking it’s just going round in circles.

Or, it decided it needs to get API documentation out and spends tens of thousands of tokens fetching every file in a repo with separate tool use instead of reading the documentation.

Profitable, if you are charging for token usage, I suspect.

But I’m reaching the point where I can’t recommend claude to people who are interesting in skeptically trying it out, because of the default model.

I guess I engineered around this before 4.6 - I did notice a regression in it wanting to search deeper than I wanted and had specified, but just restricted it with tooling I wrote that would enforce what I wanted. In that respect, I feel comfortable running 4.6 with the guardrails I already have, but did notice some squirrelyness I didnt anticipate in my utility scripts.

It is clever. its its best and worst feature.

Yeah after my switch to Opus 4.6 I noticed a lot of this. I've been wary that eventually models are going to optimize for token usage increases, since that's how the company makes money. I told it to read the files in my directory (4 files, longest was like 380 lines) and caught it using 14 tool uses- including head -n 20 and tail -n 20 on a file. Definitely a what are you doing moment.

OTOH I find it pretty funny that the instant they manage to make a model that breaks general containment of popularity and usefulness (4.5), the toxicity of the business model kicks in and they instantly enshittify.

I think this change is really disingenuous.

If they hide how the tool is accessing files (aka using tokens) and then charging us per token - how are we able to track loosely what our spend is?

I’m all for simplification of the UX. But when it’s helping to hide the main spend it feels shitty.

i think yesterday it ate the whole context window in one thinking call.

i bet in a week itll eat the whole 5hour throttle in one call too:P

music is a form of storytelling and expression of human emotions, i can't connect with some generated noise or go to its live gig

after seeing the recent surge of meme stocks, 0dte option trading, sports betting, prediction markets and funny internet coins, one thing is apparent is that people just love to gamble

so i don't believe it will ever go to zero as it has intrinsic value as a casino, if nothing else

this is cultural appropriation, i learned to type like this on irc in the 90s

also i don't want to be mistaken for a phone poster

There are two notable differences between when the AGI-posters do it and when IRC-posters do it. AGI-posters extend their lowercase posting to what would normally be seen as more formal communication. They also tend to stick to using punctuation despite the lowercase. IRC posters usually keep it to informal communications, where it's a sign of casualness. That said, there is overlap, and it's of course not possible to instantly distinguish someone as a Sama devotee because of how they type; but it is clear that a lot of people in that bubble are intentionally adopting the style.

i really dislike the constant appeal to authority of techfluencers on HN

man they really butchered the user interface, the "dark" mode now isn't even dark, it's just grey, and it's looking more like a whitespacemaxxed children's toy than a tool for professionals

Right now it looks like as VS Code (give or take). Pretty sure both are\will be used by many professionals.

"looks like a toy" has very little to do with its use anyway.

Yeah the theming options are lacking and I could never hack one up to work.

yeah it looks worse than before

i don't know, are we intelligent?

you could argue that our input (senses) entirely define the output (thoughts, muscle movements, etc)

The whole point of humans is the way we process the input. Every life form out there receives sound vibrations and has photons hitting their body all the time, not everyone uses that information in the same way or at all. That plus natal reflexes and hardcoded assumptions

There's a bit of baked-in stuff as well. We are a full culture-mind-body[-spirit] system.

Fortunately we've got the full system because even under ideal conditions nobody's actually ever been intelligent at all times and we need the momentum from that full system to resume in an intelligent direction after an upset when it's not all at its best.

i don't think i have ever even looked at what order the commits are, i only care about the diff vs the target branch when reviewing

especially since every developer has a different idea of what a commit should be, with there being no clear right answer