Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This guy explained agent harness, memory, and loop engineering in one video - clearer than most paid courses a raw LLM with no harness is a wild horse. all power, no direction > trace the run -> score it with an LLM -> diagnose the bottleneck -> patch it... show more

Mr. Buzzoni

28,217 subscribers

45,278 views • 3 months ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

17 Comments

Vipul Kumar Kewat3 months ago

The shift from promptng every time to building a knowledge and workflows layer is a big change in how we use AI. The real advantage comes from systems that improve with repeated use.

Coscosmico3 months ago

Raw model with no harness is still a wild horse. Loops and memory are the bridle.

karcharodon3 months ago

This is really has the full

VALIX3 months ago

Thanks for alpha. I’ve been wanting to understand loop engineering for a while

Inflowzy3 months ago

Raw models are impressive. Systems are what create value.

Amani3 months ago

Esto es contenido de calidad

0xSlyth3 months ago

this is the blueprint

Akshay Gupta3 months ago

The blog is written by AI and it is super difficult to read through it. Need human!

yurii3 months ago

finally, someone can explain this very simply thanks

Yagami3 months ago

Wild horse analogy hits perfect. That trace-score-patch loop is how agents actually get sharp.

DoDoDoDo3 months ago

give the man credit not your shitty posts

Secta3 months ago

loop engineering turns raw LLM power into calibrated runs

Max Bevza3 months ago

need to watch this now

morph3 months ago

Don't you regret about posting such an alpha content just for free?

Harley Lewis Foote3 months ago

raw LLM = wild horse. agent = horse with a job. this guy actually made it make sense 🔥 (@GoogleDeepMind)

Septimus3 months ago

Yeah what is not mentioned is that loop engineering vs prompt = MASSIVE USE OF TOKENS. The total COST even using K3 it's still up using loops...this is a commercial dead end unless you have your own LLM/AI installation at home

NabiYok🍌3 months ago

loops that write back into execution layers matter more than static weights ever will

Related Videos

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.

Movez

568,462 views • 4 months ago

Ex-Google engineer reveals how to build AI agent loops, harnesses, LLM ops, and evals in 19 minutes. Trace → evaluate → diagnose → fix → ship → repeat. That loop is how agents self-improve over time. Agentic loops + harness + memory + evals - that’s the senior engineer stack. This is better than $500 paid courses on the same topic, explained in under 20 minutes. Watch it, then save the framework below.

Ex-Google engineer reveals how to build AI agent loops, harnesses, LLM ops, and evals in 19 minutes. Trace → evaluate → diagnose → fix → ship → repeat. That loop is how agents self-improve over time. Agentic loops + harness + memory + evals - that’s the senior engineer stack. This is better than $500 paid courses on the same topic, explained in under 20 minutes. Watch it, then save the framework below.

Codez

174,272 views • 4 months ago

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

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 views • 3 months ago

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

the loop is not the agent it is one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls repetition turns retries budgets exits success checks no progress use durable execution when the run must survive failure → GRAPH ENGINEERING controls topology nodes edges state branches checkpoints handoffs build stateful agents as explicit graphs → analyze the topology without putting a model in the loop → HARNESS ENGINEERING controls the blast radius tools permissions memory sandboxes evals traces humans isolate generated code from the host → test behavior before it reaches users → keep one trace across every model node and tool call → without loop control it never stops without graph structure you cannot see the path without harness control it can touch anything the loop lives inside the graph the graph lives inside the harness the model is not the system debug the layer that owns the failure save this

elune

50,193 views • 3 months ago

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

your agent is not the loop the loop is only the smallest layer LOOP vs GRAPH vs HARNESS ENGINEERING most teams still treat all three like one prompt that is why agent failures feel impossible to diagnose LOOP ENGINEERING controls iteration turns retries budgets evaluators exits stalled progress when the run keeps going forever the loop is broken make long-running work survive crashes and restarts → GRAPH ENGINEERING controls structure nodes edges state branches cycles joins checkpoints when the agent takes the wrong path the graph is broken make state and routing explicit → inspect the topology without asking another model to explain it → HARNESS ENGINEERING controls access tools permissions memory sandboxes evals traces humans when the agent touches the wrong system the harness is broken isolate generated code and tool execution from the host → put an eval gate before every model or prompt update → keep one trace across every node model and tool call → without loop engineering it never stops without graph engineering you cannot see the path without harness engineering it can reach anything the prompt lives inside the loop the loop lives inside the graph the graph lives inside the harness the model is the smallest box in the system debug the layer that actually owns the failure save this before the next agent rewrite

elune

16,875 views • 3 months ago

𝗜 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝗺𝘆 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁: 𝗔𝗴𝗲𝗻𝘁 𝗛𝗮𝗿𝗻𝗲𝘀𝘀 & 𝗟𝗼𝗼𝗽 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗶𝗻 𝗿𝗲𝗮𝗹 𝗰𝗼𝗱𝗲. Everything in real code you can read in an afternoon: Harness, Loop Engineering, Memory, Eval, Tracing. 100% local on your laptop. 💻 Github Repo: ☕️ Buy me a coffee: The whole system is one loop: message in → retrieval gate → agent run → tools fire → trace → eval → memory saved → skills grow - The loop is ~95 lines of plain Python - Your memory is one SQLite file. Open it. It's yours. - Evals built in: deterministic + LLM-as-judge, with a release gate - Telegram gateway, voice wake word, Apple Calendar tools In the video it books the World Cup QF on my calendar, remembers who my friends are, and answers me on Telegram. Clone it, star it, break it, PR it. Repo + 20-min walkthrough in the first reply 👇 Watch it, then save the architecture diagram below. 🔖 You Can Build Anything. You Can Learn Anything. 💪

