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 AI engineering breakdown from IBM Technology is pure f*cking treasure it explains the role as a connected system 01 Python and APIs give you the surface to build on: services, data, integrations, and the software around the model 02 RAG and embeddings solve the context layer: finding the... right information before the model has to reason about it 03 agents turn that context into work: they choose tools, run steps, and move toward an outcome 04 observability closes the feedback loop: traces, metrics, failures, latency, and the evidence needed to improve the system 05 deployment is where the system becomes real: reliability, constraints, and the conditions that let people actually depend on it the model sits inside this architecture the AI engineer connects every layer into one operating loop: build → retrieve → act → observe → ship save this, then build your solo business with an AI employee ⭣show more

beamnxw ./

7,993 subscribers

13,505 views • 11 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

this is pure f*cking trasure 10 AI deep dives worth keeping in your second brain context. long-horizon agents. tool contracts. real-world experiments. containment. protocols. research. builder education 01 Effective Context Engineering ▸ 02 Effective Harnesses for Long-Running Agents ▸ 03 Writing Effective Tools for Agents ▸ 04 Project Vend: Phase Two ▸ 05 Project Pilot ▸ 06 How We Contain Claude ▸ 07 Model Context Protocol ▸ 08 OpenAI Research Index ▸ 09 OpenAI Academy ▸ 10 Google AI for Developers ▸ the loop: shape the context → build the harness → design the tool → test the system → contain the blast radius → ship save this, then build your solo business with an AI employee ⭣

this is pure f*cking trasure 10 AI deep dives worth keeping in your second brain context. long-horizon agents. tool contracts. real-world experiments. containment. protocols. research. builder education 01 Effective Context Engineering ▸ 02 Effective Harnesses for Long-Running Agents ▸ 03 Writing Effective Tools for Agents ▸ 04 Project Vend: Phase Two ▸ 05 Project Pilot ▸ 06 How We Contain Claude ▸ 07 Model Context Protocol ▸ 08 OpenAI Research Index ▸ 09 OpenAI Academy ▸ 10 Google AI for Developers ▸ the loop: shape the context → build the harness → design the tool → test the system → contain the blast radius → ship save this, then build your solo business with an AI employee ⭣

beamnxw ./

32,623 views • 12 days 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 • 1 month ago

If you are trying to understand where AI agents are going, learn harness engineering. A capable model is only one part of an agent system. Once the model begins reading files, calling tools, modifying state and working across many steps, the quality of the system depends increasingly on the software around it. Consider a coding agent working through a large repository. The model can decide that it needs to inspect a file, search for a symbol, make an edit or run a test, but those decisions do not execute themselves. The surrounding runtime has to decide which resources are available, whether the requested action is permitted, how the operation should be performed, what result should be retained, and what information should be presented to the model on the next step. This becomes harder as the run gets longer. As history accumulates, replaying everything can become costly and less effective. The harness has to decide what should remain in context, what should be summarized or retrieved later, and what belongs in persistent state outside the context window. Execution has similar problems. A long-running agent may need to survive an interruption, avoid repeating completed work, enforce permissions around consequential actions, and preserve enough history to reconstruct what happened when the final result is wrong. These are harness problems. The harness is the layer that manages context, tools, execution, state, checkpoints, limits and traces around the model. Harness engineering is the work of designing and improving that layer. Engineers inspect execution traces, evaluate agents on representative tasks, look for recurring failure modes, and then change things such as context selection, tool interfaces, state handling or execution controls. That last part matters because agent failures are often not fixed by changing the model. Sometimes the useful change is in what the model sees, how a tool is exposed, what state is preserved, or what the runtime does after a failed step. As agents take on longer tasks, the demands on this surrounding software grow. Model capability remains essential, but harness engineering is what turns that capability into an execution process that can be controlled, inspected, tested and improved.

