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

1M context is now generally available for Opus 4.6 and Sonnet 4.6

claude.com

Post reply on HN
Print view View original

51–60 of 565 posts

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#51

Post by grafmax »

boredtofears wrote: post #40
ogig wrote: post #33

Earlier quoted context omitted.

When running long autonomous tasks it is quite frequent to fill the context, even several times. You are out of the loop so it just happens if Claude goes a bit in circles, or it needs to iterate over CI reds, or the task was too complex. I'm hoping a long context > small context + 2 compacts.

All of those things are smells imo, you should be very weary of any code output from a task that causes that much thrashing to occur. In most cases it’s better to rewind or reset and adapt your prompt to avoid the looping (which usually means a more narrowly defined scope)

A person has a supervision budget. They can supervise one agent in a hands-on way or many mostly-hands-off agents. Even though theres some thrashing assistants still get farther as a team than a single micromanaged agent. At least that’s my experience.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#52

Post by chrisweekly »

boredtofears wrote: post #40
ogig wrote: post #33

Earlier quoted context omitted.

When running long autonomous tasks it is quite frequent to fill the context, even several times. You are out of the loop so it just happens if Claude goes a bit in circles, or it needs to iterate over CI reds, or the task was too complex. I'm hoping a long context > small context + 2 compacts.

All of those things are smells imo, you should be very weary of any code output from a task that causes that much thrashing to occur. In most cases it’s better to rewind or reset and adapt your prompt to avoid the looping (which usually means a more narrowly defined scope)

weary (tired) -> wary (cautious)

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#53

Post by steve-atx-7600 »

dimitri-vs wrote: post #39
MikeNotThePope wrote: post #20

Earlier quoted context omitted.

Is it ever useful to have a context window that full? I try to keep usage under 40%, or about 80k tokens, to avoid what Dex Horthy calls the dumb zone in his research-plan-implement approach. Works well for me so far. No vibes allowed: https://youtu.be/rmvDxxNubIg?is=adMmmKdVxraYO2yQ

It's kind of like having a 16 gallon gas tank in your car versus a 4 gallon tank. You don't need the bigger one the majority of the time, but the range anxiety that comes with the smaller one and annoyance when you DO need it is very real.

It seems possible, say a year or two from now that context is more like a smart human with a “small”, vs “medium” vs “large” working memory. The small fellow would be able to play some popular songs on the piano , the medium one plays in an orchestra professionally and the x-large is like Wagner composing Der Ring marathon opera. This is my current, admittedly not well informed mental model anyway. Well, at least we know we’ve got a little more time before the singularity :)

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#54

Post by chaboud »

Awesome.... With Sonnet 4.5, I had Cline soft trigger compaction at 400k (it wandered off into the weeds at 500k). But the stability of the 4.6 models is notable. I still think it pays to structure systems to be comprehensible in smaller contexts (smaller files, concise plans), but this is great.

(And, yeah, I'm all Claude Code these days...)

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#55

Post by ashdksnndck »

MikeNotThePope wrote: post #44
ogig wrote: post #33

Earlier quoted context omitted.

When running long autonomous tasks it is quite frequent to fill the context, even several times. You are out of the loop so it just happens if Claude goes a bit in circles, or it needs to iterate over CI reds, or the task was too complex. I'm hoping a long context > small context + 2 compacts.

I haven't figured out how to make use of tasks running that long yet, or maybe I just don't have a good use case for it yet. Or maybe I'm too cheap to pay for that many API calls.

My change cuts across multiple systems with many tests/static analysis/AI code reviews happening in CI. The agent keeps pushing new versions and waits for results until all of them come up clean, taking several iterations.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#56

Post by mattfrommars »

vessenes wrote: post #7

This is super exciting. I've been poking at it today, and it definitely changes my workflow -- I feel like a full three or four hour parallel coding session with subagents is now generally fitting into a single master session. The stats claim Opus at 1M is about like 5.4 at 256k -- these needle long context tests don't always go with quality reasoning ability sadly -- but this is still a significant improvement, and…

Random: are you personally paying for Claude Code or is it paid by you employer?

My employer only pays for GitHub copilot extension

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#57

Post by steve-atx-7600 »

vessenes wrote: post #7

This is super exciting. I've been poking at it today, and it definitely changes my workflow -- I feel like a full three or four hour parallel coding session with subagents is now generally fitting into a single master session. The stats claim Opus at 1M is about like 5.4 at 256k -- these needle long context tests don't always go with quality reasoning ability sadly -- but this is still a significant improvement, and…

Did it get better? I used sonnet 4.5 1m frequently and my impression was that it was around the same performance but a hell of a lot faster since the 1m model was willing to spends more tokens at each step vs preferring more token-cautious tool calls.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#58

Post by tudelo »

MikeNotThePope wrote: post #44
ogig wrote: post #33

Earlier quoted context omitted.

When running long autonomous tasks it is quite frequent to fill the context, even several times. You are out of the loop so it just happens if Claude goes a bit in circles, or it needs to iterate over CI reds, or the task was too complex. I'm hoping a long context > small context + 2 compacts.

I haven't figured out how to make use of tasks running that long yet, or maybe I just don't have a good use case for it yet. Or maybe I'm too cheap to pay for that many API calls.

I mean if you don't have your company paying for it I wouldn't bother... We are talking sessions of 500-1000 dollars in cost.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#59

Post by hombre_fatal »

SkyPuncher wrote: post #45
MikeNotThePope wrote: post #20

Earlier quoted context omitted.

Is it ever useful to have a context window that full? I try to keep usage under 40%, or about 80k tokens, to avoid what Dex Horthy calls the dumb zone in his research-plan-implement approach. Works well for me so far. No vibes allowed: https://youtu.be/rmvDxxNubIg?is=adMmmKdVxraYO2yQ

Yes. I've recently become a convert. For me, it's less about being able to look back -800k tokens. It's about being able to flow a conversation for a lot longer without forcing compaction. Generally, I really only need the most recent ~50k tokens, but having the old context sitting around is helpful.

Also, when you hit compaction at 200k tokens, that was probably when things were just getting good. The plan was in its final stage. The context had the hard-fought nuances discovered in the final moment. Or the agent just discovered some tiny important details after a crazy 100k token deep dive or flailing death cycle.

Now you have to compact and you don’t know what will survive. And the built-in UI doesn’t give you good tools like deleting old messages to free up space.

I’ll appreciate the 1M token breathing room.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#60

Post by steve-atx-7600 »

zmmmmm wrote: post #8

Noticed this just now - all of a sudden i have 1M context window (!!!) without changing anything. It's actually slightly disturbing because this IS a behavior change. Don't get me wrong, I like having longer context but we really need to pin down behaviour for how things are deployed.

You can pin to specific models with —-model. Check out their doc. See https://support.claude.com/en/articles/11940350-claude-code-.... You can also pin to a less specific tag like sonnet-4.5[1m] (that’s from memory might be a little off).
Post reply on HN