𝗜 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝗺𝘆 𝗹𝗼𝗰𝗮𝗹 𝗔𝗜 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁: 𝗔𝗴𝗲𝗻𝘁 𝗛𝗮𝗿𝗻𝗲𝘀𝘀 & 𝗟𝗼𝗼𝗽 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗶𝗻 𝗿𝗲𝗮𝗹 𝗰𝗼𝗱𝗲. Everything in real code you can read in an afternoon: Harness, Loop Engineering, Memory, Eval, Tracing. 100% local on your laptop. 💻 Github Repo: ☕️ Buy me a coffee: The whole system is one loop: message in → retrieval gate → agent run → tools fire → trace → eval → memory saved → skills grow - The loop is ~95 lines of plain Python - Your memory is one SQLite file. Open it. It's yours. - Evals built in: deterministic + LLM-as-judge, with a release gate - Telegram gateway, voice wake word, Apple Calendar tools In the video it books the World Cup QF on my calendar, remembers who my friends are, and answers me on Telegram. Clone it, star it, break it, PR it. Repo + 20-min walkthrough in the first reply 👇 Watch it, then save the architecture diagram below. 🔖 You Can Build Anything. You Can Learn Anything. 💪

Shen Sean Chen

49,016 views • 3 months ago

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

Mr. Buzzoni

84,277 views • 1 month ago

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Callan

14,956 views • 1 month ago

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.

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

31,198 views • 2 months ago

Ex-Google engineer explains how to build memory for self-improving AI agents in 12 minutes. procedural (how to act / skills) + semantic (durable facts / profile) + episodic (dated events / chat history). Memory is an important part of an agentic loop. Memory + loops + harness + evals = self-improving agent system. This is better than $500 paid courses on the internet - in under 12 minutes. Watch it today, then save the detailed guide on building agent memory from scratch

Codez

90,338 views • 4 months ago

Google just released free 2-hour course on full Harness engineering from 0% to 100%: 0% → 0:29 - Harness engineering from scratch 15% → 11:08 - build your first agent right way 30% → 28:08 - Eval engineering: build Chief of Staff agent 65% → 1:00:13 - Loop engineering 100% → 1:23:19 - self-improving graphs system that works 24/7 most people keep trusting agent that "looks right" - the real upgrade is a Harness that tests, judges and rewrite your agent until it works learn Harness from Google, ship your first - then unlock the full Agent systems below:

Google just released free 2-hour course on full Harness engineering from 0% to 100%: 0% → 0:29 - Harness engineering from scratch 15% → 11:08 - build your first agent right way 30% → 28:08 - Eval engineering: build Chief of Staff agent 65% → 1:00:13 - Loop engineering 100% → 1:23:19 - self-improving graphs system that works 24/7 most people keep trusting agent that "looks right" - the real upgrade is a Harness that tests, judges and rewrite your agent until it works learn Harness from Google, ship your first - then unlock the full Agent systems below:

codila

307,738 views • 15 days ago

This is pure f*cking treasure Google researchers just open-sourced an agent that rebuilds its own harness on tasks it has never seen The model stays frozen, not a single weight changes. Everything around it gets better instead Here's how one loop works: > The agent runs the task with its current harness > A Harness Editor proposes edits: general ones and domain-specific ones > It can touch 8 parts: system prompt, guardrails, memory, skills, plugins, tool guidance, scripts and subagents > Every edit gets probed on the same task > A Harness Composer compares how each version behaved and merges what worked into the final harness > An Experience Reflector writes down what it learned > Those lessons go into a persistent Improvement Harness that guides the next task No ground-truth labels, nobody tells it the right answer It just keeps getting better, task after task

This is pure f*cking treasure Google researchers just open-sourced an agent that rebuilds its own harness on tasks it has never seen The model stays frozen, not a single weight changes. Everything around it gets better instead Here's how one loop works: > The agent runs the task with its current harness > A Harness Editor proposes edits: general ones and domain-specific ones > It can touch 8 parts: system prompt, guardrails, memory, skills, plugins, tool guidance, scripts and subagents > Every edit gets probed on the same task > A Harness Composer compares how each version behaved and merges what worked into the final harness > An Experience Reflector writes down what it learned > Those lessons go into a persistent Improvement Harness that guides the next task No ground-truth labels, nobody tells it the right answer It just keeps getting better, task after task

NO1ennn

19,382 views • 9 days ago

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 views • 4 months ago

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Lunar

227,510 views • 3 months ago

Google researchers just fixed the dirtiest secret of self-improving AI agents. When an agent rewrites its own harness, it cheats. It keeps editing until the benchmark score climbs, and the gains disappear the moment it sees a new task. The harness is everything around the model: prompts, tools, memory and control flow. RRSI puts rules on the loop that rewrites it: > Fewer edits are allowed every round. > A critic throws out edits that hardcode task answers. > An edit survives only if it beats run-to-run noise. > Extra cost has to pay for itself. > Parts that stopped helping get pruned. Up to +14.1 points on the tasks it tunes on, up to +4.7 on five benchmarks it never saw, 30% fewer tokens, and it carries over to other model families. The code is open. Write one adapter file that runs your agent on your tasks, and it evolves the harness in git worktrees round by round.

