AI · Article
Memorilla Gives Frozen AI Models Long-Term Memory Without Retraining
GeekNews ·
At a glance
Memorilla stores many documents ahead of time as compact number sets and passes only the parts needed for each question to an AI. The AI model itself stays unchanged. It scored highest on average in tests of personalization, long-text understanding, and knowledge questions.
Key points
- Documents are converted once and stored, and each question pulls 16 pieces of relevant content.
- Answers come much faster than when the full documents are fed in, dropping from 19.9 seconds to 0.74 seconds for 512 documents.
- In a game test, remembering past experience reduced repeated wandering and raised success from 18.6% to 24.2%.
Why it matters
For AI to remember long conversations or documents while answering quickly and cheaply, this kind of memory approach is needed. The article shows one way to add memory to an existing AI without changing it.
Original source
Memorilla: LLM을 위한 잠재 의미 메모리
GeekNews · Nov 8, 14:38 KST
Read on GeekNews ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to GeekNews.
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST