Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I built ChatGPT's memory system into Apple's LLM

stevenzhang's profile picture

Steven Zhang

11,562 subscribers

120,124 Aufrufe • vor 10 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

24 Kommentare

Profilbild von Sanchit monga
Sanchit mongavor 10 Monaten

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

Profilbild von hinzi
hinzivor 10 Monaten

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

Profilbild von Sahil
Sahilvor 10 Monaten

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 ?

Profilbild von Steven Zhang
Steven Zhangvor 10 Monaten

it’s a low parameter model that’s available in iOS 26

Profilbild von Stevie Graham (new account)
Stevie Graham (new account)vor 10 Monaten

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

Profilbild von Steven Zhang
Steven Zhangvor 10 Monaten

@therealdaneel let’s see who can get one first

Profilbild von Ego Sum Banditos
Ego Sum Banditosvor 10 Monaten

Great job !

Profilbild von Jeff
Jeffvor 10 Monaten

Very cool

Profilbild von Prasanna
Prasannavor 10 Monaten

@LocallyAIApp should get this

Profilbild von Daniel
Danielvor 10 Monaten

Ohh that's cool How do I try this?

Profilbild von Josué Gdm
Josué Gdmvor 10 Monaten

wait this is fire

Profilbild von toma
tomavor 10 Monaten

have you tried any of the memory benchmarks?

Profilbild von Christopher Karani
Christopher Karanivor 10 Monaten

would love to try it out

Profilbild von Justin Liao
Justin Liaovor 10 Monaten

Wow niche, I’d love to try

Profilbild von lenny 🥷
lenny 🥷vor 9 Monaten

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

Profilbild von enzo enrico
enzo enricovor 10 Monaten

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

Profilbild von Kaya Jones
Kaya Jonesvor 10 Monaten

share the github

Profilbild von LMD
LMDvor 10 Monaten

You can just do things

Profilbild von Godfrey.Builds
Godfrey.Buildsvor 10 Monaten

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

Profilbild von Sambit
Sambitvor 10 Monaten

@rudrank you should have look at this!

Profilbild von Ron Adin
Ron Adinvor 10 Monaten

this is good! pls see dm

Profilbild von mscode07
mscode07vor 10 Monaten

Sounds interesting

Profilbild von Yan-David (Yanda) Erlich
Yan-David (Yanda) Erlichvor 10 Monaten

👀😍

Profilbild von Mher
Mhervor 10 Monaten

Is this using an on-device LLM provided by Apple?

Ähnliche Videos

I turned my iPad into Tom Riddle’s diary with Apple’s new Foundation Models, an LLM built into iOS. It’s lightning fast!
0:34

I turned my iPad into Tom Riddle’s diary with Apple’s new Foundation Models, an LLM built into iOS. It’s lightning fast!

Ethan Saadia @ SIGGRAPH

330,886 Aufrufe • vor 1 Jahr

Holy shit... One month before Andrej Karpathy dropped the “LLM Wiki” idea… someone had already built it. Not theory. Not hype. A working system. LLMs today restart from zero every time. No memory. No evolution. No learning. That’s broken. Most people use CLAUDE.md / AGENTS.md → Manual updates → Easy to forget → Knowledge gets lost That’s not intelligence. That’s a notepad. So I built dynamic memory for LLMs: • Learns automatically • Stores without manual effort • Weakens irrelevant data over time • Strengthens what actually matters Before the “LLM Wiki” idea went viral, this already had: • Brain-like decay/boost memory • Smart deduplication (no noise) • Experience tracking per tech • Cross-referenced knowledge graph • Loss-proof backups • Auto-grouped tool sessions Then I added: • memory_audit (clean + optimize memory) • Memory injection directly into tools Now this isn’t just a concept. It’s a live system that turns LLMs from stateless tools → evolving intelligence. Using it daily: → ~5K tokens → Zero manual work → Memory that actually compounds Link in comments. RT & Bookmark — this will be standard soon.
0:32