If you are trying to understand where AI agents are going, learn harness engineering. A capable model is only one part of an agent system. Once the model begins reading files, calling tools, modifying state and working across many steps, the quality of the system depends increasingly on the software around it. Consider a coding agent working through a large repository. The model can decide that it needs to inspect a file, search for a symbol, make an edit or run a test, but those decisions do not execute themselves. The surrounding runtime has to decide which resources are available, whether the requested action is permitted, how the operation should be performed, what result should be retained, and what information should be presented to the model on the next step. This becomes harder as the run gets longer. As history accumulates, replaying everything can become costly and less effective. The harness has to decide what should remain in context, what should be summarized or retrieved later, and what belongs in persistent state outside the context window. Execution has similar problems. A long-running agent may need to survive an interruption, avoid repeating completed work, enforce permissions around consequential actions, and preserve enough history to reconstruct what happened when the final result is wrong. These are harness problems. The harness is the layer that manages context, tools, execution, state, checkpoints, limits and traces around the model. Harness engineering is the work of designing and improving that layer. Engineers inspect execution traces, evaluate agents on representative tasks, look for recurring failure modes, and then change things such as context selection, tool interfaces, state handling or execution controls. That last part matters because agent failures are often not fixed by changing the model. Sometimes the useful change is in what the model sees, how a tool is exposed, what state is preserved, or what the runtime does after a failed step. As agents take on longer tasks, the demands on this surrounding software grow. Model capability remains essential, but harness engineering is what turns that capability into an execution process that can be controlled, inspected, tested and improved.

Tech with Mak

46,947 views • 3 days ago

this is f*cking gold Google engineers explained how to make AI rewrite an agent’s system prompt against failing tests. a failed check becomes the next repair job. the regression suite watches for whatever that repair breaks. even the instructions become something you can test and improve. Agent = Model + Harness. the independently compiled page here maps the broader system into six parts: guides carry project rules, constraints and lessons from past failures > sensors check the work through tests, linters and validators > the loop runs the task, checks the result, retries within limits and escalates > memory preserves state, artifacts and decisions across runs > permissions control tools, writes and actions requiring approval > observability records what happened, what it cost and where it failed an agent changes a build file and announces “done.” the check looks for evidence that it actually ran the validator. if that behavior is missing, you have a specific failure to target. adjust the instructions. rerun the evaluations. check whether the improvement holds without breaking existing behavior. now a prompt change has a test history. a recurring mistake has a regression check. the next model upgrade has something concrete to pass. bookmark the diagram. give “done” a test it has to pass.

this is f*cking gold Google engineers explained how to make AI rewrite an agent’s system prompt against failing tests. a failed check becomes the next repair job. the regression suite watches for whatever that repair breaks. even the instructions become something you can test and improve. Agent = Model + Harness. the independently compiled page here maps the broader system into six parts: guides carry project rules, constraints and lessons from past failures > sensors check the work through tests, linters and validators > the loop runs the task, checks the result, retries within limits and escalates > memory preserves state, artifacts and decisions across runs > permissions control tools, writes and actions requiring approval > observability records what happened, what it cost and where it failed an agent changes a build file and announces “done.” the check looks for evidence that it actually ran the validator. if that behavior is missing, you have a specific failure to target. adjust the instructions. rerun the evaluations. check whether the improvement holds without breaking existing behavior. now a prompt change has a test history. a recurring mistake has a regression check. the next model upgrade has something concrete to pass. bookmark the diagram. give “done” a test it has to pass.

NO1ennn

71,256 views • 15 days ago

holy sh*t, someone mapped an entire company into 388 AI agent skills every solo builder can steal the workflow this repo covers 20 domains across engineering, product, marketing, finance, sales, compliance and research the patterns: → challenge your architecture with a CTO persona → turn customer research into a product spec → build with engineering and DevOps skills → run QA and security checks before launch → plan content, SEO, pricing and distribution → model budgets and SaaS metrics → prepare compliance evidence as you grow the architecture: skills define how → agents define the job → personas shape decisions → orchestration connects the work the part solo builders should steal: idea → research → spec → build → test → launch → sell one person can run the whole sequence with a clear job for their agent at every step save this, then build a second brain for your company⭣

holy sh*t, someone mapped an entire company into 388 AI agent skills every solo builder can steal the workflow this repo covers 20 domains across engineering, product, marketing, finance, sales, compliance and research the patterns: → challenge your architecture with a CTO persona → turn customer research into a product spec → build with engineering and DevOps skills → run QA and security checks before launch → plan content, SEO, pricing and distribution → model budgets and SaaS metrics → prepare compliance evidence as you grow the architecture: skills define how → agents define the job → personas shape decisions → orchestration connects the work the part solo builders should steal: idea → research → spec → build → test → launch → sell one person can run the whole sequence with a clear job for their agent at every step save this, then build a second brain for your company⭣

