Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Fully Aggressive variant Uncensored MoE model that won’t refuse red team or pentesting tasks & coding. - 35B parameters, 3B active (MoE) - 0 refusals (Aggressive variant) - Excellent agentic coding + multimodal Powerful uncensored coding model 73.4% on SWE-bench Verified & fully uncensored, It dangerous (in a good... show more

Md Ismail Šojal 🕷️

46,591 subscribers

28,103 görüntüleme • 3 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Harman

41,278 görüntüleme • 3 ay önce

$Someone is running Qwen3.8-35B-A3B on a single RTX 3060 with just 12GB of VRAM and 16GB of system RAM. And the reported numbers are surprisingly good. ~50 tok/s decode ~550 tok/s prefill 262K context window 12GB VRAM 16GB system RAM No multi-GPU setup. Just a consumer graphics card and a carefully configured local inference engine. The model is particularly interesting because it’s Qwen3.8 distilled into the Qwen3.6-35B-A3B architecture. That makes it worth investigating beyond raw inference speed. The developer currently uses Ornith-1.5 as the engine behind their Hermes and Pi agents. Now the question is whether this new model can deliver enough quality and reliability to replace it. The next step is testing it as an agent, not just a chatbot. The planned comparison includes four models: • Qwen3.8-35B-A3B • Ornith-1.5-35B • Qwen3.8-27B • Base Qwen3.6-35B-A3B An agentic coding benchmark should help reveal whether the distilled model can follow instructions, modify code, solve problems, and complete multi-step tasks effectively. That distinction matters because high token throughput doesn’t automatically translate into a better coding agent. A model can generate code quickly and still struggle with planning, debugging, tool calls, or completing a task without intervention. The hardware configuration is also worth examining. The developer is using llama-server with the Q4_K_M GGUF quantization, Flash Attention enabled, and 26 MoE layers assigned to CPU processing. The configuration also enables a 262,144-token context window, Q8 KV-cache quantization, and reasoning mode. This is how the setup is configured: llama-server \ -m Qwen3.8-35B-A3B-Q4_K_M.gguf \ -ngl 99 \ --n-cpu-moe 26 \ -c 262144 \ -fa on \ --jinja \ -np 1 \ --cache-type-k q8_0 \ --cache-type-v q8_0 \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --reasoning on One important detail: the model’s 35B parameter count doesn’t mean all 35 billion parameters are activated for every token. The A3B designation indicates roughly 3 billion active parameters per token. That sparse MoE architecture helps explain how a model of this size can deliver high generation speeds on modest hardware. CPU-based expert processing also helps work around the GPU’s limited memory, although the exact trade-offs depend on the workload. The 262K context claim is equally interesting. Supporting a context window that large doesn’t mean every request at that length will maintain the same speed. Prompt length, KV-cache memory, and CPU/GPU placement can all affect performance. The developer’s next test is particularly useful: graphing decode speed against context length. That should help show how performance changes as the prompt grows, rather than presenting one speed figure without the conditions behind it. If the coding benchmark also holds up, this could become a serious option for people who want capable local agents without investing in expensive GPUs. For now, the reported inference numbers are promising. The real test is whether Qwen3.8-35B-A3B can match or outperform Ornith-1.5-35B on actual agentic coding tasks. Fast local inference gets your attention. Reliable autonomous task completion is what earns a model a place in the stack.$

Someone is running Qwen3.8-35B-A3B on a single RTX 3060 with just 12GB of VRAM and 16GB of system RAM. And the reported numbers are surprisingly good. ~50 tok/s decode ~550 tok/s prefill 262K context window 12GB VRAM 16GB system RAM No multi-GPU setup. Just a consumer graphics card and a carefully configured local inference engine. The model is particularly interesting because it’s Qwen3.8 distilled into the Qwen3.6-35B-A3B architecture. That makes it worth investigating beyond raw inference speed. The developer currently uses Ornith-1.5 as the engine behind their Hermes and Pi agents. Now the question is whether this new model can deliver enough quality and reliability to replace it. The next step is testing it as an agent, not just a chatbot. The planned comparison includes four models: • Qwen3.8-35B-A3B • Ornith-1.5-35B • Qwen3.8-27B • Base Qwen3.6-35B-A3B An agentic coding benchmark should help reveal whether the distilled model can follow instructions, modify code, solve problems, and complete multi-step tasks effectively. That distinction matters because high token throughput doesn’t automatically translate into a better coding agent. A model can generate code quickly and still struggle with planning, debugging, tool calls, or completing a task without intervention. The hardware configuration is also worth examining. The developer is using llama-server with the Q4_K_M GGUF quantization, Flash Attention enabled, and 26 MoE layers assigned to CPU processing. The configuration also enables a 262,144-token context window, Q8 KV-cache quantization, and reasoning mode. This is how the setup is configured: llama-server \ -m Qwen3.8-35B-A3B-Q4_K_M.gguf \ -ngl 99 \ --n-cpu-moe 26 \ -c 262144 \ -fa on \ --jinja \ -np 1 \ --cache-type-k q8_0 \ --cache-type-v q8_0 \ --temp 0.6 \ --top-p 0.95 \ --top-k 20 \ --reasoning on One important detail: the model’s 35B parameter count doesn’t mean all 35 billion parameters are activated for every token. The A3B designation indicates roughly 3 billion active parameters per token. That sparse MoE architecture helps explain how a model of this size can deliver high generation speeds on modest hardware. CPU-based expert processing also helps work around the GPU’s limited memory, although the exact trade-offs depend on the workload. The 262K context claim is equally interesting. Supporting a context window that large doesn’t mean every request at that length will maintain the same speed. Prompt length, KV-cache memory, and CPU/GPU placement can all affect performance. The developer’s next test is particularly useful: graphing decode speed against context length. That should help show how performance changes as the prompt grows, rather than presenting one speed figure without the conditions behind it. If the coding benchmark also holds up, this could become a serious option for people who want capable local agents without investing in expensive GPUs. For now, the reported inference numbers are promising. The real test is whether Qwen3.8-35B-A3B can match or outperform Ornith-1.5-35B on actual agentic coding tasks. Fast local inference gets your attention. Reliable autonomous task completion is what earns a model a place in the stack.

FHILY👑

19,254 görüntüleme • 2 gün önce

MiniMax M2.1 is really good for writing code. It's open source, and you can connect Visual Studio Code to it and start coding right away. The model is especially good for those who don't use Python as a primary language. It's currently the best multilingual model out there. The model hits 72.5% on SWE-Multilingual and 88.6% on VIBE-Bench (best!) This means the model is also really good at performing real engineering work and does very well at agentic tasks: • Long tool chains • Structured agent scaffolding • Following repo-level rules and slash commands • Working inside existing agent frameworks without falling apart And obviously, it's faster, cheaper, and more concise than M2, which was already really good. I recorded a video to show you how to run MiniMax (official)'s 2.1 using Visual Studio Code.

MiniMax M2.1 is really good for writing code. It's open source, and you can connect Visual Studio Code to it and start coding right away. The model is especially good for those who don't use Python as a primary language. It's currently the best multilingual model out there. The model hits 72.5% on SWE-Multilingual and 88.6% on VIBE-Bench (best!) This means the model is also really good at performing real engineering work and does very well at agentic tasks: • Long tool chains • Structured agent scaffolding • Following repo-level rules and slash commands • Working inside existing agent frameworks without falling apart And obviously, it's faster, cheaper, and more concise than M2, which was already really good. I recorded a video to show you how to run MiniMax (official)'s 2.1 using Visual Studio Code.

Santiago

47,879 görüntüleme • 8 ay önce

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

We’re excited to share that 🥇Llama Nemotron Super 49B v1.5 -- our latest open reasoning model -- is now #1 on the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, in the 70B open model category. Llama Nemotron Super 49B v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. It delivers state-of-the-art accuracy and throughput, running on a single H100. Key features: 🎯 Leading accuracy on multi-step reasoning, math, coding, and function-calling 🏗️ Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples 📊 Fully transparent training data and techniques If you're building AI agents and want a high accuracy, fully-open, and transparent reasoning model that you can deploy anywhere, try Super v1.5 on or download from Hugging Face 🤗 ➡️ Leaderboard:

NVIDIA AI Developer

100,506 görüntüleme • 1 yıl önce

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

YanXbt

53,423 görüntüleme • 4 ay önce

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

RAVI KUMAR SAHU

380,400 görüntüleme • 7 ay önce

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,263 görüntüleme • 11 ay önce

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

29,013 görüntüleme • 2 yıl önce

Choose a model (any model) and build your application with it. Do not spend time swapping models early on. Do not try to optimize before you have a working system. This is one of the first recommendations I make to every new team I consult with. Eventually, it will be time to optimize the model. • You may need a cheaper model • You may need a faster model • You might need a smarter model Good luck if you stitched together 12 different APIs and SDKs from 7 different vendors. Over half of the companies I consult for run on Microsoft software and have access to Microsoft Foundry. Microsoft Foundry is a complete agentic ecosystem. If you're in that world and building AI applications, Microsoft Foundry is where everything lives: • Models (largest selection in the market) • Agentic SDK (Python, C#, JavaScript/TypeScript) • Tools • Evaluations • Monitoring They are fully integrated with GitHub and Visual Studio Code. The best part: Their agentic platform is fully agnostic of the models you use. You can integrate with any model using the same OpenAI-style API. Swapping one model for another takes 1 second.

Choose a model (any model) and build your application with it. Do not spend time swapping models early on. Do not try to optimize before you have a working system. This is one of the first recommendations I make to every new team I consult with. Eventually, it will be time to optimize the model. • You may need a cheaper model • You may need a faster model • You might need a smarter model Good luck if you stitched together 12 different APIs and SDKs from 7 different vendors. Over half of the companies I consult for run on Microsoft software and have access to Microsoft Foundry. Microsoft Foundry is a complete agentic ecosystem. If you're in that world and building AI applications, Microsoft Foundry is where everything lives: • Models (largest selection in the market) • Agentic SDK (Python, C#, JavaScript/TypeScript) • Tools • Evaluations • Monitoring They are fully integrated with GitHub and Visual Studio Code. The best part: Their agentic platform is fully agnostic of the models you use. You can integrate with any model using the same OpenAI-style API. Swapping one model for another takes 1 second.

Santiago

12,014 görüntüleme • 7 ay önce

Progress in open models is keeping Big AI labs up at night, and I'm here for it! We have a brand new open-weight multimodal model optimized for long-horizon tasks. This model is really good at something: it can work on tasks that keep evolving over time. • 280B total parameters, but only 16B active • 512K context window • Understands text, images, and audio • Strong reasoning, coding, and tool use But the best of all: the model learns and adapts to new information! Imagine you start running an agent today to solve a problem, and while it's working, you get new information that changes the initial conditions, or you change your mind. The agents you run today don't have issues with short tasks and goals that don't change, but reality is messy, and that makes it hard for long-horizon agents to succeed. The new dots3-note Preview model introduces TEMPO. TEMPO is a new reinforcement learning technique that lets the model periodically pause and critique its own progress. Basically, from time to time, the agent asks itself: "Am I getting closer to the goal, or am I wasting my time?" The same model switches between actor and critic. The actor works on the problem. The critic looks at the current state, reasons about how much progress it has made, and determines what should happen next. TEMPO gives the model feedback along the way. This is huge for any agent that can work on long-horizon tasks without wasting its time.

Santiago

80,792 görüntüleme • 1 ay önce

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Bo Wang

13,221 görüntüleme • 7 ay önce

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

Santiago

41,738 görüntüleme • 1 yıl önce

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Tencent just dropped Hy3, and it's worth a look if you're building AI agents. I spent some time putting it through its paces today. A quick rundown of what makes this release notable: → 295B total parameters (Mixture-of-Experts), but only 21B active at inference — a real efficiency play → 256K context window for handling large codebases or long documents → Purpose-built improvements for coding and multi-step agent tasks → Fully open under Apache 2.0 — no restrictive commercial terms → A free two-week API window currently live on OpenRouter On the practical side: prompts involving layered instructions and coding tasks came back fast and coherent. Tencent says this release builds directly on feedback from 50+ internal product teams following an earlier preview, with reported drops in hallucination rate (12.5% → 5.4%) and commonsense errors (25.4% → 12.7%). Those are Tencent's own numbers, so treat them as a starting point rather than gospel until third parties weigh in. For context: Tencent's own comparisons put Hy3 behind GLM-5.2 specifically on coding benchmarks — GLM is a much bigger model (~744B total), so the trade-off makes sense. Hy3's pitch isn't "biggest," it's "efficient enough to actually deploy." Bottom line — if you're evaluating open-weight options for agent workloads, this is a solid one to add to the testing queue while the free window is open. Try it here: Tencent Hy #Hy3 #Hunyuan #TencentAI #AICoding

Felix

36,925 görüntüleme • 3 ay önce

Tencent's Hy3 lands today with real coding and agent ability and a price that undercuts the models you'd put it against. It's a 295B MoE with only 21B active parameters, a big part of why it stays cheap to serve, plus a 256K context window and an Apache 2.0 license that even outperforms GLM-5.1 although GLM is 2.5x larger. On OpenRouter it runs at $0.14 per million input tokens and $0.58 per million output. For a model Tencent benchmarks against much larger flagships, that pricing is insane. Price-performance-ratio is China's real moat. I already wrote about Tencent Hy3 earlier and the significant leap in quality it represents. Therefore, I'm pleased to recommend this model from Tencent Hy. Open Router link down below: #Hy3 #Hunyuan #AICoding

Tencent's Hy3 lands today with real coding and agent ability and a price that undercuts the models you'd put it against. It's a 295B MoE with only 21B active parameters, a big part of why it stays cheap to serve, plus a 256K context window and an Apache 2.0 license that even outperforms GLM-5.1 although GLM is 2.5x larger. On OpenRouter it runs at $0.14 per million input tokens and $0.58 per million output. For a model Tencent benchmarks against much larger flagships, that pricing is insane. Price-performance-ratio is China's real moat. I already wrote about Tencent Hy3 earlier and the significant leap in quality it represents. Therefore, I'm pleased to recommend this model from Tencent Hy. Open Router link down below: #Hy3 #Hunyuan #AICoding

Chubby♨️

23,439 görüntüleme • 3 ay önce

MIT PhD student Alex Zhang reveals the scaling result where a model trained on short tasks generalizes to problems 100x longer for free: "If you're very clever about the design of your harness or how you use the language model, you can almost get scaling gains for free." "If you train a model naively, there's no tricks. It's just the same way you train a model on these RL environments. You just roll it out, and then you just get some reward." "If you train it on only short tasks, like only tasks that are 10,000 tokens long, and then you were to run it on a similar domain, but at a million tokens, or 10 million tokens, or 100,000 tokens, it generalizes really, really well. If you look at it compared to even the base transformer, you get way better generalization properties." "When the model uses an RLM (Recursive Language Model) after it's trained on these short tasks, it will see some kind of trajectory of actions that it does. Between these two problems of different lengths, the RLM learns to see them as almost the same problem." "Token for token, they're almost the same. You can describe it in code. In one code setting, maybe the for loop is a little bigger, but it's the same kind of code and it derives the constants from the data. There's no hard coding, so they literally look the same." alex zhang

MIT PhD student Alex Zhang reveals the scaling result where a model trained on short tasks generalizes to problems 100x longer for free: "If you're very clever about the design of your harness or how you use the language model, you can almost get scaling gains for free." "If you train a model naively, there's no tricks. It's just the same way you train a model on these RL environments. You just roll it out, and then you just get some reward." "If you train it on only short tasks, like only tasks that are 10,000 tokens long, and then you were to run it on a similar domain, but at a million tokens, or 10 million tokens, or 100,000 tokens, it generalizes really, really well. If you look at it compared to even the base transformer, you get way better generalization properties." "When the model uses an RLM (Recursive Language Model) after it's trained on these short tasks, it will see some kind of trajectory of actions that it does. Between these two problems of different lengths, the RLM learns to see them as almost the same problem." "Token for token, they're almost the same. You can describe it in code. In one code setting, maybe the for loop is a little bigger, but it's the same kind of code and it derives the constants from the data. There's no hard coding, so they literally look the same." alex zhang

MTS

100,519 görüntüleme • 2 ay önce

BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally Every 📧 for the last week or so across coding, writing, marketing, editing, and more—here's our vibe check: - It broke our benchmarks. Fable scored a 91/100 on our Senior Engineer benchmark—this is human senior engineer level. The previous high score was Opus 4.8 at 63. GPT-5.5 is a 62. - It's a one-shot wonder. You can set it and forget for hours or overnight on huge coding tasks, and come back to completed work. It cleared entire production bug backlogs, built a playable 3D, and even made a 2-minute animated film—all one-shot. - Taste and attention to detail. In coding and knowledge work tasks, it has much better taste and attention to detail than we've ever seen. It gets subtle things right, adds little features you might not have thought of, and generally understands the assignment in ways that surprised us. - Great use of context. We set it loose analyzing customer feedback surveys and our website data and it came back with a crisp, clean report that identified a. our biggest problem and b. a concrete testable solution—and then we sent it off to build that. - It's best for power users. If you're already used to orchestrating multiple agents in your work, this model can do things that you've never seen before. If you're a knowledge worker or vibe coder with a more basic setup, you're not going to notice a huge difference—in fact, it probably isn't the right model for you. - It's very slow, token-hungry. Using this thing for regular knowledge work is like squashing an ant with a rocket launcher. It also routinely uses 500k to 1M tokens on tasks. That's why it's best for your heaviest jobs—but not as good for tasks like collaborative writing. - It's expensive. It's about twice as expensive as Opus, and it's also incredibly token hungry—so expect it to be something you'll use sparingly unless your company pays for it. Overall, I think of it like a warp drive for coding: It can get you across the galaxy in a few hours, when it used to take months or years. But it's not appropriate for getting around town—you need something faster, cheaper, and more maneuverable. The ceiling is extraordinarily high on this model though. Even our most advanced testers like Kieran Klaassen felt like they were only scratching the surface of it. Want our full vibe check with all of our testing and benchmarks? Read it on Every 📧:

BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally Every 📧 for the last week or so across coding, writing, marketing, editing, and more—here's our vibe check: - It broke our benchmarks. Fable scored a 91/100 on our Senior Engineer benchmark—this is human senior engineer level. The previous high score was Opus 4.8 at 63. GPT-5.5 is a 62. - It's a one-shot wonder. You can set it and forget for hours or overnight on huge coding tasks, and come back to completed work. It cleared entire production bug backlogs, built a playable 3D, and even made a 2-minute animated film—all one-shot. - Taste and attention to detail. In coding and knowledge work tasks, it has much better taste and attention to detail than we've ever seen. It gets subtle things right, adds little features you might not have thought of, and generally understands the assignment in ways that surprised us. - Great use of context. We set it loose analyzing customer feedback surveys and our website data and it came back with a crisp, clean report that identified a. our biggest problem and b. a concrete testable solution—and then we sent it off to build that. - It's best for power users. If you're already used to orchestrating multiple agents in your work, this model can do things that you've never seen before. If you're a knowledge worker or vibe coder with a more basic setup, you're not going to notice a huge difference—in fact, it probably isn't the right model for you. - It's very slow, token-hungry. Using this thing for regular knowledge work is like squashing an ant with a rocket launcher. It also routinely uses 500k to 1M tokens on tasks. That's why it's best for your heaviest jobs—but not as good for tasks like collaborative writing. - It's expensive. It's about twice as expensive as Opus, and it's also incredibly token hungry—so expect it to be something you'll use sparingly unless your company pays for it. Overall, I think of it like a warp drive for coding: It can get you across the galaxy in a few hours, when it used to take months or years. But it's not appropriate for getting around town—you need something faster, cheaper, and more maneuverable. The ceiling is extraordinarily high on this model though. Even our most advanced testers like Kieran Klaassen felt like they were only scratching the surface of it. Want our full vibe check with all of our testing and benchmarks? Read it on Every 📧:

Dan Shipper

622,666 görüntüleme • 4 ay önce

The kyutai fully end-to-end audio model demo of today is a huge deal that many people missed in the room Mostly irrelevant are the facts that: - they come a few week after OpenAI ChatGPT-4o - the demo was less polished than the 4o one (in terms of voice quality, voice timing…) Relevant: - the model training pipeline and model archi are simple and hugely scalable, with a tiny 8+ people team like Kyutai building it in 4 months. Synthetic data is a huge enabler here - laser focus on local devices: Moshi will soon be everywhere. Frontier model builders have low incentive to let you run smaller models locally (price per token…) but non-profits like Kyutai have very different incentives. The Moshi demo is already online while the OpenAI 4o one is still in limbo. - going under 300 ms of latency while keeping Llama 8B or above quality of answers is a key enabler in terms of interactivity, it’s game changing, This feeling when the model answer your question before you even finished asking is quite crazy or when you interrupt the model while it’s talking and it react… Predictive coding in a model, instantly updated model of what you’re about to say... Basically they nailed the fundamentals. It’s here. This interactive voice tech will be everywhere. It will soon be an obvious commodity.

The kyutai fully end-to-end audio model demo of today is a huge deal that many people missed in the room Mostly irrelevant are the facts that: - they come a few week after OpenAI ChatGPT-4o - the demo was less polished than the 4o one (in terms of voice quality, voice timing…) Relevant: - the model training pipeline and model archi are simple and hugely scalable, with a tiny 8+ people team like Kyutai building it in 4 months. Synthetic data is a huge enabler here - laser focus on local devices: Moshi will soon be everywhere. Frontier model builders have low incentive to let you run smaller models locally (price per token…) but non-profits like Kyutai have very different incentives. The Moshi demo is already online while the OpenAI 4o one is still in limbo. - going under 300 ms of latency while keeping Llama 8B or above quality of answers is a key enabler in terms of interactivity, it’s game changing, This feeling when the model answer your question before you even finished asking is quite crazy or when you interrupt the model while it’s talking and it react… Predictive coding in a model, instantly updated model of what you’re about to say... Basically they nailed the fundamentals. It’s here. This interactive voice tech will be everywhere. It will soon be an obvious commodity.

Thomas Wolf

339,688 görüntüleme • 2 yıl önce

watch and let this sit for a second anon, a 35B AI model, building a complete multi-file game by itself on hermes agent. no cloud or api. not one line of code written by a human. running on a DGX spark in 2026. because not long ago this was science fiction. this is Ornith, a new open agentic coding model, running near lossless on a single DGX Spark, a 128GB box that sits on your desk. i hand it one spec and step back. it reasons about the architecture, creates the project structure, writes every module one by one, and here's the part that got me, it checks its own work as it goes. makes a call, reads the result, decides if it's right, corrects itself before moving on. no steering from me. this is what people keep underestimating about local AI. they hear "local" and think weaker, slower, a toy. watch the clip. a 35B at near full precision, planning and self correcting on a single desktop. the open models got genuinely good at agentic work, not benchmark good, actually builds the thing good. sped 5x so you can watch the whole build start to finish. this is where local AI actually is now. not coming soon. here.

watch and let this sit for a second anon, a 35B AI model, building a complete multi-file game by itself on hermes agent. no cloud or api. not one line of code written by a human. running on a DGX spark in 2026. because not long ago this was science fiction. this is Ornith, a new open agentic coding model, running near lossless on a single DGX Spark, a 128GB box that sits on your desk. i hand it one spec and step back. it reasons about the architecture, creates the project structure, writes every module one by one, and here's the part that got me, it checks its own work as it goes. makes a call, reads the result, decides if it's right, corrects itself before moving on. no steering from me. this is what people keep underestimating about local AI. they hear "local" and think weaker, slower, a toy. watch the clip. a 35B at near full precision, planning and self correcting on a single desktop. the open models got genuinely good at agentic work, not benchmark good, actually builds the thing good. sped 5x so you can watch the whole build start to finish. this is where local AI actually is now. not coming soon. here.

Sudo su

30,299 görüntüleme • 3 ay önce

Qwen3.8-27B running at full BF16 on a free Kaggle TPU is kind of ridiculous. No quantization. No tiny context window. No expensive GPU instance. Just Qwen3.8-27B running on a Kaggle TPU v5e-8. The reported numbers: ~130 tok/s decode ~10,000 tok/s prefill 262K context That prefill number is especially wild. You can throw a huge amount of code or context at the model and ingest it extremely quickly, while still getting around 130 tokens per second during generation. And because it’s running in full BF16, you’re not relying on an aggressive quant just to make the model fit. But the really interesting part isn’t even the raw throughput. You can expose it as an OpenAI-compatible endpoint. That means you can plug the model into tools that already understand OpenAI-style APIs. Claude Code. Codex. OpenCode. And other compatible clients. So the workflow becomes pretty simple: Spin up the Qwen3.8-27B endpoint on Kaggle. Point your coding tool at the API. And suddenly you have a 27B coding model sitting behind the same interface you’d normally use for hosted models. The 262K context is also a huge deal for agentic coding. Large repositories can fit into a single context. Long conversations don’t need to be constantly trimmed. And tools can feed much more information back to the model without hitting a tiny context ceiling. The fact that this can be built around a free TPU environment is what makes this especially interesting. We’re getting to a point where experimenting with serious open models doesn’t always require owning a $2,000 GPU or paying for a large cloud instance. Free compute + open weights + an OpenAI-compatible API + existing coding agents. That’s a pretty powerful combination. Qwen3.8-27B is already an interesting model. Running the full BF16 version at ~130 tok/s with 262K context on free Kaggle TPU compute makes it a lot more interesting.

Qwen3.8-27B running at full BF16 on a free Kaggle TPU is kind of ridiculous. No quantization. No tiny context window. No expensive GPU instance. Just Qwen3.8-27B running on a Kaggle TPU v5e-8. The reported numbers: ~130 tok/s decode ~10,000 tok/s prefill 262K context That prefill number is especially wild. You can throw a huge amount of code or context at the model and ingest it extremely quickly, while still getting around 130 tokens per second during generation. And because it’s running in full BF16, you’re not relying on an aggressive quant just to make the model fit. But the really interesting part isn’t even the raw throughput. You can expose it as an OpenAI-compatible endpoint. That means you can plug the model into tools that already understand OpenAI-style APIs. Claude Code. Codex. OpenCode. And other compatible clients. So the workflow becomes pretty simple: Spin up the Qwen3.8-27B endpoint on Kaggle. Point your coding tool at the API. And suddenly you have a 27B coding model sitting behind the same interface you’d normally use for hosted models. The 262K context is also a huge deal for agentic coding. Large repositories can fit into a single context. Long conversations don’t need to be constantly trimmed. And tools can feed much more information back to the model without hitting a tiny context ceiling. The fact that this can be built around a free TPU environment is what makes this especially interesting. We’re getting to a point where experimenting with serious open models doesn’t always require owning a $2,000 GPU or paying for a large cloud instance. Free compute + open weights + an OpenAI-compatible API + existing coding agents. That’s a pretty powerful combination. Qwen3.8-27B is already an interesting model. Running the full BF16 version at ~130 tok/s with 262K context on free Kaggle TPU compute makes it a lot more interesting.

