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

Post by lifeformed » Sat, Mar 14, 2026, 8:12 AM UTC

sho wrote: post #171

furyofantares wrote: post #135

Earlier quoted context omitted.

When Anthropic said they wouldn't sell LLMs to the government for mass surveillance or autonomous killing machines, and got labeled a supply chain risk as a result, OpenAI told the public they have the same policy as Anthropic while inking a deal with the government that clearly means "actually we will sell you LLMs for mass surveillance or autonomous killing machines but only if you tell us it's legal". If you alrea…

I'm not some kind of OpenAI or Pentagon fanboy, but it's pretty easy to for me to understand why a buyer of a critical technology wants to be free to use it however they want, within the law, and not subject to veto from another entity's political opinions. It sounds perfectly reasonable to me for the military to want to decide its uses of technologies it purchases itself. It's not like the military was specifically…

Post by peacebeard » Sat, Mar 14, 2026, 8:27 AM UTC

esperent wrote: post #89

convenwis wrote: post #5

Is there a writeup anywhere on what this means for effective context? I think that many of us have found that even when the context window was 100k tokens the actual usable window was smaller than that. As you got closer to 100k performance degraded substantially. I'm assuming that is still true but what does the curve look like?

> As you got closer to 100k performance degraded substantially In practice, I haven't found this to be the case at all with Claude Code using Opus 4.6. So maybe it's another one of those things that used to be true, and now we all expect it to be true. And of course when we expect something, we'll find it, so any mistakes at 150k context use get attributed to the context, while the same mistake at 50k gets attributed…

Post by lemagedurage » Sat, Mar 14, 2026, 8:32 AM UTC

n_u wrote: post #236

syntaxing wrote: post #144

It’s interesting because my career went from doing higher level language (Python) to lower language (C++ and C). Opus and the like is amazing at Python, honestly sometimes better than me but it does do some really stupid architectural decisions occasionally. But when it comes to embedded stuff, it’s still like a junior engineer. Unsure if that will ever change but I wonder if it’s just the quality and availability of…

I've found it's ok at Rust. I think a lot of existing Rust code is high quality and also the stricter Rust compiler enforces that the output of the LLM is somewhat reasonable.

Post by pjerem » Sat, Mar 14, 2026, 8:48 AM UTC

furyofantares wrote: post #77

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

I'd been on Codex for a while and with Codex 5.2 I: 1) No longer found the dumb zone 2) No longer feared compaction Switching to Opus for stupid political reasons, I still have not had the dumb zone - but I'm back to disliking compaction events and so the smaller context window it has, has really hurt. I hope they copy OpenAI's compaction magic soon, but I am also very excited to try the longer context window.

Post by tariky » Sat, Mar 14, 2026, 8:55 AM UTC