beamnxw ./

94,590 views • 2 days ago

THE LOOP ENGINEERING SETUP THAT LETS CLAUDE RUN YOUR WORK FOR HOURS WITHOUT YOU you sit there babysitting it prompt by prompt other people set the loop up once and let Claude plan, act, verify and fix its own work with nobody at the keyboard that gap is the whole skill of loop engineering the 3 resources that actually teach it, in the order i'd read them: > Claude's "Getting started with loops" - the cleanest entry point, straight from the Claude team ↳ > Claude loop engineering: how to build an agent that works while you sleep - the full roadmap from a single prompt to a loop that runs overnight ↳ > the Loop Engineering orange book - the deep conceptual breakdown, for when you want the whole mental model ↳ entry point, then practice, then the concept. that order saves you a week learn this and the work that eats your whole day starts running without you

THE LOOP ENGINEERING SETUP THAT LETS CLAUDE RUN YOUR WORK FOR HOURS WITHOUT YOU you sit there babysitting it prompt by prompt other people set the loop up once and let Claude plan, act, verify and fix its own work with nobody at the keyboard that gap is the whole skill of loop engineering the 3 resources that actually teach it, in the order i'd read them: > Claude's "Getting started with loops" - the cleanest entry point, straight from the Claude team ↳ > Claude loop engineering: how to build an agent that works while you sleep - the full roadmap from a single prompt to a loop that runs overnight ↳ > the Loop Engineering orange book - the deep conceptual breakdown, for when you want the whole mental model ↳ entry point, then practice, then the concept. that order saves you a week learn this and the work that eats your whole day starts running without you

Mr. Buzzoni

18,365 views • 22 days ago

Kimi K3 + GPT-6 Astra can become something bigger than two agents: a Two-Brain AI Operating System the formula: Two-Brain OS = Research Brain + Execution Brain + Shared State + Router + Tools + Verification not two models doing the same job. two specialized brains connected through one persistent system step 1 -> Kimi K3 becomes the research brain. complex research, source comparison, long-context synthesis and strategic planning happen here. its job is to explore the problem and compress the findings into a clear plan. step 2 -> GPT-6 Astra becomes the execution brain. it receives the plan, writes code, operates tools, creates artifacts and turns decisions into finished work. step 3 -> build a shared state layer. store the objective, evidence, decisions, constraints, failed attempts and next action outside the chat. both brains always know what happened and where the system should continue. step 4 -> add the router. uncertainty and open-ended questions move to Kimi K3. execution, tool use and deterministic tasks move to GPT-6 Astra. every job reaches the brain designed to handle it. step 5 -> create the handoff loop: research -> plan -> execute -> inspect -> update state -> continue. if execution reveals missing information, the task returns to Kimi. if the plan is ready, Astra takes control again. step 6 -> verify before completion. tests, source checks, constraints and explicit success criteria decide whether the result ships or returns to the correct brain with a clear failure signal. that is the difference between using two AI models and building a Two-Brain AI Operating System. Kimi K3 expands the search space. GPT-6 Astra converts it into action. shared state preserves progress, the router controls every handoff, tools execute the work and verification decides when the system is actually finished. one model can generate an answer. two specialized brains connected through memory, routing and verification can run an entire workflow. the full Kimi K3 + GPT-6 Astra Two-Brain OS breakdown is below ↓

Kimi K3 + GPT-6 Astra can become something bigger than two agents: a Two-Brain AI Operating System the formula: Two-Brain OS = Research Brain + Execution Brain + Shared State + Router + Tools + Verification not two models doing the same job. two specialized brains connected through one persistent system step 1 -> Kimi K3 becomes the research brain. complex research, source comparison, long-context synthesis and strategic planning happen here. its job is to explore the problem and compress the findings into a clear plan. step 2 -> GPT-6 Astra becomes the execution brain. it receives the plan, writes code, operates tools, creates artifacts and turns decisions into finished work. step 3 -> build a shared state layer. store the objective, evidence, decisions, constraints, failed attempts and next action outside the chat. both brains always know what happened and where the system should continue. step 4 -> add the router. uncertainty and open-ended questions move to Kimi K3. execution, tool use and deterministic tasks move to GPT-6 Astra. every job reaches the brain designed to handle it. step 5 -> create the handoff loop: research -> plan -> execute -> inspect -> update state -> continue. if execution reveals missing information, the task returns to Kimi. if the plan is ready, Astra takes control again. step 6 -> verify before completion. tests, source checks, constraints and explicit success criteria decide whether the result ships or returns to the correct brain with a clear failure signal. that is the difference between using two AI models and building a Two-Brain AI Operating System. Kimi K3 expands the search space. GPT-6 Astra converts it into action. shared state preserves progress, the router controls every handoff, tools execute the work and verification decides when the system is actually finished. one model can generate an answer. two specialized brains connected through memory, routing and verification can run an entire workflow. the full Kimi K3 + GPT-6 Astra Two-Brain OS breakdown is below ↓

