cd /news/artificial-intelligence/experimenting-with-imperfect-llm-mem… · home topics artificial-intelligence article
[ARTICLE · art-136667] src=discuss.huggingface.co ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Experimenting with imperfect LLM memory

A project called SelMem is experimenting with imperfect LLM memory by storing each input in two forms: a sealed archive of the immutable original input used only for auditing and evaluation, and a mutable "lived memory" compressed representation the agent actually uses. Lived traces carry semantic content plus attributes including salience, affect, self-relevance, fidelity, access history and permanence, and can decay, become latent, merge, or be reconstructed differently on recall. Recall pairs retrieval with a grounding/judging layer that compares the reconstruction against the trace's semantic core, classifying outcomes as preservation, compression, elaboration, reframing, contradiction or unrelated recall, with repeated grounding failures able to trigger corrective reconsolidation.

read1 min views1 publishedSep 22, 2026

Long story short of what the repo does:

Instead of treating memory as immutable information storage, SelMem maintains mutable lived traces:

input → semantic segmentation → selective encoding → trace → recall/reconstruction → reconsolidation → forgetting/merging

Each input is stored in two forms:

sealed archive — immutable original input, used only for auditing/evaluation;

lived memory — compressed and mutable representation used by the agent.

Lived traces contain semantic content plus attributes such as salience, affect, self-relevance, fidelity, access history and permanence. Memories can decay, become latent, merge, or be reconstructed differently when recalled.

Recall uses retrieval to select memories, then a grounding/judging layer compares the reconstruction against the trace’s semantic core. It distinguishes cases such as preservation, compression, elaboration, reframing, contradiction and unrelated recall. Repeated grounding failures can trigger corrective reconsolidation

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @selmem 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/experimenting-with-i…] indexed:0 read:1min 2026-09-22 ·