Is this a significant problem? It seems like there are 15 solutions to every AI “text format” problem, but all are merely structure over feeding the AI informal English, structure which I believe the “transformer” model is specifically able to strip to a common form (which is how training it on the entire internet worked).

AI does benefit from learning to use skills, and being instructed with good structures (like “save [specific important kind of detail] in memories” and “plan before implementing anything”). But none of these memory solutions seem better than any other, they’re basically just different folders. Your CLAUDE.md can say “see AGENTS.md” and AGENTS.md can say “write memories to .agent/memories/“, and I’d be interested in a measurement, but I assume it performs almost the exact same as native CLAUDE.md and .claude/memories.

One thing I’ve noticed AI does much better than me, is not have OCD over the “perfect” solution.

▲

bee_rider a day ago | parent | next [-]

As someone not involved in AI development, it seems really surprising that memories are another text-format issue. Seems like (in a human analogy) something more equivalent to your notebook or scratchpad.

Memories are lossy things that live in our brains, I’d expect they to be stored in some native LLM encoded representation (which would make the lack of standardization understandable).

This probably seems like a dumb distinction, but I think some of the problems in the article come from calling these things memories. Like, the prompt injection/provenience issue. The model has received some notes from someone about a topic, if it they were treated as “notes from <whoever sent them> about <topic>” instead of “my memories about <topic>” that should put things on the right footing to start at least, right?

▲

wongarsu 19 hours ago | parent [-]

The issue with storing the memories in some encoded representation (e.g. in embedding space) is that this would turn that representation into something that has to be supported "forever". I have projects that I have worked on with Opus 4.6, 4.7, 4.8, 5, 5.5, as well as Fable 5 and 5.1, and obvious some Sonnet subagents along the way. And I expect to keep working on the same codebase when Opus 6 and Opus 7 release. Text is trivially compatible with all of those, but their embeddings all differ. And whatever other representation you come up with right now in Opus 5.5 might no longer make sense in the model architecture of Opus 7

Imho the interesting challenges with memory are about "what does this memory belong to" (attaching it to lines of code or similar), "what does it relate to" (webs of memories), "is this even still true" ("sleeping", "reconciliation", etc). But there's no real consensus what is even useful to handle, never mind how to handle it

	▲	sebastienburel 7 hours ago \| parent [-]
		[dead]

▲

reactordev a day ago | parent | prev | next [-]

This is what happens when you treat the LLM as a black box, you end up building the same stuff around it. Like trying to make your dog understand your intentions. You can train it to do tricks and it recognizes specific reward patterns but most dogs have no idea what you’re saying beyond basic triggers.

▲

soraminazuki a day ago | parent [-]

It's sad what software engineering has been reduced to for a lot of people. It's basically pickup artists compiling a list of "body languages" for LLMs, pretending as if there's science behind any of their interpretations.

▲

yladiz a day ago | parent | next [-]

At least body language has some studies put into understanding it.

▲

soraminazuki a day ago | parent [-]

That may be so, but most "body language tips" circulated online are cringey and lack the rigor and nuance of proper scientific studies. I think of human reactions as more complex than what those kinds of online materials imply.

It's even worse when applied to LLMs, which are more unpredictable.

▲

ares623 21 hours ago | parent [-]

At the very least the pick up artists have a common baseline in that they are also human.

	▲	reactordev 20 hours ago \| parent [-]
		And LLMs have a common baseline in that they produce tokens. The comparison is apt. Both fields should be studied. Body language and Prompt Language.

▲

alberto467 21 hours ago | parent | prev | next [-]

People had this grand idea of software engineering and how much complex it is and problem solving and this and that and you actually deserve 250k to do your “complex” job.

In reality many of them have not needed to look at a data structure or do any real computer science for years. They were just attending bullshit meetings and approving some pr with some basic sql query or some new react code.

Common people knew very little about computers and so they thought they were running on magic and that the software engineers were the magicians.

	▲	soraminazuki 20 hours ago \| parent [-]
		Can't we just appreciate computer science, or any other field of study, for what it is? It's unfortunate that so many people now treat the fundamentals underpinning our whole profession as a nuisance to be left for LLMs, or resume padding.

▲

esafak 21 hours ago | parent | prev [-]

That's what 'democratization' looks like. Everybody's an AI engineer now!

▲

Tejush a day ago | parent | prev | next [-]

Honestly I have just a few lines in claude.md. And one of them is treat agents.md as the main file and update skills in the .agents folder and use it as source of your skills. Its working so far.

▲

jase_jase 16 hours ago | parent | prev [-]

[flagged]