The idea of Claude having "anterograde amnesia" and the top-rated comment there by Noosphere89 really resonated with me:

  "I would analogize this to a human with anterograde amnesia, who cannot form new memories, and who is constantly writing notes to keep track of their life. The limitations here are obvious, and these are limitations future Claudes will probably share unless LLM memory/continual learning is solved in a better way."

  This is an extremely underrated comparison, TBH. Indeed, I'd argue that frozen weights + lack of a long-term memory are easily one of the biggest reasons why LLMs are much more impressive than useful at a lot of tasks (with reliability being another big, independent issue).

  It emphasizes 2 things that are both true at once: LLMs do in fact reason like humans and can have (poor-quality) world-models, and there's no fundamental chasm between LLM capabilities and human capabilities that can't be cured by unlimited resources/time, and yet just as humans with anterograde amnesia are usually much less employable/useful to others than people who do have long-term memory, current AIs are much, much less employable/useful than future paradigm AIs.

▲ skybrian 8 hours ago | parent [-]

For a coding agent, the project "learns" as you improve its onboarding docs (AGENTS.md), code, and tests. If you assume you're going to start a new conversation for each task and the LLM is a temp that's going to start from scratch, you'll have a better time.

▲

stingraycharles an hour ago | parent | next [-]

But these docs are the notes, it constantly needs to be re-primed with them, an approach which doesn’t scale. How much of this knowledge can you really put in these agent docs? There's only so much you can do, and for any serious-scale projects, there's SO much knowledge that needs to be captured. Not just "do this, do that", but also context about why certain decisions were made (rationale, business context, etc).

It is exactly akin to a human that has to write down everything on notes, and re-read them every time.

▲

falcor84 8 hours ago | parent | prev | next [-]

But that's the thing: Claude Plays Pokemon is an experiment in having Claude work fully independently, so there's no "you" who would improve its onboarding docs or anything else, it has to do so on its own. And as long as it cannot do so reliably, it effectively has anterograde amnesia.

And just to be clear, I'm mentioning this because I think that Claude Plays Pokemon is a playground for any agentic AI doing any sort of long-term independent work; I believe that the solution needed here is going to bring us closer to a fully independent agent in coding and other domains. It reminds me of the codeclash.ai benchmark, where similar issues are seen across multiple "rounds" of an AI working on the same codebase.

	▲	skybrian 6 hours ago \| parent [-]
		Sure, it's not close to fully independent. But I was interpreting "much, much less employable" as not very useful for programming in its current state, and I think it is quite useful.

▲

BoredPositron 20 minutes ago | parent | prev | next [-]

It does not learn. It has to look at the files over and over again. If or the agent forgets to look at them it has 0 knowledge about what it did.

▲

kaashif 8 hours ago | parent | prev [-]

Yeah but it feels terrible. I put as much as I can into Claude skills and CLAUDE.md but the fact that this is something I even have to think about makes me sad. The discrete points where the context gets compacted really feel bad and not like how I think AGI or whatever should work.

Just continuously learn and have a super duper massive memory. Maybe I just need a bazillion GPUs to myself to get that.

But no-one wants to manage context all the time, it's incidental complexity.

	▲	falcor84 8 hours ago \| parent \| next [-]
		I agree with essentially everything you said, except for the final claim that managing context is incidental complexity. From what I know of cognitive science, I would argue that context management is a central facet of intelligence, and a lot of the success of humans in society is dependent on their ability to do so. Looking at it from the other side, executive function disorders such as ADHD offer significant challenges for many humans, and they seem to be not quite entirely unlike these context issues that Claude faces.
	▲	onion2k 4 hours ago \| parent \| prev [-]
		no-one wants to manage context all the time Maybe we'll start needing to have daily stand-ups with our coding agents.