Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Since the editor itself is a unit, you can plug it to a graph to debug inside and outside at the same time.

io_sammt's profile picture

Samuel Timbó

9,694 subscribers

114,604 Aufrufe • vor 2 Jahren •via X (Twitter)

BildungWissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

The Unit Environment allows one to interact with an app and debug its internals in the same place and at the same time — every project can have its own custom developer experience.
0:34

The Unit Environment allows one to interact with an app and debug its internals in the same place and at the same time — every project can have its own custom developer experience.

Samuel Timbó

373,406 Aufrufe • vor 11 Monaten

Launching Animation Studio A full animation graph editor for ThreeJS games You can directly use Codex chat inside the app to build the graph for you Features: - Graph editor - Blendtrees - State Machines - Subgraphs - Parameters - Root Motion - Bone Masks - Additive Animations Free and Open Source (MIT), enjoy
1:12

Launching Animation Studio A full animation graph editor for ThreeJS games You can directly use Codex chat inside the app to build the graph for you Features: - Graph editor - Blendtrees - State Machines - Subgraphs - Parameters - Root Motion - Bone Masks - Additive Animations Free and Open Source (MIT), enjoy

robot 2.0

42,752 Aufrufe • vor 7 Monaten

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 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 3 Monaten

This time Astra helped write and debug the control code for a G1 cycling independently from a rolling start It now rides for 30 seconds from rest in MuJoCo simulator without virtual stabilizers If you look closely enough you can see the upper body tilting to balance itself.
0:20

This time Astra helped write and debug the control code for a G1 cycling independently from a rolling start It now rides for 30 seconds from rest in MuJoCo simulator without virtual stabilizers If you look closely enough you can see the upper body tilting to balance itself.

H

11,156 Aufrufe • vor 1 Monat

A rare chance to film the inside and the outside of the venue in the same shot... RALLY ENERGY IS BUILDING!!!
0:31

A rare chance to film the inside and the outside of the venue in the same shot... RALLY ENERGY IS BUILDING!!!

Brick Suit

20,177 Aufrufe • vor 7 Tagen

Repentance is not a feeling. It is a direction. It is movement. 👇 It means movement back to the point of departure. How long has it been since you were really close with God? Since you laid at the altar and cried. Since you felt the conviction of going outside the parameters of His Word. 📖
1:04

Repentance is not a feeling. It is a direction. It is movement. 👇 It means movement back to the point of departure. How long has it been since you were really close with God? Since you laid at the altar and cried. Since you felt the conviction of going outside the parameters of His Word. 📖

Paula White-Cain

10,940 Aufrufe • vor 1 Monat

There is a game coming out where you have to play it in 2d and 3d at the same time
0:43

There is a game coming out where you have to play it in 2d and 3d at the same time

Dexerto

7,085,142 Aufrufe • vor 2 Jahren

your agent doesn't need a graph. it needs a verifier that isn't doing five jobs at once. a loop is already a graph - one node, one edge back to itself. you add a node when you'd hire a specialist. not before. here is the list of all 5 signals. read it before you draw another node.
0:36

your agent doesn't need a graph. it needs a verifier that isn't doing five jobs at once. a loop is already a graph - one node, one edge back to itself. you add a node when you'd hire a specialist. not before. here is the list of all 5 signals. read it before you draw another node.

Rohit

16,004 Aufrufe • vor 3 Monaten

This is the ultimate power tower. It's portable, can be used inside and outside, and is as stable as the structure you attach it to.
0:21

This is the ultimate power tower. It's portable, can be used inside and outside, and is as stable as the structure you attach it to.

