151–160 of 168 posts
The top of my ~/.claude/CLAUDE.md: > Don't turn a one-off or area-specific comment into a durable memory without my explicit confirmation. You have a history of over-indexing on one-offs, and those memories end up getting cited to override well-tuned skills.
Does that second sentence provide value beyond getting that off your chest? ;-) (Semi-serious question)
I remember when OpenAI announced ChatGPT now will remember stuff between sessions. Oh, you mean find random trivia about me and copy paste it between prompts without out my explicit consent. ”compare these three cars. Oh btw I am a data engineer, and my moms maiden name is Joana, and I am allergic to bad poetry. And code should be DRY, I prefer SQL over Python and what’s the most poisonous flower in Scandinavia?”. I’…
>We have found zero performance benefit on SWE tasks when agents have search access to their previous transcript sessions I refuse to believe this is true. The ability for an agent to find information from before a compaction is incredibly useful. At compaction time it's impossible to know what exactly may be still needed.
With the million-context-window models we never hit compaction, observed over hundreds of sessions. What are you doing that has you hitting compaction regularly?
Million context models also are still not effective for the entire context size.
Earlier quoted context omitted.
> Of course the house must pass safety inspections and stuff, but the materials and techniques don’t matter one bit for that. All that matters is you achieve the desired outcome, and I will ignore the glaring fact that you achieve the desired outcome by using the right materials and techniques. This analogy is more true than you think. This is why modern homes/appartments are trash. You can pass safety inspections us…
You are aware that you can just pay more money and get a higher quality house and higher quality shoes, right? Costs of those things have gone down over time. The high end still exists, you just don't actually care about quality as much as you think you do. And yes, for capital-intensive things like real estate development, fast/cheap matters a lot because otherwise there would be no capital available to build any of…
False. You can pay more money for branding that purports to be higher quality. The Running shoe market is a perfect example. Best shoes I ever bought were Altra Loan Peaks from 2018, brand has been getting more expensive and lower quality every year. Whether that extra cost actually translates to quality require diligent research.
I like the memory system, in general. For reference I'm using mostly Opus 4.8 + Max effort. It will often pull things out of memory that are relevant. Like I'll ask it to come up with a few options I should consider for, say, a self-hosted OIDC provider and it'll say things like "Considering the size of your operations team, this might be a better fit because of X and Y". Now, I'll agree that this is probably the sor…
There's also a noticable hierarchy to such context that needs to be correctly modeled - you could for example be involved with multiple teams of different sizes that are subject to different rules which is something a human would understand naturally.
Earlier quoted context omitted.
A) Context and prompting cuts the search space for next token generation. That’s pretty useful, as you mentioned. B) The other use of context is that it introduces entirely new information via RAG B will never go away (as others pointed out). A, well that’s just something we’re all going to keep getting surprised at. We’ll barely give it any direction or context and the newer models will simply find the happy path. T…
>Chain of reasoning is a lot of context to guide token generation, but we simply see that newer models don’t need that context to get to the answer I thought each new generation typically used more reasoning tokens?
It’s on by default, in a way. You can probably prompt these models with “and don’t reason about it, just give me the answer” and probably get a comparably good response without it using reasoning tokens for many things.
I don't actually want Claude to have those memories, but they often point to gaps in my harness. I'll occasionally sweep the memories, pick out what should go into the harness or CLAUDE.md, then delete the memories.
I remember when OpenAI announced ChatGPT now will remember stuff between sessions. Oh, you mean find random trivia about me and copy paste it between prompts without out my explicit consent. ”compare these three cars. Oh btw I am a data engineer, and my moms maiden name is Joana, and I am allergic to bad poetry. And code should be DRY, I prefer SQL over Python and what’s the most poisonous flower in Scandinavia?”. I’…
I have to imagine these types of features are for people who treat chatgpt like their friend/therapist/girlfriend/assistant/... instead of people who use it to answer questions
I mean I know the draw, it's just so easy to get suckered into it... After all, it's usually mostly correct! And since the Advent of llms searching via Google has gotten essentially impossible with 1000 slop articles per one genuine article... But the danger is real, even with eg fable
Strongly agree here. claude-code’s memory system is occasionally useful but much more often harmful, pulling in obsolete info that muddies the waters about current tasks. I’ve frequently seen Claude’s own memories severely mislead it. My guess is that has something to do with the training process leaving models unable to differentiate between “what’s happening now” and “what happened before”. Perhaps if making infere…
Training with memory is an interesting idea...
Strongly agree here. claude-code’s memory system is occasionally useful but much more often harmful, pulling in obsolete info that muddies the waters about current tasks. I’ve frequently seen Claude’s own memories severely mislead it. My guess is that has something to do with the training process leaving models unable to differentiate between “what’s happening now” and “what happened before”. Perhaps if making infere…
Pretty annoying when it brings those up again later from memory...