Загрузка видео...

Не удалось загрузить видео

На главную

You can break down every memory implementation into two axes - time: what changed, and when - connections: what links to what supermemory's graph keeps both on atomic facts, the latest fact wins, the old one stays as history, and you never draw an edge

supermemory's profile picture

supermemory

29,403 subscribers

10,316 просмотров • 14 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old fact stays as history, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!
1:00

Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old fact stays as history, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!

mem0

10,761 просмотров • 2 месяцев назад

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this, and the repo that runs it is below ↓
0:45

Memory vs. Graphs, clearly explained! memory is great, and the ceiling arrives quietly: it stores what happened. it does not store what to do about it. six runs later your file has fifty lines, and the model reloads all of them before it does anything. Graph engineering fixes this by changing what memory is: not a place things are kept, but an edge that runs backwards. you need both, and here is the sentence that resolves the whole confusion: a store keeps what happened. an edge keeps what to do about it. ↳ a store grows with every run, and every line is reloaded before the next one ↳ an edge carries one derived rule, and the rule replaces the run that produced it Prompts → Context → Harness → Loops → Graphs the transcript goes away, the constraint stays. and the constraint is smaller, because "adapters preserve keyword args exactly" is four hundred tokens shorter than the run that proved it. the same four blocks work on anything you can cut into lanes. i pointed them at token launches on Robinhood Chain, open source, nothing leaves your terminal the trick is knowing what deserves to survive. an output is not memory. "ported the utils slice, green on first pass" tells the next run nothing it can act on. the rule you derived from it does. one thing to know before you scale it. what you write down is not what comes back. ↳ the root rules file and auto memory are re-injected from disk. they come back intact, every time ↳ path-scoped rules live in message history. they get summarized away and do not return until a matching file is read again so a rule that must persist cannot be path-scoped. move it to the root and pay the always-loaded cost, or accept that it is advisory in any long session. and the one that eats whole nights: a memory file that has never had a line deleted is not memory. it is a tax on every run you will ever make, and nobody reads it back. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this, and the repo that runs it is below ↓

Hanako

48,225 просмотров • 1 месяц назад

New FPS where you can draw any weapon in chalk and pull it off the wall to use it - How it handles depends on what you draw - Draw a grip and the animations change - Draw an axe to break down doors - Draw a bigger mag and get slower reload Game is Chalk Warfare
0:24

New FPS where you can draw any weapon in chalk and pull it off the wall to use it - How it handles depends on what you draw - Draw a grip and the animations change - Draw an axe to break down doors - Draw a bigger mag and get slower reload Game is Chalk Warfare

Indie Game Joe

6,564,171 просмотров • 1 месяц назад

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!
0:50

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 просмотров • 4 месяцев назад

context engineering vs graph engineering. every few months the list gets a new word and everyone treats it as a replacement for the last one. these two are not on the same list. one decides what the model sees this turn, the other decides what exists at all. the cleanest way to tell them apart is to ask what a single unit of work looks like. > context engineering is the window the window opens empty, every single time. you assemble what goes in it. the prompt, the docs, the history, the tool results. the assembling is the work. the window only grows. it never shrinks on its own, so eventually something gets dropped. usually from the middle. usually without telling you. then the turn ends and the window is thrown away. not archived, thrown away. the next turn opens empty again and you re-explain what you already explained. good context engineering is knowing what to leave out, not what to pack in. the unit of work is one window. > graph engineering is the structure the same material arrives from the same sources. instead of packing it into a window, you pull entities out of it, resolve the duplicates into one node, and write typed edges between them. nothing here is stored as text you hope to find again. it is stored as a thing with a name and its connections to other things. when the turn ends, the graph is still there. the next turn does not start from zero. it starts by querying what already exists, and the query walks edges instead of guessing at similarity. good graph engineering is deciding what counts as the same thing twice. the unit of work is one relationship. > they are not alternatives the graph is what refills the window. context engineering decides what fits. graph engineering decides what there is to choose from. remove the graph and every session starts blind. remove the context work and the best structure in the world arrives as an unreadable dump. that also tells you which one broke. the answer drifted from what you actually said, or forgot something from this same session. that is the window. the answer is coherent but invents a connection that does not exist, or cannot join two facts it has clearly seen. that is the structure. people debug the prompt because the prompt is the easiest thing to edit. it keeps taking the blame for failures that live a layer down. save this - then read the full breakdown below
0:40