Cooper Mitchell - HomeGymGuy

99,276 Aufrufe • vor 7 Monaten

Heres how to get started with the neatlogs MCP ! with this you can access your traces, detections, complete RCA and traige cards right inside Claude Code, Cursor, Windsurf, or whichever you like to build and you dont need to jump between your editor and a bunch of dashboards, you can just debug and fix your agents in one place. :)
1:33

Heres how to get started with the neatlogs MCP ! with this you can access your traces, detections, complete RCA and traige cards right inside Claude Code, Cursor, Windsurf, or whichever you like to build and you dont need to jump between your editor and a bunch of dashboards, you can just debug and fix your agents in one place. :)

simran sachdeva

24,742 Aufrufe • vor 4 Monaten

This is the treatment for touching yourself all the time. Electro chastity cage with electric urethral sound plug zapping your dick from the inside out. Mated with a big electro plug thumping away. You struggle all you can, there's no way to stop it No mercy 😭
0:21

Sensitive content

This is the treatment for touching yourself all the time. Electro chastity cage with electric urethral sound plug zapping your dick from the inside out. Mated with a big electro plug thumping away. You struggle all you can, there's no way to stop it No mercy 😭

Dog Stricken 🤝 MIR2026

83,640 Aufrufe • vor 2 Jahren

Can you turn a sphere inside out without cutting or tearing it? Remarkably, yes. If we allow the surface to pass through itself, it can be turned completely inside out while remaining smooth at every stage. This is called sphere eversion.
1:01

Can you turn a sphere inside out without cutting or tearing it? Remarkably, yes. If we allow the surface to pass through itself, it can be turned completely inside out while remaining smooth at every stage. This is called sphere eversion.

Math Files

680,687 Aufrufe • vor 16 Tagen

Your brain rewires itself around whatever you tell it most. Every time you call yourself stupid, weak, or a failure, you’re not just venting. You’re handing your brain a blueprint and it builds accordingly. Here’s the shift: talk to yourself the way you’d talk to someone you love. Same tone. Same patience. Same grace. That’s not soft. That’s how you build a healthier brain, one thought at a time.
0:54

Your brain rewires itself around whatever you tell it most. Every time you call yourself stupid, weak, or a failure, you’re not just venting. You’re handing your brain a blueprint and it builds accordingly. Here’s the shift: talk to yourself the way you’d talk to someone you love. Same tone. Same patience. Same grace. That’s not soft. That’s how you build a healthier brain, one thought at a time.

Tehxi

35,894 Aufrufe • vor 2 Monaten

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇
3:42

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

Lev Chizhov

86,944 Aufrufe • vor 3 Jahren

I had some time to improve on my rigging tool, it is basic a smart tool for adding controllers to drive shape keys. it automatically detects and sets up the transform direction and you can set up multiple at the same time #b3d #blender #Blendercommunity
1:10

I had some time to improve on my rigging tool, it is basic a smart tool for adding controllers to drive shape keys. it automatically detects and sets up the transform direction and you can set up multiple at the same time #b3d #blender #Blendercommunity

Luwizart 🔶

21,555 Aufrufe • vor 2 Jahren

When we get leaders, not rulers, transformational leaders that this country so desperately needs, you will know by their priorities. It is a fallacy to think you can loot a country and develop it at the same time.
5:41

When we get leaders, not rulers, transformational leaders that this country so desperately needs, you will know by their priorities. It is a fallacy to think you can loot a country and develop it at the same time.

Gbadebo Rhodes-Vivour

35,240 Aufrufe • vor 2 Jahren

Yet another childless woman claiming that mothers can “have it all, at the same time”. Knowles tries to explain that you can’t be in a corporate cubicle AND at home with your children at the same time yet all she responds with is “my answer is do both!” Is this “girl math”??
1:19

Yet another childless woman claiming that mothers can “have it all, at the same time”. Knowles tries to explain that you can’t be in a corporate cubicle AND at home with your children at the same time yet all she responds with is “my answer is do both!” Is this “girl math”??

Samantha D.

159,973 Aufrufe • vor 1 Jahr

The Sopranos is the show every prestige drama since has been trying to be. Two performances hold it up Gandolfini's Tony is ruthless and pathetic inside the same shot. Falco has the harder job. Carmela has to know and not know at the same time, love him and despise him, and Falco never tells you which one is winning You believe the marriage. The fights, the four seconds of silence before somebody gives in
0:58

The Sopranos is the show every prestige drama since has been trying to be. Two performances hold it up Gandolfini's Tony is ruthless and pathetic inside the same shot. Falco has the harder job. Carmela has to know and not know at the same time, love him and despise him, and Falco never tells you which one is winning You believe the marriage. The fights, the four seconds of silence before somebody gives in

best of the sopranos

31,690 Aufrufe • vor 3 Monaten