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.

Finding 1: Harness affects cost more than correctness. Fable 5 can cost twice as much for a 1.1-point gain in success rate. On SWE-bench Lite: - Claude Code: 97.8% accuracy, $1.33/rollout - Pi: 96.7% accuracy, $0.67/rollout While Claude Code reaches the highest success rate on the SWE-bench Lite frontier,... show more

Melissa Pan

5,229 subscribers

14,563 views • 6 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

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

The easiest way to find out which models you can run on your computer: Just run: - 𝗻𝗽𝗺 𝗶 -𝗴 @𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲𝗱𝗲𝘃/𝗰𝗹𝗶 - 𝗺𝗮𝗴𝗻𝗶𝘁𝘂𝗱𝗲 𝘀𝗲𝘁𝘂𝗽 It profiles your machine and ranks the models across: - Speed - Accuracy - Intelligence - Memory required Finally, you can choose your favorite harness (Pi, OpenCode, Claude Code, Codex, etc.) to run with it. Get started here: (don't forget to star 🌟) I also wrote a detailed article on running your favorite harnesses with local models. The article is quoted below.

Akshay 🚀

356,204 views • 18 days ago

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.

Avi Chawla

44,124 views • 2 months ago

If you spend $2,000 a month and pay for ChatGPT and Claude, this card hands you around $1,000 back a year - and almost nobody has done the math > 3% base cashback on Core, 5% on your AI subscriptions > Bump to Platinum and AI cashback jumps to 10%, with Claude Pro and ChatGPT Plus bundled in - roughly $500 of subscriptions covered before you count a single cashback dollar Access Code: W6TRRM That is money coming back on spending you were doing anyway. Groceries, subscriptions, the AI tools you already pay for One honest catch I cover in the article - the cashback pays in $XPL, a volatile token and the rate is capped and laddered, not flat. So run your own numbers, do not take a headline rate as gospel But the structure is real. Every other card treats your AI bill as ordinary spend. This one turns it into your highest earning category Full math, every tier, every tradeoff, in the article

If you spend $2,000 a month and pay for ChatGPT and Claude, this card hands you around $1,000 back a year - and almost nobody has done the math > 3% base cashback on Core, 5% on your AI subscriptions > Bump to Platinum and AI cashback jumps to 10%, with Claude Pro and ChatGPT Plus bundled in - roughly $500 of subscriptions covered before you count a single cashback dollar Access Code: W6TRRM That is money coming back on spending you were doing anyway. Groceries, subscriptions, the AI tools you already pay for One honest catch I cover in the article - the cashback pays in $XPL, a volatile token and the rate is capped and laddered, not flat. So run your own numbers, do not take a headline rate as gospel But the structure is real. Every other card treats your AI bill as ordinary spend. This one turns it into your highest earning category Full math, every tier, every tradeoff, in the article

Valentin

13,123 views • 1 month ago

people often ask me how well does clipping work imo clipping has a 100% success rate because it's so new i don't think people truly understand what it is it's essentially just distributing a viral format at scale all we do is find a plethora of formats that go viral and convert extremely well you either find that yourself by doing reseach if ur niche is well developed or hire creators on a retainer to test out formats to find that if your niche doesnt have a lot of viral content it all really just comes down to finding viral formats consistantly and having clippers replicate content in that format hundreds of times once you find the winner, you put it on Content Rewards and you scale it up it's truly impossible to fail when a format is a winner and you have so much control over that you will obviously never push a format that doesn't convert so technically it has a 100% success rate

people often ask me how well does clipping work imo clipping has a 100% success rate because it's so new i don't think people truly understand what it is it's essentially just distributing a viral format at scale all we do is find a plethora of formats that go viral and convert extremely well you either find that yourself by doing reseach if ur niche is well developed or hire creators on a retainer to test out formats to find that if your niche doesnt have a lot of viral content it all really just comes down to finding viral formats consistantly and having clippers replicate content in that format hundreds of times once you find the winner, you put it on Content Rewards and you scale it up it's truly impossible to fail when a format is a winner and you have so much control over that you will obviously never push a format that doesn't convert so technically it has a 100% success rate

Alex

12,424 views • 4 months ago

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.

this is the worst local ai will ever be. it only gets better from here. if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think. i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now. if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried. the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness. and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at Nous Research. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference. own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored. just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.

