Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

New paper! LLMs Corrupt Your Documents When You Delegate LLMs are enabling a new way of working: delegated work, where users supervise an LLM as it edits documents on their behalf. Delegation requires trust: does the LLM complete tasks without introducing errors? We simulate delegation across 52 professional domains... show more

Philippe Laban

1,561 subscribers

121,246 views • 5 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs *on the local network* - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs on the local network - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝

LM Studio

142,641 views • 2 years ago

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers

Vikas gupta

14,138 views • 13 days ago

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,250 views • 10 months ago

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

THAT $70 "RUN YOUR OWN LLMS" PI KIT CAN'T RUN A SINGLE LLM. IT'S A VISION CHIP WITH NO RAM. that clip sells a raspberry pi 5 in a slick case with an ai accelerator and the caption "your own llms." clean build, fun kit. the claim is where it breaks. the fine print: the popular $70 pi ai kit uses a hailo-8l, 13 tops. it's built for vision, object detection and image processing, and it has no memory of its own. so it cannot run large language models. full stop the board that actually can is a different one: the newer ai hat+ 2, hailo-10h, 40 tops, with 8gb of dedicated ram. that's $130, not $70 and even that runs only tiny models. llama 3.2 at 1b, qwen 2.5 at 1.5b, deepseek r1 at 1.5b. edge llms live in the 1-7b range, against cloud models at 500b to 2 trillion so the honest pitch: for $130 you can run a very small language model on a pi, slowly, as a fun learning project. that's real and it's cool. "your own llms" on a $70 vision kit is not. why this keeps happening: "ai kit" and a big "tops" number sell. tops sounds like intelligence. but tops measures vision-style math, not whether the chip has the memory to hold a language model. the spec that matters for llms is ram, and the cheap kit has none. the honest caveats, both ways: the $70 kit is genuinely great, just at vision. cameras, object detection, that's its job the $130 hat really does run small llms locally, which a pi couldn't do at all two years ago. that's progress "small" is the load-bearing word. don't expect gpt at home on a pi the takeaway: before you buy a kit because the caption says llm, check two numbers. not the tops. the ram, and the size of the model it can actually load. no 70-dollar miracle, no gpt in a pi case, no tops number that means what you think. save this before you buy the wrong kit for the word on the box.

RetroChainer

11,100 views • 2 months ago

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

The Singularity Layer

13,891 views • 2 months ago

💬 We get asked What should I do if I don’t have my own trading ideas yet? ❕ Answer from a GT App Specialist: You don’t need to be a professional strategist to start trading. GT App’s AI layer generates new strategy ideas every day that you can immediately explore and test. 🔸 Daily AI-generated strategies Advanced LLMs build fresh trading strategies daily. The LLM Builder creates complete strategy setups that you can instantly optimize to see how they would have performed. 🔸 Pick and test in seconds Inside the app you’ll find AI strategy cards labeled by the LLM that generated them. Select a strategy, run an optimization, and instantly review metrics like win rate, trade history, and profit performance. 🔸 Or build a strategy directly in Telegram You can also generate and test strategies through our Telegram bot. Just open @gt_ai_trading_bot, request a strategy for a trading pair, and the AI will build and backtest it for you. Explore AI-generated strategies 👉

💬 We get asked What should I do if I don’t have my own trading ideas yet? ❕ Answer from a GT App Specialist: You don’t need to be a professional strategist to start trading. GT App’s AI layer generates new strategy ideas every day that you can immediately explore and test. 🔸 Daily AI-generated strategies Advanced LLMs build fresh trading strategies daily. The LLM Builder creates complete strategy setups that you can instantly optimize to see how they would have performed. 🔸 Pick and test in seconds Inside the app you’ll find AI strategy cards labeled by the LLM that generated them. Select a strategy, run an optimization, and instantly review metrics like win rate, trade history, and profit performance. 🔸 Or build a strategy directly in Telegram You can also generate and test strategies through our Telegram bot. Just open @gt_ai_trading_bot, request a strategy for a trading pair, and the AI will build and backtest it for you. Explore AI-generated strategies 👉

GT Protocol

32,277 views • 6 months ago

We are investing in the frontiers of agentic capabilities with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you. When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.

