Loading video...

Video Failed to Load

Go Home

Anthropic CEO after realizing a Chinese dev explained loop vs graph engineering better than anyone at the company

kirillk_web3's profile picture

Kirill

40,386 subscribers

1,422,754 views • 12 days ago •via X (Twitter)

Science & TechnologyEducationNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Elon after realizing a random guy explained Grok bot better than the entire xAI team
0:14

Elon after realizing a random guy explained Grok bot better than the entire xAI team

Archive

105,922 views • 11 days ago

Anthropic CEO, Dario Amodei: the first billion-dollar company with a single human employee could emerge by 2026
0:10

Anthropic CEO, Dario Amodei: the first billion-dollar company with a single human employee could emerge by 2026

Haider.

65,997 views • 1 year ago

me after realizing i handled a situation way better than my past self would've & I'm actually growing ✨
0:18

me after realizing i handled a situation way better than my past self would've & I'm actually growing ✨

spicebae

1,938,401 views • 3 years ago

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do
0:10

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

leopardracer

53,328 views • 1 month ago

What feels better than this after a long day at the gym?
0:15

Sensitive content

What feels better than this after a long day at the gym?

Cherri Findom

54,222 views • 1 month ago

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.
0:17

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.

Iseunife The First

19,414 views • 1 month ago

A TEAM JUST DEPLOYED 15 AUTONOMOUS LOOP AGENTS FROM A SINGLE PROMPT USING APPLIED GRAPH ENGINEERING Most developers still manually hardcode multi agent systems, writing separate logic for every individual task. Graph engineering changes this by using a central topological map to spin up all 15 nodes simultaneously. A single 200 word input generates the architecture, routing 120 unique pathways between agents instantly. Instead of failing under conflicting instructions, these loop agents self correct via continuous state sharing. Managing a 15 node mesh requires high token throughput, making this dependent on strict low-] latency API tiers. See exactly how this automated multi agent graph architecture actually operates in real time ↓
0:15

A TEAM JUST DEPLOYED 15 AUTONOMOUS LOOP AGENTS FROM A SINGLE PROMPT USING APPLIED GRAPH ENGINEERING Most developers still manually hardcode multi agent systems, writing separate logic for every individual task. Graph engineering changes this by using a central topological map to spin up all 15 nodes simultaneously. A single 200 word input generates the architecture, routing 120 unique pathways between agents instantly. Instead of failing under conflicting instructions, these loop agents self correct via continuous state sharing. Managing a 15 node mesh requires high token throughput, making this dependent on strict low-] latency API tiers. See exactly how this automated multi agent graph architecture actually operates in real time ↓

slash1s

301,699 views • 1 month ago

Awkward moment: OpenAI CEO Sam Altman and Anthropic CEO Dario Amodei visibly declined to hold hands during a group photo at the India AI Impact Summit.
0:14

Awkward moment: OpenAI CEO Sam Altman and Anthropic CEO Dario Amodei visibly declined to hold hands during a group photo at the India AI Impact Summit.

Visegrád 24

137,383 views • 6 months ago

Jensen Huang the CEO of the world’s most valuable company, NVIDIA, delivers a message of support to Israelis working at the company. (JBN)
0:16

Jensen Huang the CEO of the world’s most valuable company, NVIDIA, delivers a message of support to Israelis working at the company. (JBN)

Mossad Commentary

63,804 views • 5 months ago

desi editors are doing better job at promoting #GirlRulesSeries than that blue company bcz why this suits more than the ost 🤧
0:17

desi editors are doing better job at promoting #GirlRulesSeries than that blue company bcz why this suits more than the ost 🤧

Van

19,460 views • 5 months ago

Me at the family party realizing none of these people know how to implement DSA, deploy a backend server, or even write a for loop.
0:11

Me at the family party realizing none of these people know how to implement DSA, deploy a backend server, or even write a for loop.

mitsuri

31,345 views • 1 year ago

Yixing mixed up all three languages at once — thanked the waiter in English, Chinese and Korean 😭 his reaction after realizing it was the cutest thing ever 😭🤏
0:18

Yixing mixed up all three languages at once — thanked the waiter in English, Chinese and Korean 😭 his reaction after realizing it was the cutest thing ever 😭🤏

🍊🧡🐣

40,710 views • 9 months ago

A Chinese tech company presented a device weighing no more than 20 kilograms to a company that breaks rocks using heavy machinery. When the device split a massive rock into two within seconds, the workers were astonished.
0:16

A Chinese tech company presented a device weighing no more than 20 kilograms to a company that breaks rocks using heavy machinery. When the device split a massive rock into two within seconds, the workers were astonished.