Holy shit... One month before Andrej Karpathy dropped the “LLM Wiki” idea… someone had already built it. Not theory. Not hype. A working system. LLMs today restart from zero every time. No memory. No evolution. No learning. That’s broken. Most people use CLAUDE.md / AGENTS.md → Manual updates → Easy to forget → Knowledge gets lost That’s not intelligence. That’s a notepad. So I built dynamic memory for LLMs: • Learns automatically • Stores without manual effort • Weakens irrelevant data over time • Strengthens what actually matters Before the “LLM Wiki” idea went viral, this already had: • Brain-like decay/boost memory • Smart deduplication (no noise) • Experience tracking per tech • Cross-referenced knowledge graph • Loss-proof backups • Auto-grouped tool sessions Then I added: • memory_audit (clean + optimize memory) • Memory injection directly into tools Now this isn’t just a concept. It’s a live system that turns LLMs from stateless tools → evolving intelligence. Using it daily: → ~5K tokens → Zero manual work → Memory that actually compounds Link in comments. RT & Bookmark — this will be standard soon.

Nainsi Dwivedi

15,814 Aufrufe • vor 6 Monaten

How to hack apple's emoji system:
0:23

Sensitive content

How to hack apple's emoji system:

AlphaFox

4,391,876 Aufrufe • vor 1 Jahr

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.
36:05

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

Noisy

25,571 Aufrufe • vor 1 Monat

I built an LLM from scratch. Here's everything I learned along the way.
1:54

I built an LLM from scratch. Here's everything I learned along the way.

CJ (Coding Garden)

258,519 Aufrufe • vor 3 Monaten

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕
0:28

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕

Pietro Schirano

120,827 Aufrufe • vor 2 Jahren

He is a 1st year AI engineering student at Stanford - and already launched an automated system making $2.1M a year: 00:20 - how Anthropic engineers make millions with LLM and Transformers 38:34 - In-Context Learning makes AI smarter for free 59:47 - 1st year student made $2.1M using LLM from scratch after watching I gave LLM the idea I had been holding in my head for 3 years - it built it in one evening. save & watch - the article below is a step by step guide to build your automated LLM system.
1:16:48

He is a 1st year AI engineering student at Stanford - and already launched an automated system making $2.1M a year: 00:20 - how Anthropic engineers make millions with LLM and Transformers 38:34 - In-Context Learning makes AI smarter for free 59:47 - 1st year student made $2.1M using LLM from scratch after watching I gave LLM the idea I had been holding in my head for 3 years - it built it in one evening. save & watch - the article below is a step by step guide to build your automated LLM system.

Noisy

43,713 Aufrufe • vor 3 Monaten

I built the LLM interface I wished existed. interface0 is for power users: cross-provider memory & chat, multi-model synthesis, sharing & team features, granular context engineering, template prompts, forking, prompt enhancing, & more Here's a demo—see 🧵 for the rest
3:43

I built the LLM interface I wished existed. interface0 is for power users: cross-provider memory & chat, multi-model synthesis, sharing & team features, granular context engineering, template prompts, forking, prompt enhancing, & more Here's a demo—see 🧵 for the rest

Andy Bromberg

26,673 Aufrufe • vor 1 Jahr

He is 18 built an LLM and sold it to Anthropic for $3.2M - and at Stanford shared how to repeat it from scratch: 00:30 - how to build an LLM worth $100k in one evening 21:34 - how one LLM controls 1000 processes at the same time 43:47 - from first prompt to $3.2M from Anthropic after watching I built my first LLM in 60 minutes- a week later Anthropic offered me $100k for the system. save & watch - the article below shows how to build an LLM and sell it to Anthropic for $3.2M from scratch
1:44:13

He is 18 built an LLM and sold it to Anthropic for $3.2M - and at Stanford shared how to repeat it from scratch: 00:30 - how to build an LLM worth $100k in one evening 21:34 - how one LLM controls 1000 processes at the same time 43:47 - from first prompt to $3.2M from Anthropic after watching I built my first LLM in 60 minutes- a week later Anthropic offered me $100k for the system. save & watch - the article below shows how to build an LLM and sell it to Anthropic for $3.2M from scratch

Noisy

46,947 Aufrufe • vor 1 Monat

CLAUDE COWORK TOUR: I built my own rules and memory system (harness) so that Claude Cowork remembers everything I do. In this video I show you the specific folder structures, files, and why I did it this way. I use this same system for all 3 of my companies.
13:09

CLAUDE COWORK TOUR: I built my own rules and memory system (harness) so that Claude Cowork remembers everything I do. In this video I show you the specific folder structures, files, and why I did it this way. I use this same system for all 3 of my companies.