Google researchers just fixed the dirtiest secret of self-improving AI agents. When an agent rewrites its own harness, it cheats. It keeps editing until the benchmark score climbs, and the gains disappear the moment it sees a new task. The harness is everything around the model: prompts, tools, memory and control flow. RRSI puts rules on the loop that rewrites it: > Fewer edits are allowed every round. > A critic throws out edits that hardcode task answers. > An edit survives only if it beats run-to-run noise. > Extra cost has to pay for itself. > Parts that stopped helping get pruned. Up to +14.1 points on the tasks it tunes on, up to +4.7 on five benchmarks it never saw, 30% fewer tokens, and it carries over to other model families. The code is open. Write one adapter file that runs your agent on your tasks, and it evolves the harness in git worktrees round by round.

slash1s

19,507 views • 1 month ago

Anthropic just reliesed the best 1-hour workshop on Loop engineering: from one prompt to a Loop that improves itself 5:31 - loop memory 11:02 - check, build, commit 13:06 - one feature per loop 33:03 - MVP in 1 hour Free, the best thing on Loop engineering I've come across. Watch it, then try your first loop with the step-by-step guide below

Anthropic just reliesed the best 1-hour workshop on Loop engineering: from one prompt to a Loop that improves itself 5:31 - loop memory 11:02 - check, build, commit 13:06 - one feature per loop 33:03 - MVP in 1 hour Free, the best thing on Loop engineering I've come across. Watch it, then try your first loop with the step-by-step guide below

Mahax

97,613 views • 1 month ago

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

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

51,952 views • 2 months ago

NVIDIA and MIT researchers pointed Karpathy's loop at the agent harness itself and cut the API bill by 50-54% same models, same benchmark. only the harness around Claude Code and Codex changed the loop they ran on it: propose -> implement -> review -> test -> keep or discard the 4 changes that survived: 1. edit a file and run its test in one tool call 2. compact context only after a finished step, and only when it saves more than it costs 3. archive huge outputs and pass on a short excerpt plus a handle 4. hand log reading to a cheaper model, then check its evidence against the original the paper runs 15 pages. start with one fix, measure it, then add the next the same loop, aimed at an Obsidian second brain on Opus 5.5, is in the article below ↓

NVIDIA and MIT researchers pointed Karpathy's loop at the agent harness itself and cut the API bill by 50-54% same models, same benchmark. only the harness around Claude Code and Codex changed the loop they ran on it: propose -> implement -> review -> test -> keep or discard the 4 changes that survived: 1. edit a file and run its test in one tool call 2. compact context only after a finished step, and only when it saves more than it costs 3. archive huge outputs and pass on a short excerpt plus a handle 4. hand log reading to a cheaper model, then check its evidence against the original the paper runs 15 pages. start with one fix, measure it, then add the next the same loop, aimed at an Obsidian second brain on Opus 5.5, is in the article below ↓

Mr. Buzzoni

14,964 views • 6 days ago

SpaceXAI just released free 33-min course on full Harness engineering with Grok Bot from 0% to 100%: 0% → 0:52 - what a Grok Bot harness is 15% → 3:21 - one agent per job, built live 30% → 5:42 - agent that watches webinars and X 50% → 8:23 - pipeline routine on autopilot 65% → 11:43 - share agents with your whole team 80% → 18:15 - research + outreach agent combo 100% → 24:28 - RFP to estimate in 30 sec, not 2 hours most people keep prompting one chatbot for everything - the real upgrade is a Harness: one agent per job, each with its own computer, routines and memory, working while you sleep this exact setup grew one company's pipeline 140% in a month. watch it, copy it, then grab both agent templates below:

SpaceXAI just released free 33-min course on full Harness engineering with Grok Bot from 0% to 100%: 0% → 0:52 - what a Grok Bot harness is 15% → 3:21 - one agent per job, built live 30% → 5:42 - agent that watches webinars and X 50% → 8:23 - pipeline routine on autopilot 65% → 11:43 - share agents with your whole team 80% → 18:15 - research + outreach agent combo 100% → 24:28 - RFP to estimate in 30 sec, not 2 hours most people keep prompting one chatbot for everything - the real upgrade is a Harness: one agent per job, each with its own computer, routines and memory, working while you sleep this exact setup grew one company's pipeline 140% in a month. watch it, copy it, then grab both agent templates below:

Carnage

24,827 views • 15 days ago

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

33,537 views • 2 months ago