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 frameworkshow more

let me save you 3 hours of head scratching.... if you're running local models like Qwen3.5-35B-A3B through Claude Code via llama.cpp's Anthropic endpoint, the chain will break every 3 to 5 minutes. tool call fails. flow stops. you reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness chokes on local inference latency. switch to OpenCode. same localhost endpoint. same model. same GPU. the chain doesn't break. the tradeoff: OpenCode sometimes loops. the model forgets what it already read and repeats the same tool call. but a loop you can interrupt. a broken chain kills your momentum and you start over. watch both side by side. proprietary agent vs open source agent. same 3B model. different failure modes. pick your poison.show more

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE... 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Moneyshow more

this is the next $100B opportunity in ai ,... most will miss it's harness engineering what this agentic engineer reveals is insane >The model is almost irrelevant. The harness is everything >every failure is a signal about what the environment needs. >when agent throughput far exceeds human attention, corrections are cheap and waiting is expensive most people will ignore and bookmark. be different.show more

Do you use Runway Gen-2 to make AI videos?... This is for you! I built a simple tool to help "extend" Runway videos beyond the 4 second clip limit. Just choose a video, and the tool will give you the final frame -- so that you can drop this back into Runway, and generate another AI video based on it. Let me know if this is useful to you! Link is at bottom of the video and it's live to try right now.show more

this is the important part to understand what is... going on. you can see the front wheel lose traction then the back of the car dips due to weight transfer. it was AFTER that the ICE agent draws his weapon.show more

This is how you unlock the next billion software... developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!show more

Probably you know them already, the tips works to... me are -Simplify the shapes of the character and animate first that simple forms -Create model sheets and trace it -Use the key draws to create the inbetweens -Sculpt a simple model, pose it and copy what you see (1/2) +show more

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.show more

Alright, now that we know *what* an agent is,... how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.show more

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an... all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!show more

seedance 2.0 + my v2 AI UGC prompting system... is giving insane results i spent the last 24 hours generating over 200 seedance 2.0 videos to figure out the best prompting framework system for AI UGC this video was made with 1 prompt and 1 tool, no editing was done to the video this was just a prompt to a video this is by far the best model i've ever used and the craziest part is that it can be fully automated this is the first time we can actually automate high quality ai ugc at this level bytedance owns tiktok so this model is trained on millions of high quality ugc videos. you just need to know how to extract that and call it in your prompt. we are so early... it's insaneshow more

2.2 million TikTok Shop Views Just one of the... 348+ videos my AI Agent made today The account is @seedsynergy This is a real life money printer 1. like 2. comment "AI AGENT" & 3. RT I'll send the info on the tool to you. (must be following me Ellie Jones )show more

Stanford researchers did it again. They just built the... agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.show more

The architecture of this new world model is one... of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.show more

This is the best AI agent-first notes app I've... found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.show more

Good UX design is more important than ever for... today’s AI. A model cannot achieve its full potential without the most fluid and intuitive interface. Here’s a first step towards the future of AI-in-the-loop artistic creation. Imagine making every tool in Photoshop feel like this.show more

The hate is justified. This whole run it back... gimmick is bad and brings down the whole momentum of the show. Even in Kayfabe , You have to be some kind of a dumbass to run it back instead of eliminating people. Roman knocked the yeet of your face and eliminated you from the Rumble and you are glazing him the next day ?? All that crashout and “im not just an entrance” is literally just a lie. You are the worst wrestler of all time brother.show more

you need to tattoo this Boris Cherny quote into... your brain: "coding is the easy part, it's knowing the domain that's the hard part" every week a new startup drops a launch video saying they "killed influencer marketing" or something but they don't get it. creating the thing is NOT the hard part it's understanding what thing you have to create, at what moment, and in what way and that takes years of pattern recognition from actually being in the arena and seeing what works AI can't shortcut that for youshow more

We were taught the derivative as a formula to... memorise. A definition to recite. A rule to apply. Something that "gives you the slope." But nobody told us what the formula was actually saying. Every symbol is a sentence. Every fraction is a question. Every limit is a story about getting closer and closer to something you can never quite touch. The top of the fraction? That's a change. A difference. A before and after. The bottom? That's how long you waited to see it. The limit? That's you, zooming in, refusing to settle for an approximation - chasing the truth all the way down to an interval so small it almost disappears. Put it all together, and you get the most honest question in calculus: How fast is something changing - right now, in this exact instant? Not on average. Not over a minute. Not eventually. Right now. That's it. That's the derivative. It's not a trick. It's not a rule. It's a beautifully precise way of asking a very human question: what's happening, in this moment? We spent years solving these. Maybe it's time we actually understood them.show more

Claude Fable 5 orchestrating Grok 4.5 is now my... favorite real workflow. all you need is this free Claude Code plugin that makes Grok the default implementer. Fable writes the specs and reviews every diff, Grok 4.5 does the typing through the Grok CLI. - Grok handles the volume, Fable handles the judgment - Every diff gets cross-vendor review for free - Specs run as parallel agents when they're independent I've been testing it for a few days and the part that sold me is watching Fable refuse to write code. It sends specs down, judges what comes back, and that's it. setup: 1. claude plugin marketplace add DannyMac180/fable-advisor && claude plugin install fable-advisor 2. Install the Grok CLI from then grok login 3. /model fable It's open source, so you can read the agent files and tweak the routing however you want.show more