TomGarden

Yeah. People get confused because they're not a bank, but they offer banking services (as a middleman)

YMMV but for me even models in the same family fail in different ways, and every incremental update changes it

By this logic you'd probably be wise to tier your claude.md by model (sonnet/opus) as well as effort level too, considering the varying failure modes

Agreed. Time trap, and even worse imo: creative flow trap. You enter critique mode too early in the process

Caught myself about to praise this, but it's the absolute bare minimum.

Time to delete the symlinks

Agreed. Banking is the killer app imo

Haha clever

I wonder if Lawslop is gonna become a mainstream expression. Anyone got a better term?

Agreed. Hallucinations and reliability are the main hurdles to anything being 'agi' in my book

This is so nostalgic!

Side note, Lucasarts' games rewired my kid brain to expect humor and (good) voice acting in games. It's really guided (and limited) what games I'm able to enjoy

This made me laugh out loud.

All the Apple Intelligence commercials were shamelessly this too. Felt like such poor branding for apple

I see! I've only really used it for coding. You should design velcrobench!

I love it as a variation from the others. 3.8 flash is the best back-and-forth model for iterating imo, but would not use for long horizon

I find just letting a model record a video it can read frame by frame later works fine, Gemini 3.8 flash would be solid for that

Agreed. They really are the greediest when it comes to data for training (unsurprising for google I guess)

Agreed. The language consistently triggers visceral negative reactions from me at this point.

You sure it was 3.8 Flash? It hasn't been called Gemini cli in a WHILE...

Nothing will change before we get perp walks. Money means nothing here.

I bought the top rated Sony's on Android and it was awful. Glad to hear there's better options!

Yeah, it's the same on Mac/iphone but better codecs. Still lossy but better than the Android experience

My understanding is that broad state power to the benefit of the people, Scandinavia style, is not the same as broad state power to monitor and/or control the people.

Arguably those two types of power are in conflict in terms of desired outcomes.

I find it slightly more acceptable, but yeah agree, still bad.

My most used follow-ups with Opus 5 are "one thing at a time" and "too much text".

Really hope they figure this thing out

Yeah agree. Someone on HN posed the theory that the dogfooding might have worked against them here - the theory is that internally they used Fable as conversational agent and Opus as subagents, leading to Opus falling deeper into a style mainly aimed at other LLMs.

All conjecture of course, and yeah it's hard to imagine they would enjoy this prose internally

It seems they are taking it seriously now - Boris et al have been mentioning they are working on a fix and shipped a temporary band-aid output style to combat Opus 5's horrendous prose.

We'll see if they can do it, I originally got into Claude Code because it, at the time, felt more accessible/conversational than Codex/Gemini. Now it's shifted to say the least

The societal hurt coming out of public releases of image/video generation models must surely outweight the gain. That said, this is super impressive.

At least we have parking lots. Ah, so many parking lots

I was thinking that, but the use of em-dashes is different from the normal LLM use.

If this is straight out of an LLM I am impressed

Interesting question for sure, but for now the writing is just bad. So people might not know it's LLM prose, they just notice its poorly written and engage with the ideas less

Exactly, unless they solve reliability and jaggedness somehow and keep a moat with it, I don't see sudden brilliance with compunding errors leading to substantially more adoption. Most things that need doing in corporate america are quite simple but need reliable follow-through