Open-weight LongCat 2.0 matched GPT-5.5 level on agentic game... dev for $0! We ran Meituan's LongCat 2.0 against cloud frontier GPT-5.5 in Kilo CLI with their agent. Same task for both - build a retro Duck Hunt game in one game.html, improved over 3 agent iterations with duck waves, ammo and physics Outputs: LongCat 2.0: 70.3K tokens, $0.00 GPT-5.5: 64.9K tokens, $0.65 LongCat kept up on graphics, physics and game logic. Ducks fly and fall when hit, the dog fetches them, ammo counts down, the waves keep coming. Both ran clean and nothing clipped. The only difference was the bill - GPT cost $0.65, LongCat ran local for $0show more

LongCat performed Opus 4.8 and GPT 5.5 level on... real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!show more

New Claude Sonnet 5 performs at GPT 5.5 level... 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other modelshow more

1-bit Kimi K3 performs at Opus 5 level on... 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all the same task, to build a giant anvil drop test as a single HTML file with real physics Outputs: K3 1bit (local): 15.8K tokens, $0 API cost Kimi K3 (API): 15.3K tokens, $0.30 API cost Opus 5: 22.8K tokens, $0.77 API cost GPT 5.6: 14.5K tokens, $0.72 API cost All four got the physics right. But only Kimi made a working winch. The drum turns and the chain drags the flat car off the pad. Opus 5 drew the most detail, road markings and sparks on the hit. And you can run a model at this level on your own box now. That still feels insane to usshow more

Fable 5 totally crushed our new contest, but it... cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.show more

Grok 4.5 performed GPT Sol level for free! We... gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: -robot deathmatch, Tombstone vs Minotaur -a hydraulic press flattening stuff on a conveyor -a semi truck jumping a canyon Outputs: GPT-5.6 Sol: 12.9K tokens, $0.51 (~7 min) Grok 4.5: 10.8K tokens, $0 (~5 min) Muse Spark 1.1: 26.8K tokens, $0.12 (~7.5 min) GLM 5.2: 10.9K tokens, $0.02 (~12 min) Grok 4.5 handled all three scenes genuinely well and got surprisingly close to GPT-5.6 this round. On top of that, it ran on the free tier. GPT-5.6 Sol, the frontier model, put out solid but not standout work. GLM 5.2 rendered all three scenes for pennies, but it came out the roughest of the four. Meta's new Muse Spark burned the most tokens yet still stayed cheap, delivering an average result.show more

Liquid's LFM2.5-8B-A1B smashed OpenAI's gpt-oss-20b on tool calling We... ran both locally on a MacBook Pro M5 Max, 64GB, and gave each the same trip-planning request that only completes if the model fires all 7 tool calls - weather for 3 cities, two currency conversions, an email and a reminder Outputs: LFM2.5-8B-A1B: 4.8 GB RAM usage, 7/7 tool-calls, 266 tok/s, 6.9s OpenAI gpt-oss-20b: 11 GB RAM usage, 3/7 tool-calls, 146 tok/s, 15.0s The 8B used less than half the RAM and still fired all 7 calls, while the 20B silently dropped more than half of its own. It also ran ~2x faster, wrapping the full agentic request in 6.9s against 15s. That's what 38T training tokens buy: a 1B-active MoE that nails the agentic tool calls a model 2.5x its active size keeps droppingshow more

