Tencent's Hy Memory Is Only as Good as the LLM That Writes It. I Measured It on LongMemEval

Description and use

<p>Tencent released Hy Memory 2.0 this week: an open framework (Apache-2.0), a 30B memory model and MemHub, an app that shares one memory across AI tools. I build something in the same space, so I wanted to know how it does on the two failures I care most about:</p> <ol> <li> <strong>Answering with an outdated version</strong> of a fact that has since changed.</li> <li> <strong>Forgetting who said what</strong>, especially what the assistant itself said.</li> </ol> <p><em>Disclosure: I'm the author of <a href="https://github.com/teolex2020/aura-memory" rel="noopener noreferrer">Aura</a>, an op

Problem

<p>Tencent released Hy Memory 2.0 this week: an open framework (Apache-2.0), a 30B memory model and MemHub, an app that shares one memory across AI tools. I build something in the same space, so I wanted to know how it does on the two failures I care most about:</p> <ol> <li> <strong>Answering with an outdated version</strong> of a fact that has since changed.</li> <li> <strong>Forgetting who said what</strong>, especially what the assistant itself said.</li> </ol> <p><em>Disclosure: I'm the author of <a href="https://github.com/teolex2020/aura-memory" rel="noopener noreferrer">Aura</a>, an op

Outcome

<p>Tencent released Hy Memory 2.0 this week: an open framework (Apache-2.0), a 30B memory model and MemHub, an app that shares one memory across AI tools. I build something in the same space, so I wanted to know how it does on the two failures I care most about:</p> <ol> <li> <strong>Answering with an outdated version</strong> of a fact that has since changed.</li> <li> <strong>Forgetting who said what</strong>, especially what the assistant itself said.</li> </ol> <p><em>Disclosure: I'm the author of <a href="https://github.com/teolex2020/aura-memory" rel="noopener noreferrer">Aura</a>, an op

Evidence

Tencent's Hy Memory Is Only as Good as the LLM That Writes It. I Measured It on LongMemEval

Source