Sudo su

58,717 views • 6 months 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 🚀

245,252 views • 2 months ago

SpaceXai just made grok 4.5 FREE in your coding agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closes

SpaceXai just made grok 4.5 FREE in your coding agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closes

painn

152,350 views • 2 months ago

you can run claude code inside antigravity completely Free with zero credit card and no rate limits 😳 use openrouter’s free models + antigravity. no anthropic bill. no paid api keys. takes 10 minutes to set up. what you get during this setup: - full claude code agent experience - strong coding models (including deepseek-r1, qwen2.5-coder, llama-4, grok-4 free tier) - antigravity’s clean workspace and sandbox - unlimited usage (as long as you stay on free models) - easy model swapping - zero cost full setup guide (100% free): step 1: install antigravity -go to and install it -create a new workspace step 2: install claude code - inside antigravity, install the claude code extension from the marketplace - open the built-in terminal step 3: create openrouter free account -go to - sign up with google (no card needed) - go to keys and create a new api key step 4: set the environment variables -in antigravity terminal run: export ANTHROPIC_API_KEY=sk-or-xxx export OPENROUTER_API_KEY=sk-or-xxx step 5: launch claude code with free model -run this command: claude-code --model deepseek/deepseek-r1:free or try: qwen/qwen2.5-coder:free if you already have antigravity? skip straight to step 2. after 10 minutes you’ll have a full agentic coding setup running for free. this is currently one of the cheapest ways to run serious coding agents in 2026. bookmark this before they limit the free models.

you can run claude code inside antigravity completely Free with zero credit card and no rate limits 😳 use openrouter’s free models + antigravity. no anthropic bill. no paid api keys. takes 10 minutes to set up. what you get during this setup: - full claude code agent experience - strong coding models (including deepseek-r1, qwen2.5-coder, llama-4, grok-4 free tier) - antigravity’s clean workspace and sandbox - unlimited usage (as long as you stay on free models) - easy model swapping - zero cost full setup guide (100% free): step 1: install antigravity -go to and install it -create a new workspace step 2: install claude code - inside antigravity, install the claude code extension from the marketplace - open the built-in terminal step 3: create openrouter free account -go to - sign up with google (no card needed) - go to keys and create a new api key step 4: set the environment variables -in antigravity terminal run: export ANTHROPIC_API_KEY=sk-or-xxx export OPENROUTER_API_KEY=sk-or-xxx step 5: launch claude code with free model -run this command: claude-code --model deepseek/deepseek-r1:free or try: qwen/qwen2.5-coder:free if you already have antigravity? skip straight to step 2. after 10 minutes you’ll have a full agentic coding setup running for free. this is currently one of the cheapest ways to run serious coding agents in 2026. bookmark this before they limit the free models.

painn

32,057 views • 3 months ago

A lot of DeFi borrowers these days aren’t really scared of high rates. They’re scared of rates that can change while they’re sleeping. You borrow USDC at 3%, utilization jumps overnight, and suddenly your cost looks nothing like what you expected. This cycle the real damage for a lot of people wasn’t liquidation. It was never knowing what their borrow cost would be next month. That’s why the latest numbers from TermMax | Fixed Rate Borrowing & Lending stood out. They’re showing fixed USDC borrow rates against cbBTC and WBTC at roughly 2.3% through May 31 and 2.5% through June 30, with July already looking cheaper than most big floating pools on Ethereum. And the rate stays locked the whole time. Most people’s first reaction is still “fixed rates are supposed to be more expensive, right?” These ones are competitive while removing the guesswork. The setup is straightforward. One collateral type, fixed term, risk visible before you borrow. You already know what you’re posting, how long you’re borrowing for, and what the cost should be during that window. No waking up to a completely different number. Floating rate markets keep moving. Liquidity changes, demand changes, utilization changes. A position that feels fine today can reprice hard a few days later. That constant uncertainty becomes its own hidden cost when you’re actually trying to manage cash flow. What they keep saying makes sense once you’ve felt it: known rate, known term, known risk. The risk doesn’t vanish, but at least you see it upfront instead of getting surprised later. Of course there are tradeoffs. Lock in now and rates could drop, leaving you paying more than you might have otherwise. Liquidity and flexibility probably won’t match the biggest variable rate pools either. Still, the mindset in DeFi lending feels like it’s shifting. A year or two ago everyone was just chasing the lowest APY. Now more people seem to care whether they can actually understand what they’re stepping into before they commit. With tokenized assets getting real traction and big projections coming out, that kind of predictability might start mattering more than pure yield chasing. You can actually plan around it. Tired of rate surprises wrecking your positions? Fixed terms like this change how you think about borrowing.

