I built ChatGPT's memory system into Apple's LLM
@stevenzhang1.2万 位关注者
120,124 次观看
24 条评论
评论来自 X (Twitter) 上的原帖

@sanchitmonga22
Checkout @RunAnywhereAI we support Apple foundation models and other inference engines, and also bringing support for embeddings
9 个赞

@hinrichbo
Hey man I built a similar app but for llms via openrouter and with council mode. Would love to connect!
7 个赞

@0xsahilsangwan
Very cool Steve. Not sure what you mean by apple’s llm though ? Is this an open source model or something Apple is already shipping in its devices ?
5 个赞

@stevenzhang
it’s a low parameter model that’s available in iOS 26
8 个赞

@stevegraham
Nice work man. I think @therealdaneel wants an orange McLaren too!
2 个赞

@stevenzhang
@therealdaneel let’s see who can get one first
2 个赞

@EgoSumBanditos
Great job !
1 个赞

@JeffreyArt1
Very cool
1 个赞

@Mrmemehead
@LocallyAIApp should get this
1 个赞

@InderosD
Ohh that's cool How do I try this?
1 个赞

@josue_gdm
wait this is fire
1 个赞

@tommaxxing
have you tried any of the memory benchmarks?
1 个赞

@ckarani7
would love to try it out
1 个赞

@imjustinliao
Wow niche, I’d love to try
1 个赞

@blockchainlenny
cool demo - digging the lightweight summaries for on-device personalization. keeps ai snappy without rag. just followed - let's connect! 🙃🤝

@enzoenrico
wait, how did you manage to make it so the model remembers stuff past its (very low) context window?

@kayacancode
share the github

@applegrifter
You can just do things

@GodfreyO_
what would be some usecases for the model? Is it just a free llm app?

@SambitBiswas
@rudrank you should have look at this!