FHILY👑

35,910 görüntüleme • 1 ay önce

BREAKING: GPT-5.5 "Spud" is out and it is a BEAST We've been testing it Every 📧 for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check: - It's a step change in coding AND it's easy to talk to. It's fast and friendly and quickly became my daily driver. But it's also a coding powerhouse—a really rare combination. - It scored 62/100 on our Senior Engineer benchmark. Opus 4.7 scored only a 33/100. (But GPT-5.5 performed best when using an Opus 4.7 plan). Naveen Naidu used over 900 million tokens during testing—and it let him ship production features for Monologue at both high speed and quality. - It has serious conceptual clarity. It can hold a complex plan in its head over hours of work, without getting distracted by existing code. This makes it the first model that we've tested that can perform well on complex refactors requiring deleting and reimagining an substantial existing codebase. - It's a very good writer. This is the first OpenAI model in about a year that got our writers Every 📧 to switch away from Claude. 5.5 has Katie Parrott's seal of approval—not an easy task. Its writing feels more organic and it's better at mimicking a writing style without going overboard. - It's great for agentic knowledge-work. This is the first OpenAI model that manages to be both a stellar senior engineer AND that can be used for everything from spreadsheets to research. It's crazy fast, and it's amazing inside of the Codex desktop app, and got much of our team to switch away from Claude Code and Cowork during the testing period. However, it's not a perfect model. - 5.5 still loses to Opus 4.7 on plan quality. It's plans are extremely readable but Opus has better attention to detail and sharper insight. - 5.5 still loses to Opus 4.7 by a bit on front-end and full-stack product work. Kieran Klaassen found that it wasn't quite as good when full-stack thinking and design are involved. And it's not great writing Ruby. - 5.5 is a great vibe coder but if you're vibe coding without a plan it's worse than Opus. Mike Taylor found that Opus is better at reading in between the lines on underspecified vibe-coding tasks. Overall GPT-5.5 is a massive achievement from OpenAI and it deserves a serious look as your daily driver. Read our full vibe check on Every 📧 here:

BREAKING: GPT-5.5 "Spud" is out and it is a BEAST We've been testing it Every 📧 for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check: - It's a step change in coding AND it's easy to talk to. It's fast and friendly and quickly became my daily driver. But it's also a coding powerhouse—a really rare combination. - It scored 62/100 on our Senior Engineer benchmark. Opus 4.7 scored only a 33/100. (But GPT-5.5 performed best when using an Opus 4.7 plan). Naveen Naidu used over 900 million tokens during testing—and it let him ship production features for Monologue at both high speed and quality. - It has serious conceptual clarity. It can hold a complex plan in its head over hours of work, without getting distracted by existing code. This makes it the first model that we've tested that can perform well on complex refactors requiring deleting and reimagining an substantial existing codebase. - It's a very good writer. This is the first OpenAI model in about a year that got our writers Every 📧 to switch away from Claude. 5.5 has Katie Parrott's seal of approval—not an easy task. Its writing feels more organic and it's better at mimicking a writing style without going overboard. - It's great for agentic knowledge-work. This is the first OpenAI model that manages to be both a stellar senior engineer AND that can be used for everything from spreadsheets to research. It's crazy fast, and it's amazing inside of the Codex desktop app, and got much of our team to switch away from Claude Code and Cowork during the testing period. However, it's not a perfect model. - 5.5 still loses to Opus 4.7 on plan quality. It's plans are extremely readable but Opus has better attention to detail and sharper insight. - 5.5 still loses to Opus 4.7 by a bit on front-end and full-stack product work. Kieran Klaassen found that it wasn't quite as good when full-stack thinking and design are involved. And it's not great writing Ruby. - 5.5 is a great vibe coder but if you're vibe coding without a plan it's worse than Opus. Mike Taylor found that Opus is better at reading in between the lines on underspecified vibe-coding tasks. Overall GPT-5.5 is a massive achievement from OpenAI and it deserves a serious look as your daily driver. Read our full vibe check on Every 📧 here:

Dan Shipper 📧

130,382 görüntüleme • 5 ay önce