context engineering vs graph engineering. every few months the list gets a new word and everyone treats it as a replacement for the last one. these two are not on the same list. one decides what the model sees this turn, the other decides what exists at all. the cleanest way to tell them apart is to ask what a single unit of work looks like. > context engineering is the window the window opens empty, every single time. you assemble what goes in it. the prompt, the docs, the history, the tool results. the assembling is the work. the window only grows. it never shrinks on its own, so eventually something gets dropped. usually from the middle. usually without telling you. then the turn ends and the window is thrown away. not archived, thrown away. the next turn opens empty again and you re-explain what you already explained. good context engineering is knowing what to leave out, not what to pack in. the unit of work is one window. > graph engineering is the structure the same material arrives from the same sources. instead of packing it into a window, you pull entities out of it, resolve the duplicates into one node, and write typed edges between them. nothing here is stored as text you hope to find again. it is stored as a thing with a name and its connections to other things. when the turn ends, the graph is still there. the next turn does not start from zero. it starts by querying what already exists, and the query walks edges instead of guessing at similarity. good graph engineering is deciding what counts as the same thing twice. the unit of work is one relationship. > they are not alternatives the graph is what refills the window. context engineering decides what fits. graph engineering decides what there is to choose from. remove the graph and every session starts blind. remove the context work and the best structure in the world arrives as an unreadable dump. that also tells you which one broke. the answer drifted from what you actually said, or forgot something from this same session. that is the window. the answer is coherent but invents a connection that does not exist, or cannot join two facts it has clearly seen. that is the structure. people debug the prompt because the prompt is the easiest thing to edit. it keeps taking the blame for failures that live a layer down. save this - then read the full breakdown below

Hanako

19,160 просмотров • 2 месяцев назад

You can log off as much as you like, you’ll be back. You can delete your account, but we both know you’ll make a new one and come back. You can’t ignore what you are. You can’t ignore your needs and desires. It’s time to face the facts and admit who you are and what you want. Mindless fucktoys have their place and are needed. Don’t ever be ashamed of what makes you happy.
0:37

Sensitive content

You can log off as much as you like, you’ll be back. You can delete your account, but we both know you’ll make a new one and come back. You can’t ignore what you are. You can’t ignore your needs and desires. It’s time to face the facts and admit who you are and what you want. Mindless fucktoys have their place and are needed. Don’t ever be ashamed of what makes you happy.

Alice 🎀

28,127 просмотров • 2 лет назад

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!
19:42

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!

supermemory

20,600 просмотров • 2 месяцев назад

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓
19:55

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

supermemory

14,752 просмотров • 3 месяцев назад

We’re living in a 3–5 year window right now. If you can anticipate what people will want in an age of abundance, understand what unlocks new AI capabilities, what data it needs, and what components you can build; this is the best time in history to execute. Execution just keeps getting cheaper and vision is the differentiator.
0:37

We’re living in a 3–5 year window right now. If you can anticipate what people will want in an age of abundance, understand what unlocks new AI capabilities, what data it needs, and what components you can build; this is the best time in history to execute. Execution just keeps getting cheaper and vision is the differentiator.

Dave Blundin

59,305 просмотров • 8 месяцев назад

We understand what every home needs—stronger, meaningful connections. And you can count on us to serve you as best as we can. Every day. #WeAreHereForYou ASC Ref. No. P0121P091324P
1:00

We understand what every home needs—stronger, meaningful connections. And you can count on us to serve you as best as we can. Every day. #WeAreHereForYou ASC Ref. No. P0121P091324P

PLDT HOME

16,621,827 просмотров • 1 год назад

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓
0:33

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Ricker

19,999 просмотров • 1 месяц назад

Neal: We reached an agreement and a tweet changed all of it? Can you imagine what the next two years are going to be like if every time the congress works its will and then there's a tweet..
0:50

Neal: We reached an agreement and a tweet changed all of it? Can you imagine what the next two years are going to be like if every time the congress works its will and then there's a tweet..

Acyn

230,551 просмотров • 1 год назад

"If you keep that core, understand what pain is, and add what you need to add, then you will achieve what hasn't been done for Arsenal" Thierry Henry speaks on Arsenal trying to win the Champions League for the first time in their history, as he wins the UEFA President’s Award 👏
2:57

"If you keep that core, understand what pain is, and add what you need to add, then you will achieve what hasn't been done for Arsenal" Thierry Henry speaks on Arsenal trying to win the Champions League for the first time in their history, as he wins the UEFA President’s Award 👏

Football on TNT Sports

287,659 просмотров • 1 месяц назад

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:41

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

73,867 просмотров • 2 месяцев назад

Gave UEFN its own blueprint graph. Python tool running inside the editor. Scans your level and parses your Verse code to draw a full visual map of your game logic. What it shows you: - Every device in your level as a node - Every @ editable reference between devices - Every event subscription and function call - Which Verse functions are actually being used vs sitting there doing nothing What it catches: - Broken connections where an @ editable points to nothing - Orphan devices with zero connections - Unassigned editables you forgot to wire up What you can do with it: - Click a node, and it selects the device in your viewport - Double-click to fly straight to it - Open the Verse file in VS Code with one button - Search and filter by device type - Zoom in and out - Add notes to any device - Export the whole graph as a doc
0:32