a moonshot engineer leaked the benchmark anthropic, openai and... xai all buried the same week: kimi k3 beat opus 5, gpt-5.6 and grok 4.6 at $0.94 a task. stop paying anthropic $200 a month for opus 5 and openai $200 for gpt-5.6 when kimi does the same work for $8 the leak showed kimi k3 winning 9 of 12 categories against opus 5, gpt-5.6 and grok 4.6. within 48 hours all three labs quietly pushed pricing pages and one very specific comparison chart off their sites. nobody announced anything. they just deleted, which tells you everything the four numbers they scrubbed: cost per task · $0.94 vs $1.80 -> opus 5 charges $1.80 to finish one task. gpt-5.6 $1.04. grok 4.6 $0.61. kimi k3 $0.94 and it landed 487 of 500 clean -> anthropic is billing you double for a model that lost the benchmark it paid to promote the weights · free, sitting on huggingface right now -> the entire model is a public download. pull it, keep it, run it forever, nobody can switch it off -> a model you can hold cannot be rented at $200 a month. that single fact is what three labs deleted a chart over the switch · one line of bash -> moonshot ships an anthropic-compatible endpoint. one env variable and claude code points at kimi -> same cli, same keybindings, same /model. you change a url, opus 5 never knows it lost the seat the bill · $400 down to $8 -> opus 5 max plus gpt-5.6 pro is $400 a month. kimi runs the same daily work for $8 metered -> that is a 98% cut for output that beat both of them 9 categories to 3 here is the part they will fight me on: the frontier tax died the week this leaked and all three labs know it. once the weights are public the price has a ceiling, because anyone can serve the same model. anthropic, openai and xai are charging 2025 prices on a lead that ended in a benchmark they deleted instead of answered drop your $400/mo ai stack to $8. the run above is kimi k3 finishing the task opus 5 bills $1.80 for. the full breakdown is in the article belowshow more

GPT-5.5 is MUCH more reliable on longer running tasks... - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.show more

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.show more

whoever leaked this has bigger balls than sense Google... Research and MIT ran the same agent jobs 260 different ways for Nature last month: they held the prompts, the tools and the compute budget identical and moved nothing but the wiring between the agents, and the same work swung from 70% worse than a single agent to 80.8% better, averaging out at 0.0% i ran my own single agent against the task list first and it cleared 6 of 10 alone, already past the line where a crew starts subtracting this is Graph Engineering, the layer that decides whether a crew is worth 80% more or 70% less, and it installs into the agent you already pay for: - score your solo agent on the real task first: above roughly 45% success that study predicts zero to negative returns from any crew you put around it - under that line, put one supervisor over the fan out: crews with no correction step amplified their own errors to 17.2x the single agent rate, supervised aggregation held it to 4.4x - give every worker one output and let none of them read a peer's draft, so a wrong step reaches the supervisor instead of four other agents - run the comparison again after every model upgrade, because a better model raises your baseline and a higher baseline is what makes a crew stop paying - keep the single agent alive as the control, the only number that says the wiring is earning its calls turns out the shape does not travel: the biggest win came off a finance task under one supervisor and the worst collapse off a planning task with independent agents my position, and it is the arguable one: a crew is a bet on your own diagram, and the model you pick moves that bet less than one arrow does bookmark this, the three moves that draw those arrows before you pay for one extra call are in the post below ↓show more

