Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find... new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.show more

Codez

45,678 subscribers

44,590 Aufrufe • vor 2 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

23 Kommentare

Profilbild von Gipp 🦅

Gipp 🦅vor 2 Monaten

how does deleting steering impact real-world agent reliability?

Profilbild von Codez

Codezvor 2 Monaten

Delete steering, and reliability drops fast - you’re not simplifying the agent, you’re removing the thing that keeps autonomy honest.

Profilbild von Granite

Granitevor 2 Monaten

still amazed by how smart these engineers sound btw i'm actively studying harness engineering rn

Profilbild von Codez

Codezvor 2 Monaten

Also, I’m glad we get to learn directly from the Anthropic team itself. Yeah, harness engineering is where I’m spending most of my time right now.

Profilbild von rewind

rewindvor 2 Monaten

model was never the bottleneck

Profilbild von Codez

Codezvor 2 Monaten

Maybe in the beginning of AI, but definitely not now.

Profilbild von Yarchi

Yarchivor 2 Monaten

Very clear explanation, thanks for sharing

Profilbild von AdiiX

AdiiXvor 2 Monaten

the whole point is step 1 is done, everyone still tuning prompts is fighting last years bottleneck

Profilbild von Codez

Codezvor 2 Monaten

yeah, sadly true

Profilbild von 0xRafy

0xRafyvor 2 Monaten

Thariq is always shipping alpha, great share bro !

Profilbild von Codez

Codezvor 2 Monaten

Yeah, a real legend. I really loved the system he shared on the podcast.

Profilbild von Fabrizio Degeno

Fabrizio Degenovor 2 Monaten

Something new in my feed

Profilbild von Codez

Codezvor 2 Monaten

yeah, podcast was posted less then 24-h ago

Profilbild von Muhammad Ali

Muhammad Alivor 2 Monaten

The harness insight is underrated but "delete the steering" only works when your codebase is small enough to fit in context. Past 50K lines the model needs explicit guidance or it drifts into fixing the wrong file. What repo size are you testing this approach on?

Profilbild von Genius💡💹🧲 🤖

Genius💡💹🧲 🤖vor 2 Monaten

Learning directly from builders always gives way better insights than random takes

Profilbild von Electrik Dreams

Electrik Dreamsvor 2 Monaten

RAG as anti-pattern will get pushback, but it's technically sound. At 4k tokens, vector retrieval was necessary infrastructure. At 200k, you're adding latency and fragility for diminishing returns. grep scales.

Profilbild von Adam

Adamvor 2 Monaten

The distinction between a stronger model and a better harness is the part most builders miss. Your long-form AI articles deserve one clear home where readers can browse the roadmap, newsletter and best systems—not just a Substack profile. Would a quick homepage concept be useful?

Profilbild von FenixFlow

FenixFlowvor 2 Monaten

Deleting steering cuts down on prompt brittleness and over-constraint, letting the model use its native reasoning more freely. In real workflows we've seen it boost reliability on multi-step tasks (fewer hallucinations from forced plans), but it only works well with solid agent harnesses + clean context to catch drift. The engineer basically said they stopped babysitting and started trusting the model more - results improved.

Profilbild von 0xSlyth

0xSlythvor 2 Monaten

skip the hype build the system

Profilbild von Miles S.

Miles S.vor 2 Monaten

i’m trying grep before touching another vector database

Profilbild von Neo

Neovor 2 Monaten

The real insight isn't any single step. it's that harness quality is unmeasurable by most teams. You can A/B test a model. Almost nobody has a rigorous way to A/B test a harness, which is exactly why it stays a rare skill.

Profilbild von whydeso

whydesovor 2 Monaten

Optimizing all four steps instead of just the model is key

Profilbild von Shoopy

Shoopyvor 2 Monaten

"RAG is an anti-pattern, use grep" is such a spicy line lol. Booking this one

Ähnliche Videos

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems In this 15-minute workshop, he shows exactly how to build one from scratch AI → Agents → Harness → Loops → Graphs step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter Anthropic calls this "dreaming" Most people spend weeks building this by hand You don't have to Bookmark and watch it Then read the full harness engineering guide below ↓