Alex

23,962 views • 17 days ago

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Daniel San

12,514 views • 3 months ago

NO WAY. Someone is basically building a MANAGER for your AI agents. You give it one objective. It briefs Claude, Codex + the agents you choose, keeps them on the same context and coordinates the work. This is Jarvix. And I had to dig into this: 🧵 #JarvixOS

NO WAY. Someone is basically building a MANAGER for your AI agents. You give it one objective. It briefs Claude, Codex + the agents you choose, keeps them on the same context and coordinates the work. This is Jarvix. And I had to dig into this: 🧵 #JarvixOS

EyeingAI

37,574 views • 1 month ago

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

Marvin

24,954 views • 3 months ago

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

Gipp 🦅

11,709 views • 2 months ago

someone just open-sourced the entire "loop engineering" playbook. for free. 8.6k stars on github for loop engineering not prompts. loops. everything you need to build autonomous AI systems: → scheduling → memory & state → planning → sub-agents → verification → worktrees → MCP → stop conditions → safety guardrails → observability → cost tracking notice something? none of these are prompts. they're the systems wrapped around the model. that's where AI engineering is heading. we're moving from: Prompt Engineering → Context Engineering → Harness Engineering → Loop Engineering soon you'll hear people talking about Graph Engineering too. because once one loop works... the next challenge is coordinating hundreds of them. that's exactly what I explain in: save this. I think "loop engineering" is about to become one of the most important concepts in AI.

someone just open-sourced the entire "loop engineering" playbook. for free. 8.6k stars on github for loop engineering not prompts. loops. everything you need to build autonomous AI systems: → scheduling → memory & state → planning → sub-agents → verification → worktrees → MCP → stop conditions → safety guardrails → observability → cost tracking notice something? none of these are prompts. they're the systems wrapped around the model. that's where AI engineering is heading. we're moving from: Prompt Engineering → Context Engineering → Harness Engineering → Loop Engineering soon you'll hear people talking about Graph Engineering too. because once one loop works... the next challenge is coordinating hundreds of them. that's exactly what I explain in: save this. I think "loop engineering" is about to become one of the most important concepts in AI.

Rahul

65,446 views • 2 months ago

this is pure f*cking treasure 20 skills for AI agents with 1.99M+ combined stars an agent is not a model. it is a model plus everything you bolt onto it. these are the bolts. five clusters, twenty repos, all open source, all free. ORCHESTRATION · many agents, one plan : > hermes-agent · 247k > AutoGPT · 187k · > MetaGPT · 70k · > autogen · 61k · > crewAI · 59k · RUNTIME / GRAPH · the loop underneath : > langchain · 147k · > deer-flow · 83k · > langgraph · 42k · > deepagents · 30k · > openai-agents-python · 25k · WEB / BROWSER · reach the open internet : > firecrawl · 181k · > browser-use · 115k · > gemini-cli · 107k · MEMORY / RAG · what it keeps between runs : > ragflow · 91k · > mem0 · 66k · > llama_index · 50k · SHIP IT · turn it into a product : > n8n · 188k · > dify · 140k · > TradingAgents · 107k · > adk-python · 22k · most people pick one framework and stop there. that is the mistake. the stack is orchestration on top, a graph runtime under it, browser and memory on the sides, and one deploy layer that makes it a product instead of a demo. every layer above is already written. you are assembling, not inventing. the gap is one weekend wide.