We are investing in the frontiers of agentic capabilities with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you. When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.

Sundar Pichai

219,170 views • 1 year ago

🚨 BREAKING: Sec. Pete Hegseth’s Department of War just confirmed they found HIDDEN CLASSIFIED DOCUMENTS “stashed away” during an investigation into the Abbey Gate, Afghanistan bombing under Biden — where 13 Americans died Hidden in SAFES, concealed to not be found 😡😡 PARNELL: “The deeper we look, the more there is to look at. We are finding things that we did not expect.” “Recently, my team recovered highly relevant classified documents — material that should have been disclosed — stashed and hidden away in safes where they would not be found.” “And after the team reviewed these documents, it became clear why someone tried to hide them.” “To the families of those 13, and to every Gold Star family from that war: the country moved on fast, but I know you didn’t get to.” “I know five years is not a number that means anything when it’s your son, your daughter, your husband, or your wife. We have not forgotten them. I will not let this country forget them.” Uncover it all. The families deserve to know! Dems wanted to HIDE THIS.

🚨 BREAKING: Sec. Pete Hegseth’s Department of War just confirmed they found HIDDEN CLASSIFIED DOCUMENTS “stashed away” during an investigation into the Abbey Gate, Afghanistan bombing under Biden — where 13 Americans died Hidden in SAFES, concealed to not be found 😡😡 PARNELL: “The deeper we look, the more there is to look at. We are finding things that we did not expect.” “Recently, my team recovered highly relevant classified documents — material that should have been disclosed — stashed and hidden away in safes where they would not be found.” “And after the team reviewed these documents, it became clear why someone tried to hide them.” “To the families of those 13, and to every Gold Star family from that war: the country moved on fast, but I know you didn’t get to.” “I know five years is not a number that means anything when it’s your son, your daughter, your husband, or your wife. We have not forgotten them. I will not let this country forget them.” Uncover it all. The families deserve to know! Dems wanted to HIDE THIS.

Eric Daugherty

1,049,283 views • 29 days ago

Extracting structured outputs with LLMs is easy. But doing large-scale extraction with precise citations and bounding boxes back to the source documents is way harder. With our latest release in LlamaExtract, we extract citation bounding boxes along with every single key and value within a document. You can see this in the UI. Hover over any k:v pair and you’ll be able to see the corresponding highlights in the source doc. If you’re a human reviewing a million docs (resumes, IDs, invoices, claims, contracts), this will help you 5x your ability to verify values and make sure things are correct. Check out these new extraction upgrades in LlamaCloud:

Extracting structured outputs with LLMs is easy. But doing large-scale extraction with precise citations and bounding boxes back to the source documents is way harder. With our latest release in LlamaExtract, we extract citation bounding boxes along with every single key and value within a document. You can see this in the UI. Hover over any k:v pair and you’ll be able to see the corresponding highlights in the source doc. If you’re a human reviewing a million docs (resumes, IDs, invoices, claims, contracts), this will help you 5x your ability to verify values and make sure things are correct. Check out these new extraction upgrades in LlamaCloud:

Jerry Liu

23,044 views • 7 months ago

There’s been two papers released in the past couple months, one by Google and one by NVIDIA, that argue that ordering the documents retrieved by RAG systems can enhance performance. However, they both give two different strategies on HOW these documents should be ordered 🤔 Both papers agree on two main points: 1️⃣ There’s a fundamental issue in RAG - as more documents are retrieved, more irrelevant context (e.g., hard negatives) are introduced, which leads to confusion for the LLM and eventually degrades the quality of the generated output. This is called an inverted-U performance curve. 2️⃣ Ordering the retrieved documents is a key lever for optimizing RAG performance. Google Cloud researchers proposed ordering results based on relevance scores: The authors in this paper argue for relevance-based reordering, or ordering the retrieved chunks based on their similarity scores, so the most relevant documents are at the beginning and the end of the inputs to counter the “lost in the middle” effect. NVIDIA researchers proposed ordering results based on the original sequence of document chunks: The authors of this paper argue for Order-Preserving Reordering, or Order-Preserve RAG (OP-RAG), to maintain the logically coherent content flow of the document. So they preserved the original order of retrieved document chunks in the source text, instead of ranking them by relevance scores. So which one is right? It probably depends on the specific use case and dataset - relevance-based reordering could perform better in tasks where you need fast access to the most critical information (e.g., fact retrieval, QA systems), while order-preserving RAG might be better where you need to understand the sequential structure of information (e.g., narrative or legal documents). There are still so many uncertainties in AI - we don’t actually know what we’re doing, and it takes awhile to figure out the best strategies for most things! Excited to see more research about this.