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems In this 15-minute workshop, he shows exactly how to build one from scratch AI → Agents → Harness → Loops → Graphs step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter Anthropic calls this "dreaming" Most people spend weeks building this by hand You don't have to Bookmark and watch it Then read the full harness engineering guide below ↓

rari

183,635 Aufrufe • vor 14 Tagen

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build harnesses" In just 42 minutes, she shows how the Claude team builds harnesses that prompt themselves Agents → Harness → Loops → Graphs → Self-Improving Systems If this were a $500 course, people would call it one of the best agent courses of the year But it's completely free And it's better than most paid agent engineering courses Watch it today Then use the step-by-step harness engineering guide below

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build harnesses" In just 42 minutes, she shows how the Claude team builds harnesses that prompt themselves Agents → Harness → Loops → Graphs → Self-Improving Systems If this were a $500 course, people would call it one of the best agent courses of the year But it's completely free And it's better than most paid agent engineering courses Watch it today Then use the step-by-step harness engineering guide below

rari

32,547 Aufrufe • vor 16 Tagen

Anthropic engineer: “80% of our engineers are using Loops. Now everyone is exploring how to build right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of agents.” in this 1-hour talk, Anthropic engineer shows how to build a self-improving agents from sratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Anthropic engineer: “80% of our engineers are using Loops. Now everyone is exploring how to build right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of agents.” in this 1-hour talk, Anthropic engineer shows how to build a self-improving agents from sratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Codez

36,334 Aufrufe • vor 1 Monat

Anthropic engineer: “80% of our engineers are using self-improving loops. Now everyone is exploring how to build the right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of building agents.” In this 40-minute lecture, an Anthropic engineer shows how to build a self-improving agentic workflow from scratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Anthropic engineer: “80% of our engineers are using self-improving loops. Now everyone is exploring how to build the right Context for agents.” in 3-6 months, we’ll all become context engineers. Context is the most important part of building agents.” In this 40-minute lecture, an Anthropic engineer shows how to build a self-improving agentic workflow from scratch. It’s worth more than a $500 agentic course. Watch this video, then read the article below on how to become a context architect.

Movez

21,136 Aufrufe • vor 1 Monat

Instagram co-founder, now at Anthropic: "Most usage at Anthropic isn't Claude Code anymore, it's agents wired with the right loops and graphs working as teammates." In 25 minutes he explains how the people building frontier models actually work now. Worth more than any $700 course on AI you can find. Watch it, then read the step-by-step guide below on building an agent system that improves itself.

Instagram co-founder, now at Anthropic: "Most usage at Anthropic isn't Claude Code anymore, it's agents wired with the right loops and graphs working as teammates." In 25 minutes he explains how the people building frontier models actually work now. Worth more than any $700 course on AI you can find. Watch it, then read the step-by-step guide below on building an agent system that improves itself.

Anatoli Kopadze

64,102 Aufrufe • vor 18 Tagen

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓

codila

119,500 Aufrufe • vor 1 Monat

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

codila

11,581 Aufrufe • vor 2 Monaten

Google's team published a 9-page PDF on Harness Engineering. one formula replaced prompt engineering: Agent = Model + Harness the twist: same Claude Sonnet, same benchmark. change only the harness the playbook, six steps: step 1 -> add guides AGENTS.md, rule files, constraint docs. every line is a past agent failure turned into a permanent fix step 2 -> add sensors linters, tests, validation scripts the agent runs on its own output before a human sees it step 3 -> build the agentic loop plan, execute, verify, fix. bounded retries, budget caps, escalation when stuck step 4 -> externalize memory the model forgets every session. the harness holds state, decisions and artifacts across all of them step 5 -> enforce permissions which tools, how many writes, what needs approval. safety lives in the harness, never in the model step 6 -> wire observability track every tool call, cost and retry. trip wires fire when behavior drifts the result: your agent turns from a demo into infrastructure every failure makes the system permanently better, not just the next conversation that's also the line between an agent you show people and one a client pays you to leave running one harness gets you a reliable loop. connect several and it becomes graph engineering, where one agent's failure turns into another agent's sensor the PDF stops at the harness. the graph is the next layer that breakdown, running on Kimi, is below ↓

