{"podcast":{"title":"Tech Stories Tech Brief By HackerNoon","slug":"tech-stories-tech-brief-by-hackernoon-6365648","podcast_index_feed_id":6365648,"rss_url":"https://feeds.transistor.fm/tech-stories-tech-brief-by-hackernoon","website_url":"https://hackernoon.com/c/tech-stories","image_url":"https://img.transistorcdn.com/P-42oHG33sV1aPenbVg2DrwaV5AQtWp46GJ4Bp_EP-s/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxNDI5LzE2ODM1/ODM0NjQtYXJ0d29y/ay5qcGc.jpg","author":"HackerNoon","episode_count":100,"summary":"Learn the latest tech-stories updates in the tech world.","last_synced_at":"2026-07-30T06:17:37.489609+00:00","page_url":"https://stenobird.com/podcast/tech-stories-tech-brief-by-hackernoon-6365648"},"episode":{"title":"Experimental Results from a Self-Improving Retrieval System for Conversational Memory","slug":"experimental-results-from-a-self-improving-retrieval-system-for-conversational-memory","published_at":"2026-05-08T16:01:06+00:00","page_url":"https://stenobird.com/podcast/tech-stories-tech-brief-by-hackernoon-6365648/experimental-results-from-a-self-improving-retrieval-system-for-conversational-memory","show_page_url":"https://stenobird.com/podcast/tech-stories-tech-brief-by-hackernoon-6365648","url":"https://share.transistor.fm/s/3ad0c965","audio_url":"https://media.transistor.fm/3ad0c965/5686e04d.mp3","summary":"This story was originally published on HackerNoon at: https://hackernoon.com/experimental-results-from-a-self-improving-retrieval-system-for-conversational-memory . Eighteen retrieval experiments on agent memory: why BM25 dominates, what clustered retrieval-induced forgetting actually does, and the Rust port that shipped. Check more stories related to tech-stories at: https://hackernoon.com/c/tech-stories . You can also check exclusive content about #agent-memory , #rag , #bm25 , #retrieval-systems , #cross-encoder-reranking , #longmemeval , #faiss , #hackernoon-top-story , and more. This story was written by: @teimurjan . Learn more about this writer by checking @teimurjan's about page, and for more stories, please visit hackernoon.com . The biology-inspired mutation layer didn't work. A learned MLP adapter and segmentation mutation both produced ~zero NDCG lift on LongMemEval. The control loop was sound; the perturbations weren't load-bearing. A recall diagnostic reframed the project: 78% of relevant entries never reached the cross-encoder. Bi-encoder recall was the ceiling, not the mutation layer. Standard IR wins compounded: 0.95-cosine dedup plus BM25 alongside vector plus cross-encoder rerank took NDCG@10 from 0.22 to 0.34. BM25 alone beat pretrained embeddings by 76% on this corpus. Clustered retrieval-induced forgetting (Anderson 1994, ported as far as I can tell for the first time) added +1.9pp NDCG with p=0.0001 on LongMemEval. Regresses on NFCorpus: the mechanism is scoped to single-user long-term conversation memory, not general IR. Write-time LLM enrichment (gist plus anticipated queries via Haiku) was the biggest single lever: +8.3pp NDCG on covered queries. A regex-tokenizer fix that BM25 had been missing was worth +1.4pp NDCG on the headline benchmark.…","meta_description":"This story was originally published on HackerNoon at: https://hackernoon.com/experimental-results-from-a-self-improving-retrieval-system-for-conversationa…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2671,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/tech-stories-tech-brief-by-hackernoon-6365648/episodes/experimental-results-from-a-self-improving-retrieval-system-for-conversational-memory/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/tech-stories-tech-brief-by-hackernoon-6365648/experimental-results-from-a-self-improving-retrieval-system-for-conversational-memory.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}