A lot of DeFi borrowers these days aren’t really scared of high rates. They’re scared of rates that can change while they’re sleeping. You borrow USDC at 3%, utilization jumps overnight, and suddenly your cost looks nothing like what you expected. This cycle the real damage for a lot of people wasn’t liquidation. It was never knowing what their borrow cost would be next month. That’s why the latest numbers from TermMax | Fixed Rate Borrowing & Lending stood out. They’re showing fixed USDC borrow rates against cbBTC and WBTC at roughly 2.3% through May 31 and 2.5% through June 30, with July already looking cheaper than most big floating pools on Ethereum. And the rate stays locked the whole time. Most people’s first reaction is still “fixed rates are supposed to be more expensive, right?” These ones are competitive while removing the guesswork. The setup is straightforward. One collateral type, fixed term, risk visible before you borrow. You already know what you’re posting, how long you’re borrowing for, and what the cost should be during that window. No waking up to a completely different number. Floating rate markets keep moving. Liquidity changes, demand changes, utilization changes. A position that feels fine today can reprice hard a few days later. That constant uncertainty becomes its own hidden cost when you’re actually trying to manage cash flow. What they keep saying makes sense once you’ve felt it: known rate, known term, known risk. The risk doesn’t vanish, but at least you see it upfront instead of getting surprised later. Of course there are tradeoffs. Lock in now and rates could drop, leaving you paying more than you might have otherwise. Liquidity and flexibility probably won’t match the biggest variable rate pools either. Still, the mindset in DeFi lending feels like it’s shifting. A year or two ago everyone was just chasing the lowest APY. Now more people seem to care whether they can actually understand what they’re stepping into before they commit. With tokenized assets getting real traction and big projections coming out, that kind of predictability might start mattering more than pure yield chasing. You can actually plan around it. Tired of rate surprises wrecking your positions? Fixed terms like this change how you think about borrowing.

Domingo_gou | 火币赚币🐬

11,892 views • 4 months ago

THIS SHELF OF MAC MINIS REPLACES $4,080 A YEAR IN AI SUBSCRIPTIONS 00:02 the camera pans across a shelf of stacked Mac minis and the trick is obvious: that silent little farm runs the models you rent every month most people pay 7 companies for AI and use 3 of the tools. they forget the rest on the credit card and call it a stack the Mac mini M4 ends that. one shared memory pool means a $599 box runs 7B and 8B models faster than Windows machines that cost twice as much ollama pull, one command. open webui in one docker line. point Claude Code at localhost and it just works it draws 10 to 30 watts, sits silent next to a router, and runs 24/7 for $3 a month in power it pays back a $20 ChatGPT Plus sub in 3 months, then saves you $4,000 a year while the frontier still rents you compute every month you wait is another $340 gone for compute that fits on a shelf

THIS SHELF OF MAC MINIS REPLACES $4,080 A YEAR IN AI SUBSCRIPTIONS 00:02 the camera pans across a shelf of stacked Mac minis and the trick is obvious: that silent little farm runs the models you rent every month most people pay 7 companies for AI and use 3 of the tools. they forget the rest on the credit card and call it a stack the Mac mini M4 ends that. one shared memory pool means a $599 box runs 7B and 8B models faster than Windows machines that cost twice as much ollama pull, one command. open webui in one docker line. point Claude Code at localhost and it just works it draws 10 to 30 watts, sits silent next to a router, and runs 24/7 for $3 a month in power it pays back a $20 ChatGPT Plus sub in 3 months, then saves you $4,000 a year while the frontier still rents you compute every month you wait is another $340 gone for compute that fits on a shelf

