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

281–290 of 565 posts

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

#281

Post by silverlake »

iamacyborg wrote: post #258
kaizenb wrote: post #120

Earlier quoted context omitted.

Thanks for the video. His fix for "the dumb zone" is the RPI Framework: ● RESEARCH. Don't code yet. Let the agent scan the files first. Docs lie. Code doesn't. ● PLAN. The agent writes a detailed step-by-step plan. You review and approve the plan, not just the output. Dex calls this avoiding "outsourcing your thinking." The plan is where intent gets compressed before execution starts. ● IMPLEMENT. Execute in a fresh…

> RESEARCH. Don't code yet. Let the agent scan the files first. Docs lie. Code doesn't. I find myself often running validity checks between docs and code and addressing gaps as they appear to ensure the docs don’t actually lie.

I have Codex and Gemini critique the plan and generate their plans. Then I have Claude review the other plans and add their good ideas. It frequently improves the plan. I then do my careful review.

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

#282

Post by lukan »

SequoiaHope wrote: post #41
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.

Yep I have an autonomous task where it has been running for 8 hours now and counting. It compacts context all the time. I’m pretty skeptical of the quality in long sessions like this so I have to run a follow on session to critically examine everything that was done. Long context will be great for this.

Are those long unsupervised sessions useful? In the sense, do they produce useful code or do you throw most of it away?

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

#283

Post by ipnon »

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 think the combinatorial space is just too much. When I did web dev it was mostly transforming HTML/JSON from well-defined type A to well-defined type B. Everything is in text. There's nothing to reason about besides what is in the prompt itself. But constructing and maintaining a mental model of a chip and all of its instructions and all of the empirical data from profiling is just too much for SOTA to handle reliably.

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

#284

Post by suheilaaita »

This blew my mind the first i saw this. Another leap in AI that just swooshes by. In a couple of months, every model will be the same. Can't wait for IDEs like cursor and vs code to update their tooling to adap for this massive change in claude models.

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

#285

Post by rafaelmn »

Frannky wrote: post #117

Opus 4.6 is nuts. Everything I throw at it works. Frontend, backend, algorithms—it does not matter. I start with a PRD, ask for a step-by-step plan, and just execute on each step at a time. Sometimes ideas are dumb, but checking and guiding step by step helps it ship working things in hours. It was also the first AI I felt, "Damn, this thing is smarter than me." The other crazy thing is that with today's tech, these…

I've seen a few instances of where Claude showed me a better way to do something and many many more instances of where it fails miserably.

Super simple problem :

I had a ZMK keyboard layout definition I wanted it to convert it to QMK for a different keyboard that had one key less so it just had to trim one outer key. It took like 45 minutes of back and forth to get it right - I could have done it in 30 min manually tops with looking up docs for everything.

Capability isn't the impressive part it's the tenacity/endurance.

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

#286

Post by holoduke »

I am currently mass translating millions of records with short descriptions. Somehow tokens are consumed extremely fast. I have 3 max memberships. And all 3 of them are hitting the 5 hour limit in about 5 to 10 minutes. Still don't understand why this is happening.

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

#287

Post by necovek »

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…

As someone who did Python professionally from a software engineering perspective, I've actually found Python to be pretty crappy really: unaware of _good_ idioms living outside tutorials and likely 90% of Python code out there that was simply hacked together quickly.

I have not tested, but I would expect more niche ecosystems like Rust or Haskell or Erlang to have better overall training set (developer who care about good engineering focus on them), and potentially produce the best output.

For C and C++, I'd expect similar situation with Python: while not as approachable, it is also being pushed on beginning software engineers, and the training data would naturally have plenty of bad code.

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

#288

Post by sagarpatil »

furyofantares wrote: post #112
mgambati wrote: post #86

Earlier quoted context omitted.

1m context in OpenAI and Gemini is just marketing. Opus is the only model to provide real usable bug context.

I'm directly conveying my actual experience to you. I have tasks that fill up Opus context very quickly (at the 200k context) and which took MUCH longer to fill up Codex since 5.2 (which I think had 400k context at the time). This is direct comparison. I spent months subscribed to both of their $200/mo plans. I would try both and Opus always filled up fast while Codex continued working great. It's also direct experie…

This has been my experience too.

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

#289

Post by rhubarbtree »

jf___ wrote: post #160

there is a parallel between managing context windows and hard real-time system engineering. A context window is a fixed-size memory region. It is allocated once, at conversation start, and cannot grow. Every token consumed — prompt, response, digression — advances a pointer through this region. There is no garbage collector. There is no virtual memory. When the space is exhausted, the system does not degrade graceful…

There is compaction, which is analogous to gc

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

#290

Post by MikeNotThePope »

Barbing wrote: post #129
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

Looking at this URL, typo or YouTube flip the si tracking parameter? youtu.be/rmvDxxNubIg?is=adMmmKdVxraYO2yQ

I just cut & pasted the share URL provided by YouTube. Strip out the query param if you like.
Post reply on HN