Google's team published a 9-page PDF on Harness Engineering. one formula replaced prompt engineering: Agent = Model + Harness the twist: same Claude Sonnet, same benchmark. change only the harness the playbook, six steps: step 1 -> add guides AGENTS.md, rule files, constraint docs. every line is a past agent failure turned into a permanent fix step 2 -> add sensors linters, tests, validation scripts the agent runs on its own output before a human sees it step 3 -> build the agentic loop plan, execute, verify, fix. bounded retries, budget caps, escalation when stuck step 4 -> externalize memory the model forgets every session. the harness holds state, decisions and artifacts across all of them step 5 -> enforce permissions which tools, how many writes, what needs approval. safety lives in the harness, never in the model step 6 -> wire observability track every tool call, cost and retry. trip wires fire when behavior drifts the result: your agent turns from a demo into infrastructure every failure makes the system permanently better, not just the next conversation that's also the line between an agent you show people and one a client pays you to leave running one harness gets you a reliable loop. connect several and it becomes graph engineering, where one agent's failure turns into another agent's sensor the PDF stops at the harness. the graph is the next layer that breakdown, running on Kimi, is below ↓

Annatar.md

77,397 Aufrufe • vor 9 Tagen

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.

Codez

26,868 Aufrufe • vor 2 Monaten

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the model first We made that mistake in 2016 at OpenAI - It cost us 5 years " what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " watch - bookmark, then read article below ↓

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the model first We made that mistake in 2016 at OpenAI - It cost us 5 years " what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " watch - bookmark, then read article below ↓

codila

1,910,937 Aufrufe • vor 2 Monaten

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Anatoli Kopadze

607,311 Aufrufe • vor 1 Monat

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Head of Claude Code: "I'm not prompting my agents anymore, I'm building graphs and loops so they can build the agents for me." In 10 minutes he shows exactly where agentic engineering is going and how not to get left behind. Definitely something you cannot afford to skip. Watch it, then read the step-by-step guide below on how to build a system that improves itself.

Anatoli Kopadze

381,462 Aufrufe • vor 21 Tagen

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Ichigo

98,555 Aufrufe • vor 12 Tagen

He is 19, already built an AI system making $2.3M a year - and now teaches how to do it at Stanford 01:03 - he lost his job at Anthropic because of prompt engineering 09:34 - Context Engineering gives 10x to coding speed 28:47 - Opus 5 builds an AI system making $2.3M a year from scratch after watching I deleted all my prompts and switched to Context Engineering - first $20k+ in a month. Save & watch - the article below is a step by step guide to build an AI system

He is 19, already built an AI system making $2.3M a year - and now teaches how to do it at Stanford 01:03 - he lost his job at Anthropic because of prompt engineering 09:34 - Context Engineering gives 10x to coding speed 28:47 - Opus 5 builds an AI system making $2.3M a year from scratch after watching I deleted all my prompts and switched to Context Engineering - first $20k+ in a month. Save & watch - the article below is a step by step guide to build an AI system

Noisy

67,995 Aufrufe • vor 1 Monat

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop

Lunar

40,637 Aufrufe • vor 21 Tagen

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop

Anthropic engineer: "At Anthropic, we don't write prompts anymore We build loops" In just 42 minutes, she shows how the Claude team builds loops that can prompt themselves If this were a $400 course, people would probably call it one of the best agent courses of the year It's completely free Watch it, then use the step-by-step guide below to build your first loop

Lunar

72,996 Aufrufe • vor 1 Monat

Anthropic engineer: "The fastest way to make an agent better isn't a smarter model, it's the right loop and graph around it." In 60 minutes she breaks down how Anthropic engineers use Claude Code, build agents that catch their own mistakes and improve with every run. This beats any $500 agentic engineering course you can find. Watch it, then read the full guide on loops and graphs below.

Anthropic engineer: "The fastest way to make an agent better isn't a smarter model, it's the right loop and graph around it." In 60 minutes she breaks down how Anthropic engineers use Claude Code, build agents that catch their own mistakes and improve with every run. This beats any $500 agentic engineering course you can find. Watch it, then read the full guide on loops and graphs below.

Anatoli Kopadze

135,539 Aufrufe • vor 1 Monat

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Andrew Ng: "The most important trend in AI is agentic AI." in 30-minutes talk he breaks down the agentic orchestration layer and how he actually builds with agents: step 1 → prototype fast. what used to take 3 engineers and 6 months - his team builds in an afternoon step 2 → run evals, not vibes. "new model comes out → run evals → switch in two days" step 3 → iterate in loops. outline → search → draft → revise → loop. "this is the heart of agentic systems" Worth more than any paid course on building agents. Watch the talk, then read the guide on building self-improving agentic systems below.

Movez

16,545 Aufrufe • vor 2 Monaten

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

61,226 Aufrufe • vor 2 Monaten

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

codila

11,941 Aufrufe • vor 1 Monat