[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?
1M context is now generally available for Opus 4.6 and Sonnet 4.6
361–370 of 565 posts
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#362I'm very happy about this change. For long sessions with Claude it was always like a punch to the gut when a compaction came along. Codex/GPT-5.4 is better with compactions so I switched to that to avoid the pain of the model suddenly forgetting key aspects of the work and making the same dumb errors all over again. I'm excited to return to Claude as my daily driver!
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#363The big change here is: > Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages. For Claude Code users this is huge - assuming coherence remains strong past 200k tok.
If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context.
I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong
I think context decay is a bigger problem then we feel like.
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#364Earlier quoted context omitted.
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.
Quite sure it's not about the language but the domain.
Agreed. When I've written very low level code where there are "odd" constraints ("this function must never take a lock, no system calls can be made" etc) the LLM would accidentally violate them. It seems sort of obvious why - the vast majority of code it is trained on does not have those constraints.
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#365Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#366Earlier quoted context omitted.
What kinds of things are you building? This is not my experience at all. Just today I asked Claude using opus 4.6 to build out a test harness for a new dynamic database diff tool. Everything seemed to be fine but it built a test suite for an existing diff tool. It set everything up in the new directory, but it was actually testing code and logic from a preexisting directory despite the plan being correct before I tol…
You probably just don't have the hang of it yet. It's very good but it's not a mind reader and if you have something specific you want, it's best to just articulate that exactly as best you can ("I want a test harness for , which you can find "). You need to explain that you want tests that assert on observable outcomes and state, not internal structure, use real objects not mocks, property based testing for invarian…
I absolutely have the hang of Claude and I still find that it can make those ridiculous mistakes, like replicating logic into a test rather than testing a function directly, talking to a local pg that was stale/ running, etc. I have a ton of skills and pre-written prompts for testing practices but, over longer contexts, it will forget and do these things, or get confused, etc.
You can minimize these problems with TLC but ultimately it just will keep fucking up.
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#367Opus 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…
What kinds of things are you building? This is not my experience at all. Just today I asked Claude using opus 4.6 to build out a test harness for a new dynamic database diff tool. Everything seemed to be fine but it built a test suite for an existing diff tool. It set everything up in the new directory, but it was actually testing code and logic from a preexisting directory despite the plan being correct before I tol…
Try https://github.com/gsd-build/get-shit-done. It's been a game changer for me.
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#368The big change here is: > Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages. For Claude Code users this is huge - assuming coherence remains strong past 200k tok.
If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context. I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong I think context decay is a bigger problem then we feel like.
That’s not context decay, that’s training data ambiguity. So much misinformation, nerfs, buffs, changes that an LLM can not keep up given the training time required. Do it for a game that has been stable and it knows its stuff.
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#369The big change here is: > Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages. For Claude Code users this is huge - assuming coherence remains strong past 200k tok.
If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context. I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong I think context decay is a bigger problem then we feel like.
We need an MCP for path of building
Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6
#370The stuff I built with Opus 4.6 in the past 2.5 weeks: Full clone of Panel de Pon/Tetris attack with full P2P rollback online multiplayer: https://panel-panic.com An emulator of the MOS 6502 CPU with visual display of the voltage going into the DIP package of the physical CPU: https://larsdu.github.io/Dippy6502/ I'm impressed as fuck, but a part of me deep down knows that I know fuck all about the 6502 or its assembl…
That game is AWESOME! The fact that was vibe coded is insane.