Justin Brooke

26,774 Aufrufe • vor 6 Monaten

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system. Fed it my frontend & CRM sources, and it built a fully updating dashboard with Shadcn packages and constantly improving and linking everything for smarter outputs! Full setup video:
0:25

Used Karpathy's LLM Wiki to turn Claude Code into a self-evolving system. Fed it my frontend & CRM sources, and it built a fully updating dashboard with Shadcn packages and constantly improving and linking everything for smarter outputs! Full setup video:

WorldofAI

133,594 Aufrufe • vor 6 Monaten

The whole session ranks among my favorite David talks. Built friction out of the system not into the system and the XRP Ledger is built for business!
0:27

The whole session ranks among my favorite David talks. Built friction out of the system not into the system and the XRP Ledger is built for business!

Vet

35,717 Aufrufe • vor 1 Jahr

SCIENTISTS TURN LIGHT INTO A MEMORY SYSTEM Scientists built a tiny photonic chip and sent identical photons through it, expecting messy quantum behavior. Instead, the light started acting like a memory system, forming patterns that match a classic AI model used for associative memory. In simple terms, the interference between photons did the math needed to store and recall patterns. No brain, no computer, just light physics doing the computing. Source: NewsForce
2:34

SCIENTISTS TURN LIGHT INTO A MEMORY SYSTEM Scientists built a tiny photonic chip and sent identical photons through it, expecting messy quantum behavior. Instead, the light started acting like a memory system, forming patterns that match a classic AI model used for associative memory. In simple terms, the interference between photons did the math needed to store and recall patterns. No brain, no computer, just light physics doing the computing. Source: NewsForce

NewsForce

29,578 Aufrufe • vor 7 Monaten

LLM + Memory + Planning + Tools = Agents 🤖 Last month, Job and I discussed how generative AI is shifting how companies offer customer support. How can we add more layers to our RAG apps to make it more agentic? LLM: Large language model alone Memory: Short-term and long-term memory Planning: Breaking down questions into sub-questions, plan the steps needed before taking action, etc. Tools: Calculator, code executor, weather API, etc. I hope you find this small clip interesting! The link to the full recording is below.
2:19

LLM + Memory + Planning + Tools = Agents 🤖 Last month, Job and I discussed how generative AI is shifting how companies offer customer support. How can we add more layers to our RAG apps to make it more agentic? LLM: Large language model alone Memory: Short-term and long-term memory Planning: Breaking down questions into sub-questions, plan the steps needed before taking action, etc. Tools: Calculator, code executor, weather API, etc. I hope you find this small clip interesting! The link to the full recording is below.

Erika Shorten

32,443 Aufrufe • vor 2 Jahren

Fellas, stop guessing. I built a system that turns content into income, and I’m teaching you step-by-step. This ain’t luck, it’s strategy!
0:30

Fellas, stop guessing. I built a system that turns content into income, and I’m teaching you step-by-step. This ain’t luck, it’s strategy!

Tysin Black 2.0

11,485 Aufrufe • vor 1 Jahr

Introducing Brain in Computer. Brain is a continuously learning memory system. Every task on Computer plugs into a context graph built by Brain. It makes Computer more stateful with every run. Available as a research preview for all Perplexity Max subscribers.
1:06

Introducing Brain in Computer. Brain is a continuously learning memory system. Every task on Computer plugs into a context graph built by Brain. It makes Computer more stateful with every run. Available as a research preview for all Perplexity Max subscribers.

Perplexity

612,661 Aufrufe • vor 4 Monaten

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)
2:11

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)

Dhravya Shah

83,511 Aufrufe • vor 8 Monaten

How I Built Grey Matter, A Procedural Data System in Blender
1:12

How I Built Grey Matter, A Procedural Data System in Blender

Sam Hox

84,279 Aufrufe • vor 1 Jahr