Proud to announce the in-depth collaboration between Kingnet and... Alibaba Cloud in AI Gaming. Alibaba Cloud provides world-leading cloud computing, big data, and AI services, with disclosed revenue exceeding $15 billion in 2024, which is one of the most renowned global server providers. When two superpowers collide, the game changes. 🌊AI Gaming R&D By integrating Qwen 's LLM and Alibaba Cloud 's PAI platform (including PAI-iTAG, PAI-Designer, PAI-DSW, PAI-DLC, and PAI-EAS), Kingnet has emerged as one of the gaming industry's pioneers in AIGC-powered content generation and AI rendering. Together, we are accelerating the realization of no-code game development. 🌊GPU Computing Resources Alibaba Cloud delivers GPU-accelerated elastic computing services with exceptional processing power, supporting diverse workloads including deep learning, scientific computing, graphics visualization, and video processing - providing robust GPU computing capabilities for KingnetAI's demanding requirements. 🌊Cloud Service Optimization Cloud server deployment has become the mainstream choice for small and mid-sized game studios in global operations. Leveraging Alibaba Cloud server advantages, we will develop and deploy more cloud-native games to meet user demands. The disruptive innovation we're bringing to the industry: 🔸Minute-scale game asset production replaces traditional week/month-long cycles 🔸Single-digit dollar development costs VS traditional four-figure entry thresholds 🔸AI-powered NPCs with behavioral engines deliver dynamic player interactions, breaking static story constraints, etc. 🔜Kingnet AI V2 is approaching launch. The Agent system and game generation engine will be officially deployed across 3 chains: 🔹Leveraging Solana high throughput and low gas fee , Solana has consistently been a developer favorite, latest product will be deployed on Solana - with users paying $SOL for on-demand asset creation fees. 🔹Another key partner is BNB Chain ,We are actively participating in both the #BNBAIHack and the latest MVB 10. Powered by BNB Chain long-standing support for AI innovation. Kingnet V2 and NFT drop will be deployed on BNB Chain, providing developers and the community with comprehensive game-generation tools and support. 🔹As an early strategic partner of Kingnet, TON 💎 @TONEastAsia was one of the earliest chain to connect Web2 and Web3, Kingnet V2 will be deployed on TON, providing TON game developers with low-cost, high-efficiency asset generation, and supporting users to use $TON as an asset generation cost. The Future of AI Gaming is coming.show more

This Chinese developer launched Llama 70B locally on a... MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.show more

I just got Gemma 4 26B A4B MoE model... running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtesting trading strategies end to end, no hand holding. If you’re a trader or work on Wall Street, you don’t want to miss this. Yes. fully automated. No cloud. No APIs beyond market data. # Here's what I did: Setup: - Model: Gemma 4 26B-A4B QAT (MoE), Q4_K_XL Unsloth's quant (link in the comments) - Inference: llama.cpp (turboquant fork by Tom Turney link in the comments) - Hardware: RTX 4060, 8GB VRAM + 16GB RAM only (with 50 other chrome tabs open) - Context: 64K llama.cpp turboquant flags: -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf -c 64000 --cache-type-k q8_0 --cache-type-v turbo3 --port 8080 turboquant helps achieve high prefill and decode throughput for interactive sessions. throughput with Hermes agent: decode: 25+ tokens/sec prefill: 250+ tokens/sec # Then I gave the agent one task: Backtest a strategy: - Buy when RSI crosses above 30 - Sell at +2% profit or -1% stoploss - No overlapping positions - Use Google stock via yfinance - Generate a full HTML report with candlestick charts + signals What happened next was wild. It didn't just write code, it ran the entire workflow itself: Audited the environment (pip list, dependency check) Hit a ModuleNotFoundError, multiple Python installs were conflicting Ran where python to map every interpreter on the system Manually selected the correct Python 3.13 path and re ran the script Wrote a clean statevmachine backtester (strict no overlapping trades logic) Patched a yfinance MultiIndex quirk that would've crashed the script Built Plotly candlestick + RSI charts with buy/sell markers Calculated win rate, PnL, and summary stats Exported a polished single file HTML report. check the report at the end of the video or in the comments. Biggest takeaway: local LLMs aren't just "chat assistants" anymore. They debug their own environment, write production code, and ship a finished deliverable on consumer hardware, for $0 in API costs. If you're still calling local models "toys," you're already behind. This is just the beginning. Hermes agent just surpassed 1 trillion tokens in a single day on OpenRouter. Think about the scale of total token generation happening right now. Disclaimer: This is not financial advice. Consult a professional before making any trading decisions.show more