There’s been two papers released in the past couple months, one by Google and one by NVIDIA, that argue that ordering the documents retrieved by RAG systems can enhance performance. However, they both give two different strategies on HOW these documents should be ordered 🤔 Both papers agree on two main points: 1️⃣ There’s a fundamental issue in RAG - as more documents are retrieved, more irrelevant context (e.g., hard negatives) are introduced, which leads to confusion for the LLM and eventually degrades the quality of the generated output. This is called an inverted-U performance curve. 2️⃣ Ordering the retrieved documents is a key lever for optimizing RAG performance. Google Cloud researchers proposed ordering results based on relevance scores: The authors in this paper argue for relevance-based reordering, or ordering the retrieved chunks based on their similarity scores, so the most relevant documents are at the beginning and the end of the inputs to counter the “lost in the middle” effect. NVIDIA researchers proposed ordering results based on the original sequence of document chunks: The authors of this paper argue for Order-Preserving Reordering, or Order-Preserve RAG (OP-RAG), to maintain the logically coherent content flow of the document. So they preserved the original order of retrieved document chunks in the source text, instead of ranking them by relevance scores. So which one is right? It probably depends on the specific use case and dataset - relevance-based reordering could perform better in tasks where you need fast access to the most critical information (e.g., fact retrieval, QA systems), while order-preserving RAG might be better where you need to understand the sequential structure of information (e.g., narrative or legal documents). There are still so many uncertainties in AI - we don’t actually know what we’re doing, and it takes awhile to figure out the best strategies for most things! Excited to see more research about this.

Victoria Slocum

15,333 views • 1 year ago

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.

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.

Xuhui Zhou

143,216 views • 3 months ago

LongWriter Unleashing 10,000+ Word Generation from Long Context LLMs discuss: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability.

LongWriter Unleashing 10,000+ Word Generation from Long Context LLMs discuss: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability.

AK

50,995 views • 2 years ago

Project Animus Incubation Update // 🪺🔬 The start of Incubation is postponed as our team requires additional time to test the experience to ensure a functional, seamless, and safe incubation event. We estimate that the Incubation event will be ready in 2-3 weeks, and will provide an update on Twitter and Discord once we confirm a new date. Incubation will remain open for 3 weeks, as planned. We are working very hard to bring it to life, and we can’t wait for you to experience it 🫂. To help keep our community safe, we will also be implementing delegate xyz on 🛡️. The feature will be live from the start of incubation 🛠️.

Project Animus Incubation Update // 🪺🔬 The start of Incubation is postponed as our team requires additional time to test the experience to ensure a functional, seamless, and safe incubation event. We estimate that the Incubation event will be ready in 2-3 weeks, and will provide an update on Twitter and Discord once we confirm a new date. Incubation will remain open for 3 weeks, as planned. We are working very hard to bring it to life, and we can’t wait for you to experience it 🫂. To help keep our community safe, we will also be implementing delegate xyz on 🛡️. The feature will be live from the start of incubation 🛠️.

RTFKT

143,950 views • 2 years ago

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Swapna Kumar Panda

50,358 views • 4 months ago

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

70,090 views • 9 months ago

Almost every brand I’ve talked to has asked me about showing up in LLM answers. Here’s what matters most: 1. Mentions → Does AI actually bring up your brand? 2. Sentiment → When it does… is it positive or negative? 3. Citations → Are you being referenced as a source? You can win in traffic and still lose here. So what actually moves this? 1. Visibility across AI platforms (ChatGPT, Perplexity, Gemini, etc.) 2. Site structure that machines can understand (not just humans) 3. Content designed to answer questions (not just rank for keywords) 4. Trust signals across the internet (reviews, mentions, third-party validation) We’re early, but the data is already clear. AI-attributed commerce is growing fast, and this is only going to compound. You can treat this like SEO in 2012. Or you can get ahead of it now. We put everything we’re seeing into an AI visibility playbook for ecommerce brands. Worth a read if you care about how customers will find you next.