Fokki

12,933 views • 2 months ago

Claude Code + Google Stitch 2.0 is f*cking cracked 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)

Mike Futia

126,469 views • 6 months ago

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns that leverage different agent backends (claude, codex, pi, hermes,...). It's a meta-harness approach that unlocks new forms of test-time compute. Example of use cases it supports: > LLM councils to get different perspectives from LLMs or plan more intensively > Dynamically routing tasks to different agents based on needs (e.g., cost efficiency and optimal intelligence) > Advisor/Judge + executor workflows and pretty much any complex graph-based pattern required by the task. I find it especially useful for long-running work and code reviewing. > Agent teams that talk to each other if needed for the task. I like to use this for AI editing, artifact creation, and other creative tasks. And I am sure it supports so many things that I haven't discovered yet. I got inspired by the dynamic workflow feature released by the Claude Code team. I had actually built it earlier this year but wanted to generalize it across different agent backends. I think this is going to become more popular in the coming days. I will share more of my findings soon.

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns that leverage different agent backends (claude, codex, pi, hermes,...). It's a meta-harness approach that unlocks new forms of test-time compute. Example of use cases it supports: > LLM councils to get different perspectives from LLMs or plan more intensively > Dynamically routing tasks to different agents based on needs (e.g., cost efficiency and optimal intelligence) > Advisor/Judge + executor workflows and pretty much any complex graph-based pattern required by the task. I find it especially useful for long-running work and code reviewing. > Agent teams that talk to each other if needed for the task. I like to use this for AI editing, artifact creation, and other creative tasks. And I am sure it supports so many things that I haven't discovered yet. I got inspired by the dynamic workflow feature released by the Claude Code team. I had actually built it earlier this year but wanted to generalize it across different agent backends. I think this is going to become more popular in the coming days. I will share more of my findings soon.

elvis

32,623 views • 2 months ago

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

This lawyer made $150,000 selling portable offline AI. It analyzes docs that can’t legally be shown on the web. The whole setup costs $50 and he sells it for $999. Here's how to make one step-by-step: You need 4 things: → Raspberry Pi 5 (8GB) → PiSugar 3 Plus battery → Whisplay HAT for the screen and mic → 64GB SD card. Total cost on Ali is around $50 to $90 if you wait for the right deals. 1. Write Raspberry Pi OS Lite 64-bit to the SD card using Raspberry Pi Imager. 2. Stack the PiSugar battery underneath the Pi, snap the Whisplay HAT on top, insert the SD card, and boot the device. 3. Open the terminal and install Ollama with one command: curl -fsSL | sh 4. Pull a model that actually runs on the Pi without choking: ollama pull phi3:mini 5. Run the model and start chatting offline: ollama run phi3:mini The whole thing fits in your pocket, lasts 4 hours on battery, and never touches the internet once setup is done. The lawyer wraps his version in a custom case, preloads it with legal document analysis prompts, and sells it to law firms that can't legally process client data in the cloud. You can sell yours to doctors, accountants, government contractors, defense companies, or anyone else who handles data that legally cannot leave the building. Hardware cost: $50 to $90. Selling price: $500 to $1999

Coin Shot ☁️

200,352 views • 3 months ago

NEW HTML VIDEO SKILL: Claude can now make photo-grid promo video ads like these. These are very popular offer-style ads that work well for bottom-of-funnel conversions. Brands will often run these when they're doing seasonal sales, for example. It's pure HTML, so it's very cheap to make because there's no video generation cost. You can create dozens of variants very fast and then test them in Meta. All you have to do is install the skills and give Claude your brand website. This skill is insane - it'll make the entire Ad and give you a link where you can download the mp4 file. > If you want more variants, just mention in the prompt > If you have a specific concept in mind, just mention in the prompt > If you want any edits on the generated ad, just mention in the prompt Comment Goose and I'll DM you the skill (must be following so I can DM you)

