Загрузка видео...

Не удалось загрузить видео

На главную

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

stevenzhang's profile picture

Steven Zhang

11,139 subscribers

118,630 просмотров • 6 месяцев назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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 @ CES

329,767 просмотров • 1 год назад

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

15,726 просмотров • 2 месяцев назад

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

Sensitive content

How to hack apple's emoji system:

AlphaFox

4,385,710 просмотров • 1 год назад

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

120,814 просмотров • 1 год назад

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

24,917 просмотров • 11 месяцев назад

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

132,526 просмотров • 2 месяцев назад

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

26,611 просмотров • 2 месяцев назад

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 просмотров • 1 год назад

I've been fascinated with Apple's Dynamic Island and how fluid the entire system is. The web should also have nice things, so I built a web version of this with a couple of components and states. Made with Nextjs and Matt Perry's motion.
0:25

I've been fascinated with Apple's Dynamic Island and how fluid the entire system is. The web should also have nice things, so I built a web version of this with a couple of components and states. Made with Nextjs and Matt Perry's motion.

Seyi

10,839 просмотров • 11 месяцев назад

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 просмотров • 3 месяцев назад

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!

Massage by Black 2.0™

11,218 просмотров • 8 месяцев назад

It's built into the system we are conditioned to accept and too distracted to confront.
2:16

It's built into the system we are conditioned to accept and too distracted to confront.

🥀_ Imposter_🥀

11,427 просмотров • 1 год назад

I built the best memory for voice agents while sponsoring @YCombinator 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 @YCombinator 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

82,607 просмотров • 3 месяцев назад

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

550,867 просмотров • 6 дней назад

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 — Second Eight

82,715 просмотров • 8 месяцев назад

Just built a chat with Excel app using Qwen 3 LLM (100% local):
0:28

Just built a chat with Excel app using Qwen 3 LLM (100% local):

Avi Chawla

64,099 просмотров • 1 год назад

“I hated school, I really hated school. I hated school generally.” “I wanted to pursue understanding, I was built this way. I have a great conceptual memory but a terrible rote memory. I always like understanding.” - Ray Dalio
0:55

“I hated school, I really hated school. I hated school generally.” “I wanted to pursue understanding, I was built this way. I have a great conceptual memory but a terrible rote memory. I always like understanding.” - Ray Dalio

Ronit Pereira

81,759 просмотров • 6 дней назад

Introducing Snowflake Arctic. An efficiently intelligent and truly open LLM built by Snowflake.
0:33

Introducing Snowflake Arctic. An efficiently intelligent and truly open LLM built by Snowflake.

Snowflake

180,106 просмотров • 2 лет назад

Hermes Agent v0.7.0 is out now. Our headline update: Memory is now an extensible plugin system. Swap in any backend, or build your own. Built-in memory works out of the box; six third-party providers are ready to go. Pick one with 'hermes memory setup'. Full changelog below ↓
2:08

Hermes Agent v0.7.0 is out now. Our headline update: Memory is now an extensible plugin system. Swap in any backend, or build your own. Built-in memory works out of the box; six third-party providers are ready to go. Pick one with 'hermes memory setup'. Full changelog below ↓

Nous Research

248,688 просмотров • 2 месяцев назад

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:
0:39

I just found a web agent framework built specifically for LLMs. It turns any site into clean, agent-ready text. Any LLM can now act on the web. It’s called Notte, and it changes everything. Let me show you how:

Markandey Sharma

52,026 просмотров • 1 год назад