I Combined ChatGPT 5.5 Image-2 + Claude Fable 5…... And Built This FULL Game in JUST 8 Hours 😱 The World Has Officially Changed Forever Guys… I still can’t believe what I just pulled off. I took ChatGPT 5.5’s new Image-2 to generate every single visual characters, environments, UI, particles, everything and paired it with Claude Fable 5 for the entire codebase. The result? A complete, polished, fully playable game… finished in only 8 hours. No massive team. No months of crunch. No expensive asset packs. Image-2 created mind-blowing art assets on demand. Fable 5 turned those images into real, working code mechanics, physics, AI, animations, menus everything. This hybrid combo is straight-up sorcery. The world has truly changed. We are no longer waiting years for games to be made. One person + these two god-tier AIs just built something that used to require entire studios and huge budgets… in less than a single workday. This is the next level of human civilization. This is what creation looks like from now on. But here’s the crazy part: This free access ends June 22, 2026. After that, you’ll have to pay/subscribe to keep using it. If you’ve been waiting to see what the future of game dev actually looks like… THIS IS IT. Go try it right now before the paywall hits. Don’t sleep on this. Seriously. Drop in the comments: What game should I build next with this insane Image-2 + Fable 5 hybrid? Like if your mind is blown too 🔥 And tag a friend who NEEDS to see this before it’s gone. The future isn’t coming… It’s already here. And it’s free for one more day only. #Fable5 #ChatGPT55 #Image2 #AIHybrid #GameDevRevolutionshow more

This was captured by a doorbell camera last Thursday... evening in Chattanooga, Tennessee. The family is the Warners. The mother is Christine. Her husband is David. Their kids are Lily, age thirteen, and Marcus, age ten. The dog is a shaggy brown and white mixed-breed named Benny. Seven years old now. Two years ago, the Warners were moving from Chattanooga to Nashville. It was a long moving day with multiple trips. During the second truck run, Benny was left with a neighbor temporarily. When the neighbor opened the door to check on him, Benny slipped past and ran. They searched the neighborhood for hours. Filed lost pet reports. Drove back from Nashville three times to search. Posted on every platform they could find. Hired a pet recovery service for two months. Eventually, life kept moving. The kids still talked about Benny. The subject would come up at dinner sometimes. Christine told us she never fully unpacked Benny's things in Nashville. They just stayed in a box in the garage. Then in September, the Warners moved back to Chattanooga for David's job. Back to the same house. The same address. Last Thursday at 6:42 PM, the doorbell camera activated. Benny walked up the porch steps alone. Thinner than before. Fur longer and rougher. But unmistakably Benny. He walked to the front door and sat down. Waited. Christine was in the kitchen. Her phone showed the doorbell notification. She looked at the camera image on her screen and stood completely still for several seconds. Then she ran to the front door. The doorbell camera captured everything. Christine on her knees. Benny walking directly into her arms. Both of them on the porch floor. Christine saying his name over and over. David and both kids came to the door moments later. The camera caught all four of them on the porch in the dark. A veterinarian confirmed Benny's identity through a microchip registered in the Warners' name. The vet said Benny was underweight but in remarkable condition for two years on his own. David told us: "We moved back to the same house in September. Benny showed up in October. I don't know how to explain that. I don't know if I even need to."show more

⚡️ We are excited to introduce Rush Games -... a new platform that combines onchain gaming, mobile, social media and AI in innovative ways. 🎮 One of the key features we are most excited about is Rush Genie 🧞‍♂️, an AI agent trained on game development and the Beyond Network SDK, which will allow users to create their own mini-games without any coding knowledge. We believe this will open up new possibilities for creative game design. 🧩 With Rush, not only can you play a variety of engaging games, but you'll also have the opportunity to be rewarded for your creativity. But that's not all - we are integrating social features to take gameplay to the next level: 🆚 Connect with friends and challenge them head-to-head 🌐 Leverage decentralized social graphs for personalized, interconnected gaming experiences 💰 NFT holders will enjoy special perks like earning multipliers The $Bull token will be deeply integrated into the Rush Games ecosystem: 🪙 Spend $Bull to access Rush Genie and supercharge your game creation 🛍️ Use $Bull for in-game assets, lucky spins, draws, and raffles directly from Telegram and Farcaster on Base 🔒 Stake $Bull tokens to earn multipliers on your rewards 🔥 100% of revenues generated will be used to buy back and burn $Bull, driving sustainable value We are preparing to launch a selection of new titles that showcase the potential of on-chain gaming. Rush games beta along with our first game NetGains goes live on 25.01.25 ⚡️ Stay tuned for more details. The future of on-chain gaming is bright with #RushGames by #Bullieverse $Bullshow more