Maxx Blank 🐳

812,417 views • 5 months ago

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

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

Google AI

22,487 views • 10 months ago

Introducing StreamingLLM. Imagine chatting with an AI assistant that can contextually reference your conversations from weeks or months ago. Or summarizing reports that span thousands of pages. StreamingLLM makes this possible by enabling language models to smoothly handle endless texts without losing steam. Current LLMs are like students cramming for an exam - they can only memorize a limited context. StreamingLLM is the valedictorian with a photographic memory of everything you've ever discussed. It works by identifying and preserving the model's inherent "attention sinks" - initial tokens that anchored its reasoning. Combined with a rolling cache of recent tokens, StreamingLLM delivers up to 22x faster inference without any drop in accuracy. You know that irksome feeling when chatbots forget your earlier conversations? StreamingLLM abolishes that frustration. It remembers the touchdowns from your last game and your newborn's name without missing a beat. Monumental books, verbose contracts, drawn out debates - StreamingLLM takes them all in its stride. No shortcuts, no forgetfulness. It's like upgrading your assistant's RAM to handle heavier workloads flawlessly.

Introducing StreamingLLM. Imagine chatting with an AI assistant that can contextually reference your conversations from weeks or months ago. Or summarizing reports that span thousands of pages. StreamingLLM makes this possible by enabling language models to smoothly handle endless texts without losing steam. Current LLMs are like students cramming for an exam - they can only memorize a limited context. StreamingLLM is the valedictorian with a photographic memory of everything you've ever discussed. It works by identifying and preserving the model's inherent "attention sinks" - initial tokens that anchored its reasoning. Combined with a rolling cache of recent tokens, StreamingLLM delivers up to 22x faster inference without any drop in accuracy. You know that irksome feeling when chatbots forget your earlier conversations? StreamingLLM abolishes that frustration. It remembers the touchdowns from your last game and your newborn's name without missing a beat. Monumental books, verbose contracts, drawn out debates - StreamingLLM takes them all in its stride. No shortcuts, no forgetfulness. It's like upgrading your assistant's RAM to handle heavier workloads flawlessly.

Carlos E. Perez

557,849 views • 3 years ago

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at hello@qualiastudios.dev More soon

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at [email protected] More soon

Qualia

87,991 views • 3 months ago

Introducing Attio Objects 🚀 We know how hard it is to find a CRM that fits your unique business model. That's why we built Attio Objects – our powerful data model with custom objects that gives you complete flexibility to structure your CRM exactly how you need it. Along with custom objects, we've also introduced new standard objects: - Workspaces and Users objects for PLG businesses. - A robust Deals object for sales-driven companies. This is the culmination of a 4-year effort, with 3 years of work put in even before launching Attio. Since day one, we've been determined to solve the fundamental problem in the CRM space: the trade-off between power and time-to-value. If you wanted power and flexibility, your CRM would take forever to build and not work well with your stack. If you wanted speed, you'd need to use highly opinionated, inflexible software that doesn't really work for your business. That ends today. With Attio, you no longer have to compromise. Build your CRM your way, fast. Iterate as you grow. High-growth startups like Replicate, , and Modal and more are already using Attio's object architecture to perfectly match their businesses and accelerate their growth. To get all the details, check out our blog post 👇

Introducing Attio Objects 🚀 We know how hard it is to find a CRM that fits your unique business model. That's why we built Attio Objects – our powerful data model with custom objects that gives you complete flexibility to structure your CRM exactly how you need it. Along with custom objects, we've also introduced new standard objects: - Workspaces and Users objects for PLG businesses. - A robust Deals object for sales-driven companies. This is the culmination of a 4-year effort, with 3 years of work put in even before launching Attio. Since day one, we've been determined to solve the fundamental problem in the CRM space: the trade-off between power and time-to-value. If you wanted power and flexibility, your CRM would take forever to build and not work well with your stack. If you wanted speed, you'd need to use highly opinionated, inflexible software that doesn't really work for your business. That ends today. With Attio, you no longer have to compromise. Build your CRM your way, fast. