正在加载视频...

视频加载失败

返回首页

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...

AnnatarXBT's profile picture

Annatar.md

1,532 subscribers

72,865 次观看 • 3 天前 •via X (Twitter)

科学技术教育新闻政治
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below
0:20

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

rari

20,934 次观看 • 1 个月前

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 ↓
12:00

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

182,266 次观看 • 8 天前

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.
0:20

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.

kocer

30,675 次观看 • 11 天前

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓
0:20

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓

Alex

12,720 次观看 • 1 天前

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 ↓
1:48:52

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

98,000 次观看 • 6 天前

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.
0:23

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

68,679 次观看 • 23 天前

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓
45:37

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 次观看 • 1 个月前

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.
2:07

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.

Fluixo

11,303 次观看 • 1 个月前

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.
46:31

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.

Codez

43,789 次观看 • 1 个月前

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
30:04

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 次观看 • 10 天前

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓
1:04:49

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 次观看 • 1 个月前

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below
2:47:42

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Morlex

51,503 次观看 • 25 天前

Godfather of agents showed how he created the loop engineering that everyone now uses: as PhD student, he wrote the formula every AI agent now runs on - his formula taught agents to self-improve here's the formula: step 1 → stop making the model just think OR just act - make it alternate: think → act → observe → think again step 2 → let it reason out loud before every action - the plan guides the next move, not just the output step 3 → feed the result of each action back in - the model reads what happened and adjusts, live step 4 → when it fails, don't restart make it reflect on WHY it failed, in words, then retry with that memory step 5 → store those reflections - the agent gets better across attempts without any retraining before OpenAI, before he ran Tencent's AI - he was a grad student who quietly wrote the blueprint every agent now follows - now give 90-min course watch & bookmark - then read how the agent systems actually works ↓
1:22:01

Godfather of agents showed how he created the loop engineering that everyone now uses: as PhD student, he wrote the formula every AI agent now runs on - his formula taught agents to self-improve here's the formula: step 1 → stop making the model just think OR just act - make it alternate: think → act → observe → think again step 2 → let it reason out loud before every action - the plan guides the next move, not just the output step 3 → feed the result of each action back in - the model reads what happened and adjusts, live step 4 → when it fails, don't restart make it reflect on WHY it failed, in words, then retry with that memory step 5 → store those reflections - the agent gets better across attempts without any retraining before OpenAI, before he ran Tencent's AI - he was a grad student who quietly wrote the blueprint every agent now follows - now give 90-min course watch & bookmark - then read how the agent systems actually works ↓

codila

28,667 次观看 • 1 个月前

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below
2:04:19

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

Hanako

53,692 次观看 • 1 个月前

Buzz is Slack where the agents are teammates instead of integrations. Here's what that unlocks: Agents: - The ones you start with are just defaults - Edit them, add your own, write their instructions like a system prompt Swappable Harness: - This is the killer feature - Swap Claude Code, Codex, Goose under the same agent Context: - Every chat you've had with that agent carries over to the new harness - Global skills and skill files come too Think: Slack = the shape Agents = the teammates Harness = the engine you can change without losing anything "I get model fatigue" is a real thing. Buzz sits one layer above it.
3:58

Buzz is Slack where the agents are teammates instead of integrations. Here's what that unlocks: Agents: - The ones you start with are just defaults - Edit them, add your own, write their instructions like a system prompt Swappable Harness: - This is the killer feature - Swap Claude Code, Codex, Goose under the same agent Context: - Every chat you've had with that agent carries over to the new harness - Global skills and skill files come too Think: Slack = the shape Agents = the teammates Harness = the engine you can change without losing anything "I get model fatigue" is a real thing. Buzz sits one layer above it.

The Startup Ideas Podcast (SIP) 🧃

43,523 次观看 • 1 个月前

HARNESS vs LOOP vs GRAPH ➜ STOP MIXING THEM UP Most people treat these three as the same thing. They’re not 1\ Harness = the machinery around the model (tools, state, permissions, memory, sandboxes, observability) 2\ Loop = the repeated work + evidence + feedback cycle with clear stop rules 3\ Graph = the explicit topology (nodes, branches, joins, controlled cycles) Clean mental model environment → feedback → flow > A raw model can’t maintain state, run tests, or restart failed jobs. Those capabilities come from the harness > Loops turn one-shot calls into managed processes that only stop when evidence proves success > Graphs decide which component is allowed to run next Most production failures that get blamed on the model are actually failures of harness, loop, or graph design Design the three layers together. Diagnose by layer when something breaks Guide in the article below
0:21

HARNESS vs LOOP vs GRAPH ➜ STOP MIXING THEM UP Most people treat these three as the same thing. They’re not 1\ Harness = the machinery around the model (tools, state, permissions, memory, sandboxes, observability) 2\ Loop = the repeated work + evidence + feedback cycle with clear stop rules 3\ Graph = the explicit topology (nodes, branches, joins, controlled cycles) Clean mental model environment → feedback → flow > A raw model can’t maintain state, run tests, or restart failed jobs. Those capabilities come from the harness > Loops turn one-shot calls into managed processes that only stop when evidence proves success > Graphs decide which component is allowed to run next Most production failures that get blamed on the model are actually failures of harness, loop, or graph design Design the three layers together. Diagnose by layer when something breaks Guide in the article below