I went a little overboard with Codex last week... and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.show more

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND... LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇show more

Does LLM really need to be a helpful assistant... all the time? No. If you want to simulate people, “perfectly helpful” could be the wrong objective. Meet OdysSim, a journey toward LLMs beyond assistants, as behavioral foundation models (10B tokens of real human behavior; 23 sim benchmarks, finally in one place. new open models: outperform or on par with GPT-5.5, Gemini 3.1, or Claude Opus 4.7 in many behavior-sim dimensions). Human behavior simulation is becoming essential. Agent evaluation needs realistic users before real users show up. Medical and classroom training need realistic patients and students. Social science needs synthetic participants at scale. But real people are not ideal assistants. Real patients panic or ignore good advice. Real students misunderstand. Real customers are vague, picky, impatient, or simply leave. Human behavior is messy, diverse, and often imperfect. Frontier LLMs are getting better at math, code, and long-horizon tasks. They are NOT getting better at simulating human behavior. If anything, they drift the other way: more assistant-ish, more homogeneous, fewer of the errors and quirks real humans show. This is no accident. The whole pipeline is built for helpfulness and task success, not behavioral realism. And you can't prompt your way out of that. So we rethink the recipe from scratch and release: 🧠 The OdysSim corpus: 21.4M real human interactions (~10B tokens) from 62 sources, every conversation retrofitted with social grounding (who is talking, and why) 📏 SOUL-Index: 23 human-behavior benchmarks unified into one suite across 5 axes 🤖 OSim-8B: open weights; tops more SOUL-Index benchmarks than any frontier model, acts more like a real user than any of them on τ-bench (nearly matching real humans in the reaction dimension), and writes far more human-like text along the way.show more

Impeccable 3.7 brings linting to design. Until now it... was a skill you asked for help. Now it's a design-system-aware feedback loop that runs while your agent builds, catching slop and design drift before they land. 🪝 Design hooks for Claude, Codex, and Cursor They run after every UI edit and quietly nudge your agent to fix slop and drift. The output isn't another wall of lint: it separates new findings from already-seen ones, flags clean scans, and asks the agent to use judgment. Fix real issues, leave intentional demos alone, save exceptions to config instead of littering your source. 🎨 Slop detection is now project-aware Reads your actual design system from DESIGN.md, your typography, palette, radius scale, and tokens, and flags drift from your system, not just generic AI slop: • this font isn't in your design system • this color is outside your documented palette • this radius doesn't match your rounded scale The same engine powers both the hooks and the CLI, and it's where we're investing next. 🖥️ Live Mode, ready for real projects Svelte/SvelteKit now preview variants as temporary framework components with live params, then accept cleanly back into your source component. Manual text edits got evidence / apply / discard routes, insertions preserve their anchors, and mapped lists and JSX slots clean up far more reliably. ⚡ Leaner core, sharper detector Rule-level evals across 3 providers and 4 niches cut guidance with no measurable lift and dropped examples that taught models bad patterns. The detector now skips hidden and screen-reader-only elements, understands OKLCH alpha and Sass-like inputs, and tightened checks for repeated kickers, oversized H1s, clipped overflow, and cramped padding. 🛠️ CLI caught up impeccable detect loads DESIGN.md by default, motion findings name the exact token or cubic-bezier instead of just "bounce," and impeccable ignores gives real CRUD for exceptions. Hooks and CLI share the same ignores. No split-brain config. Plus a much-improved interactive installer with hooks setup built in. Upgrade: npx impeccable install npm i -g impeccableshow more