Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Opus 4.6

anthropic.com

Post reply on HN
Print view View original

381–390 of 1001 posts

Re: Claude Opus 4.6

#381

Post by Longwelwind »

skydhash wrote: post #344
sweetheart wrote: post #112

Earlier quoted context omitted.

React's core is agnostic when it comes to the actual rendering interface. It's just all the fancy algos for diffing and updating the underlying tree. Using it for rendering a TUI is a very reasonable application of the technology.

The terminal UI is not a tree structure that you can diff. It’s a 2D cells of characters, where every manipulation is a stream of texts. Refreshing or diffing that makes no sense.

When doing advanced terminal UI, you might at some point have to layout content inside the terminal. At some point, you might need to update the content of those boxes because the state of the underlying app has changed. At that point, refreshing and diffing can make sense. For some, the way React organizes logic to render and update an UI is nice and can be used in other contexts.

Re: Claude Opus 4.6

#383

Post by Someone1234 »

nodja wrote: post #363
Someone1234 wrote: post #19

Does anyone with more insight into the AI/LLM industry happen to know if the cost to run them in normal user-workflows is falling? The reason I'm asking is because "agent teams" while a cool concept, it largely constrained by the economics of running multiple LLM agents (i.e. plans/API calls that make this practical at scale are expensive). A year or more ago, I read that both Anthropic and OpenAI were losing money o…

> A year or more ago, I read that both Anthropic and OpenAI were losing money on every single request even for their paid subscribers, and I don't know if that has changed with more efficient hardware/software improvements/caching. This is obviously not true, you can use real data and common sense. Just look up a similar sized open weights model on openrouter and compare the prices. You'll note the similar sized mode…

> This is obviously not true, you can use real data and common sense.

It isn't "common sense" at all. You're comparing several companies losing money, to one another, and suggesting that they're obviously making money because one is under-cutting another more aggressively.

LLM/AI ventures are all currently under-water with massive VC or similar money flowing in, they also all need training data from users, so it is very reasonable to speculate that they're in loss-leader mode.

Re: Claude Opus 4.6

#384

Post by kzahel »

neuronexmachina wrote: post #81
pjot wrote: post #62

Claude Code release notes: > Version 2.1.32: • Claude Opus 4.6 is now available! • Added research preview agent teams feature for multi-agent collaboration (token-intensive feature, requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1) • Claude now automatically records and recalls memories as it works • Added "Summarize from here" to the message selector, allowing partial conversation summarization. • Skills defi…

> Claude now automatically records and recalls memories as it works Neat: https://code.claude.com/docs/en/memory I guess it's kind of like Google Antigravity's "Knowledge" artifacts?

I looked into it a bit. It stores memories near where it stores JSONL session history. It's per-project (and specific to the machine) Claude pretty aggressively and frequently writes stuff in there. It uses MEMORY.md as sort of the index, and will write out other files with other topics (linking to them from the main MEMORY.md) file.

It gives you a convenient way to say "remember this bug for me, we should fix tomorrow". I'll be playing around with it more for sure.

I asked Claude to give me a TLDR (condensed from its system prompt):

----

Persistent directory at ~/.claude/projects/{project-path}/memory/, persists across conversations

MEMORY.md is always injected into the system prompt; truncated after 200 lines, so keep it concise

Separate topic files for detailed notes, linked from MEMORY.md What to record: problem constraints, strategies that worked/failed, lessons learned

Proactive: when I hit a common mistake, check memory first - if nothing there, write it down

Maintenance: update or remove memories that are wrong or outdated

Organization: by topic, not chronologically

Tools: use Write/Edit to update (so you always see the tool calls)

Re: Claude Opus 4.6

#385

Post by libraryofbabel »

nomel wrote: post #278
dmk wrote: post #46

The benchmarks are cool and all but 1M context on an Opus-class model is the real headline here imo. Has anyone actually pushed it to the limit yet? Long context has historically been one of those "works great in the demo" situations.

Has a "N million context window" spec ever been meaningful? Very old, very terrible, models "supported" 1M context window, but would lose track after two small paragraphs of context into a conversation (looking at you early Gemini).

Umm, Sonnet 4.5 has a 1m context window option if you are using it through the api, and it works pretty well. I tend not to reach for it much these days because I prefer Opus 4.5 so much that I don't mind the added pain of clearing context, but it's perfectly usable. I'm very excited I'll get this from Opus now too.

Re: Claude Opus 4.6

#386

Post by RussianCow »

gnatolf wrote: post #246
gcanyon wrote: post #207

Earlier quoted context omitted.

One aspect of this is that apparently most people can't draw a bicycle much better than this: they get the elements of the frame wrong, mess up the geometry, etc.

Absolutely. A technically correct bike is very hard to draw in SVG without going overboard in details

I'm not positive I could draw a technically correct bike with pen and paper (without a reference), let alone with SVG!

Re: Claude Opus 4.6

#387

Post by 6thbit »

simonw wrote: post #40

The bicycle frame is a bit wonky but the pelican itself is great: https://gist.github.com/simonw/a6806ce41b4c721e240a4548ecdbe...

do you have a gif? i need an evolving pelican gif

Re: Claude Opus 4.6

#388

Post by EcommerceFlow »

epolanski wrote: post #371
EcommerceFlow wrote: post #91

Anecdotal, but it 1 shot fixed a UI bug that neither Opus 4.5/Codex 5.2-high could fix.

+1, same experience, switched model as I've read the news thinking "let's try". But it spent lots and lots of time thinking more than 4.5, did you had the same impression.

I didn't compare to that level, just had it create a plan first then implemented it.

Re: Claude Opus 4.6

#389

Post by bopbopbop7 »

breuleux wrote: post #257
itay-maman wrote: post #204

Impressive results, but I keep coming back to a question: are there modes of thinking that fundamentally require something other than what current LLM architectures do? Take critical thinking — genuinely questioning your own assumptions, noticing when a framing is wrong, deciding that the obvious approach to a problem is a dead end. Or creativity — not recombination of known patterns, but the kind of leap where you r…

> These feel like they involve something beyond "predict the next token really well, with a reasoning trace." I don't think there's anything you can't do by "predicting the next token really well". It's an extremely powerful and extremely general mechanism. Saying there must be "something beyond that" is a bit like saying physical atoms can't be enough to implement thought and there must be something beyond the physi…

> Besides, what is the human brain if not a machine that generates "tokens" that the body propagates through nerves to produce physical actions?

Ah yes, the brain is as simple as predicting the next token, you just cracked what neuroscientists couldn't for years.

Re: Claude Opus 4.6

#390

Post by petters »

> We build Claude with Claude.

Yes and it shows. Gemini CLI often hangs and enters infinite loops. I bet the engineers at Google use something else internally.

Post reply on HN