Gave UEFN its own blueprint graph. Python tool running inside the editor. Scans your level and parses your Verse code to draw a full visual map of your game logic. What it shows you: - Every device in your level as a node - Every @ editable reference between devices - Every event subscription and function call - Which Verse functions are actually being used vs sitting there doing nothing What it catches: - Broken connections where an @ editable points to nothing - Orphan devices with zero connections - Unassigned editables you forgot to wire up What you can do with it: - Click a node, and it selects the device in your viewport - Double-click to fly straight to it - Open the Verse file in VS Code with one button - Search and filter by device type - Zoom in and out - Add notes to any device - Export the whole graph as a doc

Immature

12,163 просмотров • 7 месяцев назад

A 13-PAGE BREAKDOWN OF AGENT MEMORY THAT CUTS TOKEN COST BY 90% your agent reads the same 12 files every morning reaches the same conclusions and charges you for it again the model got 10x smarter in two years it still forgets everything the second a session ends five layers fix that: 1. working memory - what it sees right now > the context window > when it fills, the old context drops out > most agents live here and never leave 2. episodic memory - what happened > the full interaction log, timestamped > the deploy that died tuesday at 3am over a typo stays remembered > you explain it once 3. semantic memory - what is true > facts, entities and relationships in a knowledge graph > "this user prefers TypeScript" survives the session 4. procedural memory - how to do things > three approaches tried, one worked > that one becomes a reusable skill > the next run starts there 5. forgetting - what to delete > an agent that remembers everything collects contradictions > you move cities, it keeps recommending the old restaurants the numbers: > Mem0 - 1,800 tokens per query instead of 26,000 > 91% lower latency > Snowflake - one ontology layer, 20% more accuracy, 39% fewer tool calls memory pays for itself on day one the layer nobody builds is the forgetting engine it decides whether the other four stay worth trusting full 13-page breakdown below 👇
0:24

A 13-PAGE BREAKDOWN OF AGENT MEMORY THAT CUTS TOKEN COST BY 90% your agent reads the same 12 files every morning reaches the same conclusions and charges you for it again the model got 10x smarter in two years it still forgets everything the second a session ends five layers fix that: 1. working memory - what it sees right now > the context window > when it fills, the old context drops out > most agents live here and never leave 2. episodic memory - what happened > the full interaction log, timestamped > the deploy that died tuesday at 3am over a typo stays remembered > you explain it once 3. semantic memory - what is true > facts, entities and relationships in a knowledge graph > "this user prefers TypeScript" survives the session 4. procedural memory - how to do things > three approaches tried, one worked > that one becomes a reusable skill > the next run starts there 5. forgetting - what to delete > an agent that remembers everything collects contradictions > you move cities, it keeps recommending the old restaurants the numbers: > Mem0 - 1,800 tokens per query instead of 26,000 > 91% lower latency > Snowflake - one ontology layer, 20% more accuracy, 39% fewer tool calls memory pays for itself on day one the layer nobody builds is the forgetting engine it decides whether the other four stay worth trusting full 13-page breakdown below 👇

Annatar.md

31,694 просмотров • 1 месяц назад

Chase Hughes just revealed a wild way to edit traumatic memories using hypnosis on the Joe Rogan Experience. HUGHES: “I figured out a way to edit memory… I can take you back and change your perspective on trauma.” “You go back to that event when you got kicked in the nuts and everybody laughed at you in elementary school… and you can reprocess that memory in a very short amount of time as an adult with the perspective of an adult.” “Instead of modifying the memory like ‘oh that never happened’ — the memory stays. The perspective changes.” “And it’s exactly what psychedelics do. This massive perspective shift on memory… their whole life can be different after that day.” He says he’s done this hundreds of times and it creates real downstream effects.
5:35

Chase Hughes just revealed a wild way to edit traumatic memories using hypnosis on the Joe Rogan Experience. HUGHES: “I figured out a way to edit memory… I can take you back and change your perspective on trauma.” “You go back to that event when you got kicked in the nuts and everybody laughed at you in elementary school… and you can reprocess that memory in a very short amount of time as an adult with the perspective of an adult.” “Instead of modifying the memory like ‘oh that never happened’ — the memory stays. The perspective changes.” “And it’s exactly what psychedelics do. This massive perspective shift on memory… their whole life can be different after that day.” He says he’s done this hundreds of times and it creates real downstream effects.

Defiant Ghost

26,912 просмотров • 4 месяцев назад

The rules of engagement have changed. The greatest threat isn't what you can see — it's what you failed to hear. Every shot echoes. Are you listening? Season Echo is now LIVE on PC, mobile, and console.
5:37

The rules of engagement have changed. The greatest threat isn't what you can see — it's what you failed to hear. Every shot echoes. Are you listening? Season Echo is now LIVE on PC, mobile, and console.

Delta Force Game

12,115,754 просмотров • 6 месяцев назад