this is pure f*cking treasure 20 skills for AI agents with 1.99M+ combined stars an agent is not a model. it is a model plus everything you bolt onto it. these are the bolts. five clusters, twenty repos, all open source, all free. ORCHESTRATION · many agents, one plan : > hermes-agent · 247k > AutoGPT · 187k · > MetaGPT · 70k · > autogen · 61k · > crewAI · 59k · RUNTIME / GRAPH · the loop underneath : > langchain · 147k · > deer-flow · 83k · > langgraph · 42k · > deepagents · 30k · > openai-agents-python · 25k · WEB / BROWSER · reach the open internet : > firecrawl · 181k · > browser-use · 115k · > gemini-cli · 107k · MEMORY / RAG · what it keeps between runs : > ragflow · 91k · > mem0 · 66k · > llama_index · 50k · SHIP IT · turn it into a product : > n8n · 188k · > dify · 140k · > TradingAgents · 107k · > adk-python · 22k · most people pick one framework and stop there. that is the mistake. the stack is orchestration on top, a graph runtime under it, browser and memory on the sides, and one deploy layer that makes it a product instead of a demo. every layer above is already written. you are assembling, not inventing. the gap is one weekend wide.

NO1ennn

21,039 views • 10 days ago

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

245,379 views • 2 months ago

Building AI agents is finally simple — and Airia is leading the way. I’ve been testing Airia AI , enterprise AI orchestration platform that unifies every model, workflow, and data source into one secure environment. Whether you’re a developer, analyst, creator, or enterprise leader, Airia makes it incredibly easy to build powerful AI agents — without wrestling with multiple tools or complex integrations. Using the no-code builder, you can drag-and-drop actions, connect data, choose your LLM, and launch an agent in minutes. Then run it live, publish it, and even share it with the Airia Community, home to 2,500+ pre-built agents you can use or remix. If you want to automate workflows, prototype faster, or explore real enterprise AI use cases, Airia is the place to start. 👉 Build your first agent today: 👉 Explore the community: #Airia #AgenticAI #AIOrchestration #AIAgents #AIWorkflow #DigitalTransformation

Building AI agents is finally simple — and Airia is leading the way. I’ve been testing Airia AI , enterprise AI orchestration platform that unifies every model, workflow, and data source into one secure environment. Whether you’re a developer, analyst, creator, or enterprise leader, Airia makes it incredibly easy to build powerful AI agents — without wrestling with multiple tools or complex integrations. Using the no-code builder, you can drag-and-drop actions, connect data, choose your LLM, and launch an agent in minutes. Then run it live, publish it, and even share it with the Airia Community, home to 2,500+ pre-built agents you can use or remix. If you want to automate workflows, prototype faster, or explore real enterprise AI use cases, Airia is the place to start. 👉 Build your first agent today: 👉 Explore the community: #Airia #AgenticAI #AIOrchestration #AIAgents #AIWorkflow #DigitalTransformation

Adarsh Chetan

269,446 views • 10 months ago

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

John Turner

21,029 views • 12 days ago

A 27-year-old from China made $150,000 after finding the real bottleneck behind AI model accounts. It was not generating another face. It was producing enough content to keep the face alive. Most AI girls look convincing in one image, then disappear because the owner cannot make enough Reels, TikToks and Shorts to keep feeding the account. The audience moves on before the paid profile has enough traffic to work. He solved that with a simple production loop. One image of the AI model goes into the system. Motion and dance templates turn it into short videos. The same character can appear in dozens of new clips without filming, scheduling shoots or rebuilding the face every time. That made mass posting possible. The clips generated organic attention, while the profile link moved interested viewers into paid subscriptions and affiliate offers. Most people think the opportunity is creating prettier AI girls. He made $150,000 by solving what happens after the first image is finished.

Kiyoro

19,785 views • 2 months ago

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

Turn complex docs into clean, LLM-ready data! Every AI company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!

Akshay 🚀

58,215 views • 10 months ago

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

We are getting absurdly close to the point where “learning Blender” means learning how to direct an AI. A shot like this looks soft and playful on the surface, but under it is the usual 3D pain: modeling, layout, materials, lighting, atmosphere, animation, and endless tiny fixes until the frame stops looking dead. That is why Kimi K3 matters. With Blender MCP, you can describe a scene like a robotic goat walking through a dreamy field and let the model help build the environment, place the camera, shape the materials, script the motion, and iterate inside the real Blender project. The real shift is not text-to-image. It is text-to-workflow. Kimi K3 does not just give you a pretty output and disappear. It can help move the actual scene from rough setup to something that looks art-directed. Soon the hardest part of 3D will not be the software. It will be whether your imagination is good enough to deserve tools like this.

Rina

45,651 views • 2 months ago

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 views • 2 months ago