Earlier quoted context omitted.
Neat idea, but why should I use AI for a find and replace? It feels like shooting a fly with a bazooka
Bazooka guarantees the hit
I like LLMs, but guarantees in LLMs are... you know... not guaranteed ;)
Claude Opus 4.6
761–770 of 1001 posts
Re: Claude Opus 4.6
#762I'm still not sure I understand Anthropic's general strategy right now. They are doing these broad marketing programs trying to take on ChatGPT for "normies". And yet their bread and butter is still clearly coding. Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the depth of research, the type of tasks it can handle, and the qual…
Their "constitution" is just garbage meant to defend them ripping off copyrighted material with the excuse that "it's not plagiarizing, it thinks!!!!1" which is, false.
I don't recall them ever offering that legal reasoning - I'm sure you can provide a citation?
Re: Claude Opus 4.6
#763Re: Claude Opus 4.6
#764They are also giving away $50 extra pay as you go credit to try Opus 4.6. I just claimed it from the web usage page[1]. Are they anticipating higher token usage for the model or just want to promote the usage? [1] https://claude.ai/settings/usage
So thats 2M tokens for free basically?
Re: Claude Opus 4.6
#765Earlier quoted context omitted.
Oh, is that what the issue is? I've seen the "flicker" thing as a meme, but as someone who uses Claude Code I've never noticed. I use ghostty mostly, so maybe it's not an issue with ghostty? Or maybe I just haven't noticed it.
Yes it's people using bad tools on underpowered machines as far as I have seen
I'm using it on Framework Desktop 128GB RAM... Its scroll is utterly broken outside of VS Code for me, on Gnome Terminal, Tilix and a few others.
And even in VS Code, it wonks out after a while.
My guess is that it mostly works on Apple devices.
Re: Claude Opus 4.6
#766Just tested the new Opus 4.6 (1M context) on a fun needle-in-a-haystack challenge: finding every spell in all Harry Potter books. All 7 books come to ~1.75M tokens, so they don't quite fit yet. (At this rate of progress, mid-April should do it ) For now you can fit the first 4 books (~733K tokens). Results: Opus 4.6 found 49 out of 50 officially documented spells across those 4 books. The only miss was "Slugulus Eruc…
Comparison to another model?
Re: Claude Opus 4.6
#767Earlier quoted context omitted.
> "engineers optimizing inferencing" are we sure this is not a fancy way of saying quantization?
When MP3 became popular, people were amazed that you could compress audio to 1/10th its size with minor quality loss. A few decades later, we have audio compression that is much better and higher-quality than MP3, and they took a lot more effort than "MP3 but at a lower bitrate." The same is happening in AI research now.
> A few decades later, we have audio compression that is much better and higher-quality than MP3
Just curious, which formats and how they compare, storage wise?
Also, are you sure it's not just moving the goalposts to CPU usage? Frequently more powerful compression algorithms can't be used because they use lots of processing power, so frequently the biggest gains over 20 years are just... hardware advancements.
Re: Claude Opus 4.6
#768Say I am just an average coder doing a days work with Claude. How much will that cost?
Re: Claude Opus 4.6
#769This is the first model to which I send my collection of nearly 900 poems and an extremely simple prompt (in Portuguese), and it manages to produce an impeccable analysis of the poems, as a (barely) cohesive whole, which span 15 years. It does not make a single mistake, it identifies neologisms, hidden meaning, 7 distinct poetic phases, recurring themes, fragments/heteronyms, related authors. It has left me completel…
> What is this sorcery?
The one you'll be seeking counter-spells against pretty soon.
Re: Claude Opus 4.6
#770Agent teams nuke your tmux layout. The fix is one line: new-window instead of split-pane. Filed as a bug.