Viewing profile — wenhan_zhou

Yep. Or even better, compact after a random number of turns. The model must then learn to preserve useful context at arbitrary context lengths.

If understanding emerges from pre-training, then perhaps memory is what emerges from post-training.

Currently working on a benchmark!

Ah, so you are effectively offloading the file exploration mechanism to the INDEX.md in the sub-directories rather than writing a complex prompt?

How does the agent intelligently synthesize information across different files?

In theory, yes. Although the privacy setting says otherwise. But in the end, it doesn't really matter; it is public on GitHub, so anyone can use it.

I just read LLM Wiki in more detail. I have heard about it second-hand before this project. The "no-code" idea was inspired by Karpathy. As I have understood it, in LLM Wiki, the h…

Although I have been working on memory before, ReadMe is very fresh. The moment I saw it running, I published it. So, no continuous running nor LLM ablation studies. Treat it as an…

I think what's missing is a benchmark that measures how well the memories contribute to future interactions.

I don't remember such details, but as you suggest, it is a healthy kind of compression. I address it through merging the lower-level memories into more abstracted ones through a te…

I see your point. A removal mechanism is not (yet) implemented. But in principle, we could adjust the instructions in Update.md so that it does a minor "refactor" of the filesystem…

Minimalism is my design philosophy :-) Good question. Since it is just an LLM reading files, it depends entirely on how fast it can call tools, so it depends on the token/s of the …

Yep. Markdown is the future :-)

Fair concern. ReadMe does support loading memories mid-reasoning! It is simply an agent reading files. Although GPT-5.4 currently likes to explore a lot upfront, and only then resp…

Context bloat is real, but the architecture has the potential to solve it. You need clever naming for the filesystem and exploration policy in AGENTS.md. (not trivial!) The benchma…

The editability is surely an underrated advantage, both for the program itself and the memories it generated. I think in terms of noise, it is less problematic here because not eve…

I have a proposal that addresses long-term memory problems for LLMs when new data arrives continuously (cheaply!). The program involves no code, but two Markdown files. For retriev…