Subj : Startup backed by Dropbox and Figma debuts breakthrough tech that
To   : All
From : TechnologyDaily
Date : Tue Jun 18 2024 08:00:06

Startup backed by Dropbox and Figma debuts breakthrough tech that could solve 
one of the biggest AI problems  AMD's BFF Lamini promises to cut 
hallucinations by 90% using mindmap-like process

Date:
Tue, 18 Jun 2024 06:50:28 +0000

Description:
Lamini Memory Tuning embeds exact facts into LLMs, cutting the problem of 
hallucinations by 90%.

FULL STORY
======================================================================

Anyone who has used generative AI for any length of time will be more than 
familiar with hallucinations. These are when AI systems generate false or 
misleading information, a flaw often rooted in limitations within their 
training data or model design. Such inaccuracies can emerge unpredictably and 
vary widely in their severity - from minor errors to substantial distortions 
that could significantly skew decision-making processes. 

Lamini Memory Tuning aims to significantly reduce hallucinations, from 50% to 
5%, a 90% cut. The technology enables the embedding of exact facts into LLMs, 
reportedly achieving accuracy rates up to 95%, a significant leap from the 
50% accuracy offered by previous methods. 

By specifically tuning millions of expert adapters, such as LoRAs (Low-Rank 
Adaptions) on any open-source LLM, Lamini Memory Tuning ensures precise fact 
retention, ranging from historical events to complex technical data, without 
the high latency and cost typically associated with such precision. Mixture 
of Memory Experts 

This method, inspired by mind mapping, selectively activates the most 
relevant experts from an index during inference, dramatically reducing 
unnecessary computations. 

As an example, the company says when tasked with recalling specific facts 
about the Roman Empire, the system pulls only the necessary information about 
Julius Caesar, aqueducts, or legions, avoiding the activation of irrelevant 
model weights. 

The underlying technology behind Lamini Memory Tuning involves a sparse 
activation framework known as a Mixture of Memory Experts (MoME), which 
scales to support a vast number of facts limited only by training data size. 
Lamini says this approach not only enhances model responsiveness but also 
significantly cuts down on computational demands, making it a viable solution 
for enhancing the performance of LLMs across various applications. More from 
TechRadar Pro AI LLM provider bets barn on mature AMD Instinct MI GPU 
Snowflake has a new LLM targeted at ticking off boring business tasks The 
secret to success: implementing an effective AI roadmap



======================================================================
Link to news story:
https://www.techradar.com/pro/startup-backed-by-dropbox-and-figma-debuts-break
through-tech-that-could-solve-one-of-the-biggest-ai-problems-amds-bff-lamini-p
romises-to-cut-hallucinations-by-90-using-mindmap-like-process


--- Mystic BBS v1.12 A47 (Linux/64)
 * Origin: tqwNet Technology News (1337:1/100)

.