China pulse 🇨🇳

90,266 views • 4 months ago

Got a transit problem? The Boring Company will fix it. Zero cost. You pitch the tunnel. Up to 1 mile. 12-foot diameter. Loop, freight, pedestrian, utility, water - pick your painkiller. Winner gets the tunnel. No invoice. Anyone for a free tunnel? The Boring Company, Elon Musk
0:17

Got a transit problem? The Boring Company will fix it. Zero cost. You pitch the tunnel. Up to 1 mile. 12-foot diameter. Loop, freight, pedestrian, utility, water - pick your painkiller. Winner gets the tunnel. No invoice. Anyone for a free tunnel? The Boring Company, Elon Musk

Mario Nawfal

48,877 views • 6 months ago

anthropic will sell you opus 5 at $200/mo. openai will sell you gpt-5.6 at $200/mo. neither will tell you the fix that drops your bill to $20 was posted free on langchain's blog on july 18 peter steinberger posted one line asking if we'd moved from loops to graphs yet. 24 hours later there was a manifesto. a week later every ai account had a $497 graph engineering course. all of them wrong about the same thing the sentence that ends the argument, buried in a langchain post nobody quoted: loop engineering isn't an alternative to graphs, so much as a simple version of them the machine, five layers, each wraps the one below: L1 the ask · 23% of errors (anthropic red team, q4 2024) -> "just add more instructions" burns tokens with zero accuracy gain -> real fix: examples, output schema, constraints as positives L2 the context · where 90% of you actually die -> 140,500 tokens where 18,000 would work, 8x the price for the worse answer -> real fix: retrieve, rank, compact, clear dead tool outputs L3 the harness · 31% of "model bugs" are harness bugs (openai safety eval, 2024) -> unbounded file perms = avg $23,400 incident. sandboxed = $0 (stripe internal) -> no timeout = $847 median in api fees before you notice -> real fix: explicit scopes, timeouts, human-required gates L4 the loop · "it stopped" is a loop exit problem -> the verifier said "looks good" to garbage. again -> real fix: machine-checkable exit test, turn cap, rubric L5 the graph · only 12% of teams use graphs in prod (stanford hai, n=2,841) -> 58% of graph failures are wrong-agent selection, not model -> teams abandon graphs saying "harder to debug than a loop." that's a harness problem -> real fix: name every node's specialty, delete decoration fix down, not up. a symptom at layer 4 usually originates at layer 2. a bigger model on a broken harness is a smarter employee locked in the same empty room drop your $200/mo ai sub to $20, check the article below
0:19

anthropic will sell you opus 5 at $200/mo. openai will sell you gpt-5.6 at $200/mo. neither will tell you the fix that drops your bill to $20 was posted free on langchain's blog on july 18 peter steinberger posted one line asking if we'd moved from loops to graphs yet. 24 hours later there was a manifesto. a week later every ai account had a $497 graph engineering course. all of them wrong about the same thing the sentence that ends the argument, buried in a langchain post nobody quoted: loop engineering isn't an alternative to graphs, so much as a simple version of them the machine, five layers, each wraps the one below: L1 the ask · 23% of errors (anthropic red team, q4 2024) -> "just add more instructions" burns tokens with zero accuracy gain -> real fix: examples, output schema, constraints as positives L2 the context · where 90% of you actually die -> 140,500 tokens where 18,000 would work, 8x the price for the worse answer -> real fix: retrieve, rank, compact, clear dead tool outputs L3 the harness · 31% of "model bugs" are harness bugs (openai safety eval, 2024) -> unbounded file perms = avg $23,400 incident. sandboxed = $0 (stripe internal) -> no timeout = $847 median in api fees before you notice -> real fix: explicit scopes, timeouts, human-required gates L4 the loop · "it stopped" is a loop exit problem -> the verifier said "looks good" to garbage. again -> real fix: machine-checkable exit test, turn cap, rubric L5 the graph · only 12% of teams use graphs in prod (stanford hai, n=2,841) -> 58% of graph failures are wrong-agent selection, not model -> teams abandon graphs saying "harder to debug than a loop." that's a harness problem -> real fix: name every node's specialty, delete decoration fix down, not up. a symptom at layer 4 usually originates at layer 2. a bigger model on a broken harness is a smarter employee locked in the same empty room drop your $200/mo ai sub to $20, check the article below

starmex

145,325 views • 18 days ago

OpenAI CEO Sam Altman and Anthropic CEO Dario Amodei visibly declined to hold hands during a group photo at the India AI Impact Summit, even as other leaders on stage linked arms for the ceremonial shot
0:16

OpenAI CEO Sam Altman and Anthropic CEO Dario Amodei visibly declined to hold hands during a group photo at the India AI Impact Summit, even as other leaders on stage linked arms for the ceremonial shot

Reuters

585,483 views • 6 months ago

The NBA has partnered with Prime Video & Twitch after realizing chat reactions are faster than replay review. 💀 Lakers vs Mavs is currently being streamed by Agent00 and Adapt 🍿
0:14

The NBA has partnered with Prime Video & Twitch after realizing chat reactions are faster than replay review. 💀 Lakers vs Mavs is currently being streamed by Agent00 and Adapt 🍿

NBACentel

682,959 views • 6 months ago

I saw a CEO of an SI company at Twitchcon this weekend, he made fun of my name last time he saw me in his chat.... Anyone wanna guess who it was?
0:16

I saw a CEO of an SI company at Twitchcon this weekend, he made fun of my name last time he saw me in his chat.... Anyone wanna guess who it was?

BocaBola

13,407 views • 10 months ago

FYI: 'Ni Hao' is now the most racist word against Chinese, even worse than 'Ching Chong'. Seriously can anyone explain why native Chinese would be triggered by a simple greeting?
0:18

FYI: 'Ni Hao' is now the most racist word against Chinese, even worse than 'Ching Chong'. Seriously can anyone explain why native Chinese would be triggered by a simple greeting?

The Great Translation Movement 大翻译运动

49,337 views • 1 year ago