Shiv

92,404 views • 2 months ago

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

Axel Bitblaze 🪓

48,825 views • 2 months ago

Claude Fable 5 + Claude Design is f*cking insane 🤯 Anthropic just dropped its most intelligent model ever, and the first thing I pointed it at was email design. I built a complete email campaign design in Claude Design, and the difference is night and day: tighter layouts, cleaner hierarchy, on-brand from the first generation. All inside Claude Design with Fable 5. Perfect for DTC brands and agencies who are still paying email agencies $3-5K/month for campaign designs that take 2 weeks to ship. If your campaign calendar is packed but every new email means briefing a designer, waiting on mockups, sending notes, and waiting again... This workflow eliminates the entire bottleneck: → Load your brand design system into Claude Design once (colors, fonts, logo, button styling) → Switch the model to Claude Fable 5 — Anthropic's new state-of-the-art model with the best vision of any AI → Prompt the campaign email section by section: header, hero, headline, offer block, CTA → Fable 5 nails layout and brand details that older models fumbled → Iterate inline — swap images, adjust styling, color-pick directly in the canvas → Export the finished email and hand off to your ESP No briefing a designer. No 2-week turnaround on a single campaign. No paying an agency $4K/month for 4 emails. What you get: → Campaign emails designed in minutes, not weeks → A reusable design system every new email pulls from automatically → Noticeably smarter design decisions from Fable 5's upgraded vision → Full inline editing before anything touches your ESP Built 100% with Claude Design + Claude Fable 5. I recorded a full walkthrough showing exactly how this works. Want it for free? > Like this post > Comment "FABLE" And I'll send it over (must be following so I can DM)

Mike Futia

43,201 views • 3 months ago

One thing I think AI developers underestimate: Your model isn't always your biggest risk. Your infrastructure is. A lot of AI apps work great in development… Until the provider you're relying on has an outage, rate limits your requests, or a model suddenly becomes unavailable. If your entire product depends on one AI provider, you've created a single point of failure. That's why I like the approach CometAPI is taking. Instead of locking your app to one vendor, it gives you access to 500+ AI models through a single OpenAI-compatible endpoint. That means you can: → switch models without rewriting your integration → build fallback routes for better reliability → compare models as new ones launch → avoid getting locked into a single provider For teams building with Claude Code, Cursor, AI agents, SaaS products, or automation tools, that flexibility matters a lot once you're in production. They're also shipping new models quickly. Recent additions include: • GPT-5.6 • Happy Horse 1.1 • Kling Video Plus recently released: • Gemini 3.1 Flash Lite Image • Claude Sonnet 5 Worth checking out if you're building AI products that need to stay reliable as the ecosystem moves fast. Try it here: #AI #LLM #Developers #OpenAI #Claude #Cursor #ClaudeCode #BuildInPublic

One thing I think AI developers underestimate: Your model isn't always your biggest risk. Your infrastructure is. A lot of AI apps work great in development… Until the provider you're relying on has an outage, rate limits your requests, or a model suddenly becomes unavailable. If your entire product depends on one AI provider, you've created a single point of failure. That's why I like the approach CometAPI is taking. Instead of locking your app to one vendor, it gives you access to 500+ AI models through a single OpenAI-compatible endpoint. That means you can: → switch models without rewriting your integration → build fallback routes for better reliability → compare models as new ones launch → avoid getting locked into a single provider For teams building with Claude Code, Cursor, AI agents, SaaS products, or automation tools, that flexibility matters a lot once you're in production. They're also shipping new models quickly. Recent additions include: • GPT-5.6 • Happy Horse 1.1 • Kling Video Plus recently released: • Gemini 3.1 Flash Lite Image • Claude Sonnet 5 Worth checking out if you're building AI products that need to stay reliable as the ecosystem moves fast. Try it here: #AI #LLM #Developers #OpenAI #Claude #Cursor #ClaudeCode #BuildInPublic

Shruti Codes

56,822 views • 2 months ago

somebody explain this because i refuse to accept it someone ran 48 scored trials and one agent beat a whole fleet of them on all 6 task families, at 0.93 cents a run against 1.9, while openai's best fleet shape was paying $0.008 for every single point of accuracy it bought i read it expecting a hit piece and found the opposite: the fleets that partitioned the dependency graph properly lifted pass rate 14% and cut wall-clock 2.10x on the same tasks, and one of them beat claude code with agent teams the thing that decides it has a name, Graph Engineering, and it is a property of the diagram rather than the model: - partition on the real dependency graph pulled from static analysis, never by folder or by file, because the gains land hardest on the most dependency-dense projects - isolate the structural hub files first, since those are the nodes every partition would otherwise have to share - measure the critical path and treat it as the floor, because a chain that genuinely feeds itself cannot be replaced by more workers and wrapping it in a scheduler does not shorten it - match the topology to the coupling instead of defaulting to parallel: on coupled work a static parallel shape drops below a single agent, so the mismatch is worse than no orchestration - remember each worker serialises its own subtasks, which adds edges inside every agent that were never in your plan - budget the fan-out before you fire it, because three agents already burn roughly three times the tokens and the multiplier compounds across sessions - check worker count against your rate limit, since fifteen workers at ten requests a second walk straight through a hundred-per-second ceiling and cascade - put a script gate in front of the planner: it costs 0.15 seconds and zero tokens, and it lets the expensive model skip 43 to 63% of the steps for at most 1.4 points of accuracy the catch is the coordination tax, and it scales with how clever the shape looks: 58% extra reasoning turns for independent workers, 263% decentralised, 285% centralised, and 515% for the hybrid setup everyone reaches for first the same paper found that hybrid then collapses hardest on tool-heavy work at a 0.452 success rate, while the plainer decentralised shape beat centralised outright despite carrying more overhead, because parallel efficiency is what survives bookmark this, the whole build sits in the article ↓

somebody explain this because i refuse to accept it someone ran 48 scored trials and one agent beat a whole fleet of them on all 6 task families, at 0.93 cents a run against 1.9, while openai's best fleet shape was paying $0.008 for every single point of accuracy it bought i read it expecting a hit piece and found the opposite: the fleets that partitioned the dependency graph properly lifted pass rate 14% and cut wall-clock 2.10x on the same tasks, and one of them beat claude code with agent teams the thing that decides it has a name, Graph Engineering, and it is a property of the diagram rather than the model: - partition on the real dependency graph pulled from static analysis, never by folder or by file, because the gains land hardest on the most dependency-dense projects - isolate the structural hub files first, since those are the nodes every partition would otherwise have to share - measure the critical path and treat it as the floor, because a chain that genuinely feeds itself cannot be replaced by more workers and wrapping it in a scheduler does not shorten it - match the topology to the coupling instead of defaulting to parallel: on coupled work a static parallel shape drops below a single agent, so the mismatch is worse than no orchestration - remember each worker serialises its own subtasks, which adds edges inside every agent that were never in your plan - budget the fan-out before you fire it, because three agents already burn roughly three times the tokens and the multiplier compounds across sessions - check worker count against your rate limit, since fifteen workers at ten requests a second walk straight through a hundred-per-second ceiling and cascade - put a script gate in front of the planner: it costs 0.15 seconds and zero tokens, and it lets the expensive model skip 43 to 63% of the steps for at most 1.4 points of accuracy the catch is the coordination tax, and it scales with how clever the shape looks: 58% extra reasoning turns for independent workers, 263% decentralised, 285% centralised, and 515% for the hybrid setup everyone reaches for first the same paper found that hybrid then collapses hardest on tool-heavy work at a 0.452 success rate, while the plainer decentralised shape beat centralised outright despite carrying more overhead, because parallel efficiency is what survives bookmark this, the whole build sits in the article ↓

Argona

32,932 views • 1 month ago

a guy scraped 5,000 Shopify stores. got the CMO contacts on Apollo. then did something nobody expected. didn't cold-email them a pitch deck. pasted their product links into Marketing Studio on Higgsfield. generated video ads for their own products. UGC, unboxing, product review, TV spot - their products, not his. then sent it to them. "hey - I made these for your product. no charge. if you want more, let's talk." response rate on a normal cold email: 1-3%. response rate when you send someone a free video ad of THEIR product: you can guess. Marketing Studio on Higgsfield, powered by Seedance 2.0. 9 formats per product link. you can upload a custom face and lock it across every video so the ads look like they came from a real brand ambassador. $0.347 per generation. the whole pitch costs less than a coffee. the math at scale: 5,000 stores. even at 5% conversion to a $200/month retainer. that's 250 clients x $200 = $50,000/month. fulfillment cost is a Marketing Studio subscription. the pitch is the videos already made for them.

Vadim

258,091 views • 5 months ago