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

551–560 of 565 posts

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

#551

Post by extr »

sarchertech wrote: post #536
extr wrote: post #528

Earlier quoted context omitted.

Fair, that's optimistic, and it depends what you're doing. Looking at a personal project I had a PR from this week at +3000 -500 that I feel quite good about, took about 2 nights of about an hour each session to shape it into what I needed (a control plane for a polymarket trading engine). Though if I'm being fair, this was an outlier, only possible because I very carefully built the core of the engine to support thi…

Those numbers are much more believable, but now we’re well into maybe a 2-3x speed up. I can easily write 500 LOC in an hour if I know exactly what I’m building (ignoring that LOC is a terrible metric). But now I have to spend more time understanding what it wrote, so best case scenario we’re talking maybe a 50% speed up to a part of my job that I spent maybe 10-20% on. Making very big assumptions that this doesn’t a…

Thinking in terms of a "speed up multiplier" undersells it completely. The speed up on a task I would have never even attempted is infinite. For my +3000 PR recently on my polymarket engine control plane, I had no idea how these types of things are typically done. It would have taken me many hours to think through an implementation and hours of research online to assemble an understanding on typical best practices. Now with AI I can dispatch many parallel agents to examine virtually all all public resources for this at once.

Basically if it's been done before in a public facing way, you get a passable version of that functionality "for free". That's a huge deal.

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

#552

Post by travisgriggs »

eru wrote: post #262
hvb2 wrote: post #191

Earlier quoted context omitted.

> Yes, these things do best when they have a (simulated) environment they can make mistakes in and that can give them clear and fast feedback. This always felt like a reason to throw it at coding. With its rigid syntax you'll know quickly and cheaply if what was written passes an absolute minimaal level of quality.

Well, rigid syntax, type checkers, automated tests, etc. They all help.

Has this been shown to be true? Or just anecdotal?

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

#553

Post by auggierose »

laksjhdlka wrote: post #465
auggierose wrote: post #43

Earlier quoted context omitted.

Sure, I get it. For me a 2x Max would be ideal and usually enough. Now, guess why they are not offering that?

Where do you live? I'm in the midwest, US, and theoretical savings between 2x and 5x amounts to a single full bag of groceries. Literally. How can this possibly be a concern?

You are clearly overpaying for your groceries. I can cook for a week from the difference.

If there wasn't a significant difference, they would offer 2x Max, the demand is there. But they don't. Clearly, their strategy works on fanboys like you.

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

#554

Post by nvardakas »

visarga wrote: post #424
nvardakas wrote: post #386

Earlier quoted context omitted.

[dead]

> I build with Claude Code daily and the context decay is real by the end of a long session it starts forgetting decisions we made earlier I generate task.md files before working on anything, some are short, others are super long and with many steps. The models don't deviate anymore. One trick is to make a post tool use hook to show the first open gate "- [ ]" line from task.md on each tool call. This keeps the agent…

[dead]

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

#555

Post by eru »

travisgriggs wrote: post #552
eru wrote: post #262

Earlier quoted context omitted.

Well, rigid syntax, type checkers, automated tests, etc. They all help.

Has this been shown to be true? Or just anecdotal?

Anecdotal from my own experience. But someone might have done a study by now: they are much cheaper and quicker to run on AIs than on undergrad students (yet alone professional devs).

Also pre-AI: when I set up nice property tests, I could develop much better even while a bit tired.

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

#556

Post by sphilipakis »

Myrmornis wrote: post #515
jeremychone wrote: post #419

Interesting, I’ve never needed 1M, or even 250k+ context. I’m usually under 100k per request. About 80% of my code is AI-generated, with a controlled workflow using dev-chat.md and spec.md. I use Flash for code maps and auto-context, and GPT-4.5 or Opus for coding, all via API with a custom tool. Gemini Pro and Flash have had 1M context for a long time, but even though I use Flash 3 a lot, and it’s awesome, I’ve neve…

This is interesting but don't you worry that you're competing with entire companies (e.g. Anthropic) and thus it's a losing battle? Since you're re-implementing a bunch of stuff they either do in their harness or have decided it was better not to do?

Personally I don't see aipack's pro@coder and other approaches (claude code, cursor, copilot, etc...) as competitors anymore. I use both approaches to solve different problems. I keep using the agentic solutions (claude code style) for more operational tasks, a bit like "smart interfaces to terminal", and pro@coder for coding / engineering tasks where I need a much tighter control over long running work sessions.

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

#558

Post by cwillu »

pqdbr wrote: post #361
olivercoleai wrote: post #358

[flagged]

I have no experience building this two-pass approach, but I arrived at it intuitively while planning for a new project. Any references to actual implementations?

This is someone's out of control bot.

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

#559

Post by cruffle_duffle »

insane_dreamer wrote: post #488
hedora wrote: post #140

Earlier quoted context omitted.

It's also identical to what Claude Code does if you put it in plan mode (bound to key), at least in my experience.

better to instruct it to write a plan .md file that is appropriately named so that it can be easily referenced/updated in multiple sessions. I've found that effective.

Dunno if you know this but the plan in plan mode is a markdown file! Ask it for the file and it will give it to you.

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

#560

Post by lukeundtrug »

jeremychone wrote: post #543
lukeundtrug wrote: post #487

Earlier quoted context omitted.

I built myself an AST based solution for that during the last 6 months roughly. I always wondered whether grep and agent-based discovery will be the end of it and thought it just has to be better with a more deterministic approach. In the end it's hard to measure but personally I feel that my agent rarely misses any context for a given task, so I'm pretty happy with it. I used a different approach than tree-sitter be…

I looked at your solution and extension README, and it's very interesting and well thought out. The fact that you've been using it for six months and that it performs well says a lot. At the end of the day, that's what counts. I like your idea of piggybacking on top of the LSP services, and I can imagine that this was quite a bit of work. Doing it as an MCP server makes it usable across different tools. I also really…

Thanks for taking the time to check it out and for the kind words! I really appreciate it.

I totally get sticking with your current approach. Your workflow sounds very intriguing as well. A combination of both approaches might really be very interesting :) Adding an LLM interpretation layer on top of my graph is also something I'm actively considering.

Thanks for the great discussion, and best of luck with your tool and workflow!

Post reply on HN