Earlier quoted context omitted.
Claude Code already compacts automatically.
CC also has the same `/compact` command if you want to force it
/compact accepts parameters, so you can tell it to focus on something specific when compacting.
Managing context on the Claude Developer Platform
41–50 of 93 posts
Re: Managing context on the Claude Developer Platform
#42I just want Anthropic to release a way to remove my payment method from Claude before the eventual data breach.
Don’t they use Stripe? You can remove your payment method at any time. But Anthropic doesn’t really have your info in the first place.
Re: Managing context on the Claude Developer Platform
#43I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…
Related, it feels like AI Studio is the only mainstream LLM frontend that treats you like an adult. Choose your own safety boundaries, modify the context & system prompt as you please, clear rate limits and pricing, etc. It's something you come to appreciate a lot, even if we are in the part of the cycle where Google's models aren't particularly SOTA rn
Re: Managing context on the Claude Developer Platform
#44I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…
Related, it feels like AI Studio is the only mainstream LLM frontend that treats you like an adult. Choose your own safety boundaries, modify the context & system prompt as you please, clear rate limits and pricing, etc. It's something you come to appreciate a lot, even if we are in the part of the cycle where Google's models aren't particularly SOTA rn
How are they not SOTA? They're all very similar with ChatGPT being the worst (for my use case anyway). Like adding lambdas and random c++ function calls into my vulkan shaders.
Re: Managing context on the Claude Developer Platform
#45Context editing is interesting because most agents work on the assumption that KV cache is the most important thing to optimise and are very hesitant to remove parts of the context during work. It also sometimes introduces hallucinations, because parts of the context are with the assumption that eg tool results are there, but theyre not. Example Manus [0]. Eg, read file A, make changes on A. Then prompt on some more…
We often talk about "hallucinations" like it is its own thing, but is there really anything different about it from the LLM's normal output?
AFAICT, no. I think it just means "bad, unhelpful output" but isn't fundamentally different in any meaningful way from their super-helpful top-1% outputs.
It's kind of qualitatively different from the human perspective, so not a useless concept, but I think that is mainly because we can't help anthropomorphizing these things.
Re: Managing context on the Claude Developer Platform
#46I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…
They introduced removing from the end of the stack but not the beginning
Re: Managing context on the Claude Developer Platform
#47From what I can tell the new context editing and memory APIs are essentially formalization of common patterns: Context editing: Replace tool call results in message history (i.e replace a file output with an indicator that it’s no longer available). Memory: Give LLM access to read and write .md files like a virtual file system I feel like these formalizations of tools are on the path towards managing message history…
> managing message history on the server, which means better vendor lock in
I feel that managing context should be doable with a non-SOTA model even locally. Just need a way to select/deselect messages from the context manually say in Claude-CLI.
Re: Managing context on the Claude Developer Platform
#48I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…
Related, it feels like AI Studio is the only mainstream LLM frontend that treats you like an adult. Choose your own safety boundaries, modify the context & system prompt as you please, clear rate limits and pricing, etc. It's something you come to appreciate a lot, even if we are in the part of the cycle where Google's models aren't particularly SOTA rn
Not sure if msty counts as mainstream but it has so many quality of life enhancements it’s bonkers.
Re: Managing context on the Claude Developer Platform
#49I wish every instruction and response had a enable/disable checkbox so that I can disable parts of the conversation in such a way that it is excluded from the context. Let's say I submit or let it create a piece of code, and we're working on improving it. At some point I want to consider the piece of code to be significantly better that what I had initially, so all those initial interactions containing old code could…
I exit and restart CC all the time to get a “Fresh perspective on the universe as it now is”.
Re: Managing context on the Claude Developer Platform
#50Earlier quoted context omitted.
Related, it feels like AI Studio is the only mainstream LLM frontend that treats you like an adult. Choose your own safety boundaries, modify the context & system prompt as you please, clear rate limits and pricing, etc. It's something you come to appreciate a lot, even if we are in the part of the cycle where Google's models aren't particularly SOTA rn
How are they not SOTA? They're all very similar with ChatGPT being the worst (for my use case anyway). Like adding lambdas and random c++ function calls into my vulkan shaders.
Gemini 2.5 Pro is the most capable for my usecase in Pytorch as well. Large context and much better instruction following for code edits make a big difference.