beamnxw ./

19,471 次观看 • 1 个月前

Sam Altman made the case for open-source harnesses in July. a month later, someone shipped it, and it's more efficient than most managed harnesses. here is the problem it was aimed at: a large share of your agent's token bill is the model rereading things it already read. that isn't the model's doing. the runtime around it decides what goes into every prompt and how often the model gets called. for example, an agent queries a CRM at step four and gets back 400 rows. those rows get piled up in the conversation history. by step nineteen, the model has to read those rows fifteen times unnecessarily, and every token read is billed at input rates. it happened because your harness assembled that prompt on every turn and kept the rows in it. that gives you two levers: how much context the harness carries forward, and how often it calls the model. there are four practical ways to keep the prompt from growing unnecessarily: → load tool schemas on demand. a server with 100 tools doesn't need to put all 100 into every prompt when the agent only calls two. → offload large results to disk. turn a large response into a short preview and a file path instead of replaying the entire result on every turn. → delegate to subagents. let a subagent spend thirty tool calls in its own context and return one summary to the root agent. → run toolchains in code. one script calls three tools, joins the results, and returns a table instead of three turns each dragging a full response. but reducing context is only half the job. you also need to control how often the model gets called. a good harness should avoid unnecessary planning, verification, and reflection when the work can be completed in fewer steps. TrueFoundry's open-source agent harness, TrueForge, is built around both of those controls. it sits between the model and the tools, deciding what goes into every prompt and when another model call is actually needed. it also breaks token usage down across the harness, skills, instructions, tools, and messages. DevRev's Enterprise-Bench is where this gets tested, on multi-step tasks of the kind where an agent pulls records from one system and reconciles them against another. TrueFoundry ran TrueForge there against Claude Managed Agents, both on the same model, and both finished the same number of tasks. the tie is the part that matters, because it means the gap underneath is not a quality tradeoff. TrueForge reached that score on close to a third of the tokens, with roughly 40% fewer trips back to the model. for the same result, that comes out around 2.7x cheaper than Claude Managed Agents. swapping in an open model made it sharper still. TrueForge with GLM-5.2 scored a little higher than either setup above, and the entire benchmark run cost about $3 at list prices. being open source matters beyond the license here. the model underneath can be swapped without rewriting the agent, and the whole thing can run inside your own environment when the data cannot leave it. all of this comes down to the runtime around the model, the context it carries, the tools it exposes, and how many times it goes back to the model. that is what a production harness actually owns. the full task list, the per-run numbers, and the MIT-licensed code are on GitHub: (don't forget to star 🌟) you can read more about the same in the article quoted below. thanks to the TrueForge team for working with me on this one.
0:39

Sam Altman made the case for open-source harnesses in July. a month later, someone shipped it, and it's more efficient than most managed harnesses. here is the problem it was aimed at: a large share of your agent's token bill is the model rereading things it already read. that isn't the model's doing. the runtime around it decides what goes into every prompt and how often the model gets called. for example, an agent queries a CRM at step four and gets back 400 rows. those rows get piled up in the conversation history. by step nineteen, the model has to read those rows fifteen times unnecessarily, and every token read is billed at input rates. it happened because your harness assembled that prompt on every turn and kept the rows in it. that gives you two levers: how much context the harness carries forward, and how often it calls the model. there are four practical ways to keep the prompt from growing unnecessarily: → load tool schemas on demand. a server with 100 tools doesn't need to put all 100 into every prompt when the agent only calls two. → offload large results to disk. turn a large response into a short preview and a file path instead of replaying the entire result on every turn. → delegate to subagents. let a subagent spend thirty tool calls in its own context and return one summary to the root agent. → run toolchains in code. one script calls three tools, joins the results, and returns a table instead of three turns each dragging a full response. but reducing context is only half the job. you also need to control how often the model gets called. a good harness should avoid unnecessary planning, verification, and reflection when the work can be completed in fewer steps. TrueFoundry's open-source agent harness, TrueForge, is built around both of those controls. it sits between the model and the tools, deciding what goes into every prompt and when another model call is actually needed. it also breaks token usage down across the harness, skills, instructions, tools, and messages. DevRev's Enterprise-Bench is where this gets tested, on multi-step tasks of the kind where an agent pulls records from one system and reconciles them against another. TrueFoundry ran TrueForge there against Claude Managed Agents, both on the same model, and both finished the same number of tasks. the tie is the part that matters, because it means the gap underneath is not a quality tradeoff. TrueForge reached that score on close to a third of the tokens, with roughly 40% fewer trips back to the model. for the same result, that comes out around 2.7x cheaper than Claude Managed Agents. swapping in an open model made it sharper still. TrueForge with GLM-5.2 scored a little higher than either setup above, and the entire benchmark run cost about $3 at list prices. being open source matters beyond the license here. the model underneath can be swapped without rewriting the agent, and the whole thing can run inside your own environment when the data cannot leave it. all of this comes down to the runtime around the model, the context it carries, the tools it exposes, and how many times it goes back to the model. that is what a production harness actually owns. the full task list, the per-run numbers, and the MIT-licensed code are on GitHub: (don't forget to star 🌟) you can read more about the same in the article quoted below. thanks to the TrueForge team for working with me on this one.

Akshay 🚀

76,552 次观看 • 22 天前

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓
42:32

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓

Lunar

16,448 次观看 • 6 天前

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓
2:00

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓

Carnage

53,972 次观看 • 1 个月前

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 次观看 • 21 天前