I love how you approached this with markdown !
I guess the markdown approach really has a advantage over others.
PS : Something I built on markdown : https://voiden.md/
Show HN: Continual Learning with .md
11–20 of 39 posts
Re: Show HN: Continual Learning with .md
#12[flagged]
[dead]
Re: Show HN: Continual Learning with .md
#13[flagged]
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 everything is being retrieved. The agent can selectively explore subsets of the tree (plus you can edit the exploration policy by yourself).
Since there is no context bloat, it is quite forgivable to just write things down.
Re: Show HN: Continual Learning with .md
#14I've seen a lot of such systems come and go. One of my friends is working on probably the best (VC-funded) memory system right now. The problem always is that when there are too many memories, the context gets overloaded and the AI starts ignoring the system prompt. Definitely not a solved problem, and there need to be benchmarks to evaluate these solutions. Benchmarks themselves can be easily gamed and not universal…
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 benchmark is definitely the core bottleneck. I don't know any good benchmark for this, probably an open research question in itself.
Re: Show HN: Continual Learning with .md
#15I've seen a lot of such systems come and go. One of my friends is working on probably the best (VC-funded) memory system right now. The problem always is that when there are too many memories, the context gets overloaded and the AI starts ignoring the system prompt. Definitely not a solved problem, and there need to be benchmarks to evaluate these solutions. Benchmarks themselves can be easily gamed and not universal…
The armchair ML engineer in me says our current context management approach is the issue. With a proper memory management system wired up to it’s own LLM-driven orchestrator, memories should be pulled in and pushed out between prompts, and ideally, in the middle of a “thinking” cycle. You can enhance this to be performant using vector databases and such but the core principle remains the same and is oft repeated by p…
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 responds. But that is more of a model behaviour (adjustable through prompting) rather than an architectural limitation.
Re: Show HN: Continual Learning with .md
#16Earlier quoted context omitted.
The armchair ML engineer in me says our current context management approach is the issue. With a proper memory management system wired up to it’s own LLM-driven orchestrator, memories should be pulled in and pushed out between prompts, and ideally, in the middle of a “thinking” cycle. You can enhance this to be performant using vector databases and such but the core principle remains the same and is oft repeated by p…
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 responds. But that is more of a model behaviour (adjustable through prompting) rather than an architectural limitation.
Ah, I mean bi-directional management of context. Add and remove. Basically just the remove bit since we have adding down.
Re: Show HN: Continual Learning with .md
#17I love how you approached this with markdown ! I guess the markdown approach really has a advantage over others. PS : Something I built on markdown : https://voiden.md/
Yep. Markdown is the future :-)
Re: Show HN: Continual Learning with .md
#18I really like the simplicity of this! What's retrieval performance and speed like?
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 model.
Haven't done a formal benchmark, but from the vibes, it feels like a few seconds for GPT-5.4-high per query.
There is an implicit "caching" mechanism, so the more you use it, the smoother it will feel.
Re: Show HN: Continual Learning with .md
#19Earlier quoted context omitted.
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 responds. But that is more of a model behaviour (adjustable through prompting) rather than an architectural limitation.
Ah, I mean bi-directional management of context. Add and remove. Basically just the remove bit since we have adding down.
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 each day, then newer abstractions can form, while irrelevant gets pruned/edited. That's the beauty of the architecture, you define how the update can occur!
But if you do have a new memory (possibly contradicting an old one), is it really a good idea to prune/edit it?
If you are genuinely uncertain between choice A and B, then having them both exist in the memory archive might be a feature. The agent gets the possibility of seeing contradictory evidence on different dates, which communicates indecisiveness.
Re: Show HN: Continual Learning with .md
#20[flagged]
This assumes that the model's behavior and memories are faithful to their english/human language representation, and don't stray into (even subtle) "neuralese".
Having run a Markdown memory system with Claude for over a year, I don't think I've seen any evidence of neuralese. That's even with Claude being regularly encouraged to write "reflections" on each session, including automated sessions, and weekly summaries of those reflections.
The bigger problem is avoiding what I call the Memento Effect. I won't spoil the movie for anyone, but Memento involves a character who cannot make new memories, so he has to take meticulous notes about everything. But if any of those notes are vague or incorrect, they still get accept as truth when next reviewed. So you really need your Markdown memory to be pristine and mustn't allow it to become polluted.