Agents need continual learning. At supermemory, we are doubling down and pushing the frontier for memory and in-context learning, for every agent and use case. Introducing 𝚕𝚎𝚊𝚛𝚗𝚎𝚛-𝟷

so what actually is learner-1

You can use supermemory to power your agents, today:

if the "learning" is just dynamically injecting better tokens into ctx, that’s still retrieval imo. interested to see what learner-1 is actually changing

This is vague af, "continual learning" okey awesome "injecting tokens in context memory", it is markdown memory files again is it?, please...

this is confusing. injecting tokens into model's context in real time ain't continual learning. how do you actually do it then? and ICL has been there since the inception of agent memory field.

Great work. You're finally learn-1 something

Cool stuff, but I think you guys need a better microphone.

What is "in-context" learning here? Do you mean continually updating the input fed into the LLM?

When it comes to injecting tokens into the context windows, what is the difference between learner-1 and what supermemory already does?

This is super cool. Congrats guys!!

congrats!! looks awesome

oh shit

Building something similar :)

Sadly memory will not be solved by context injection or ranking algorithms, it'll be an active process turning traces into standardized guides. Take from this what you will ;)

Isn’t that what the supermemory plugin does ??

wooooo!! congrats guys!

Continual learning also means continual writing: every fact an agent carries into tomorrow was taught to it by something it read today. That makes memory the persistence layer for prompt injection - a poisoned 'fact' survives the session it arrived in. Memory writes need provenance and review, not just storage.

this is amazing 🔥🔥

ok learner-1 sounds interesting, what does it actually do

holy larp

crazyyyyy stufff

W

Memory is the very core and basic part of any AI agents. Just like chips, just after the chips or hardware, memory is really important, and just after that, alignment comes.

The hard part after “agents can remember” is probably deciding what they should forget. Persistent memory gets much more useful when it has confidence, recency, deduping and expiry otherwise agents just accumulate stale context. Memory quality may matter more than memory size.

I do this manually. Rewrite the rules after every failed session and the next one goes better. But the agent itself starts blank every time.

@grok apa ini?

Why is supermemory not working?

Continual learning matters when agent memory improves decisions without bloating prompts.

Memory is useful, but agents learning from what happened last time is the real leap. How does learner-1 handle conflicting lessons over time?

continual learning is the only way agents stop forgetting yesterday's context. practical memory beats flashy in-context tricks every time

is it really continual learning tho??

Just like we learn from our daily mistakes, learner-1 helps agents grow, and I am so proud of you @0xndra for making this happen.

Continual learning's hardest failure mode isn't catastrophic forgetting, it's your agent confidently acting on a memory that was accurate 3 weeks ago. Staleness detection never makes it into the agent demos.

continual learning is a meaningless term, especially in this context. but hey I guess marketing hype helps you shill your product.