1M context is now generally available for Opus 4.6 and Sonnet 4.6 • Hacker News Board

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

#561

Post by hnipps » Mon, Mar 16, 2026, 11:33 PM UTC

tommek4077 wrote: post #532

hnipps wrote: post #520

Why would anyone need this much context? Genuine question. It's not worth the drop in quality IMO.

You sound like: "Why would anyone need more than 640KB RAM?!".

That’s just not comparable. I’ll use your figure: If you use 400KB RAM for a process, using the remaining 240KB for something else doesn’t degrade the performance of the initial process (assuming nothing is trying to use more than the available RAM). Each unit of RAM is independent no?

Every token of context you use causes a drop in LLM performance.

More RAM == more processes can be supported with no degradation

More context != more stuff can be done with no degradation

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

#562

Post by insane_dreamer » Tue, Mar 17, 2026, 11:14 PM UTC

cruffle_duffle wrote: post #559

insane_dreamer wrote: post #488

Earlier quoted context omitted.

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.

yes, but if you start a fresh session to continue working on your project, it's a lot easier if you already know which PLAN file you need for your project. Plus you can commit it.

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

#563

Post by chrisweekly » Fri, Mar 20, 2026, 1:11 AM UTC

hparadiz wrote: post #294

ai_fry_ur_brain wrote: post #211

Earlier quoted context omitted.

Im convinced everyone saying this is building the simplest web apps, and doing magic tricks on themselves.

I've been building a new task manager in C for Linux. If you're not using AI you are cooked. You just don't realize it yet. https://i.imgur.com/YXLZvy3.png

you're engaging w a troll

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

#564

Post by tuo-lei » Fri, Mar 27, 2026, 6:37 AM UTC

My main frustration with long-context coding sessions isn't just the limit itself, it's that after the fact it's hard to tell which turns actually caused the context to bloat or the session to go off track. It's painful enough I have to build a tool to help myself understand the context/turn data correlation. I have to manual compact now

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

#565

Post by gck1 » Sat, Mar 28, 2026, 5:41 PM UTC

tontinton wrote: post #473

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…

Yeah we all converge to the same workflow, in my ai coding agent I'm working on now, I've added an "index" tool that uses tree-sitter to compress and show the AI a skeleton of a code file. Here's the implementation for the interested: https://github.com/tontinton/maki/blob/main/maki-code-index%...

I'm curious, what does your workflow look like? I saw a plan prompt there, but no specs. When you want to change something, implement a new feature etc, do you just prompt requirements, have it write the plan and then have it work on it?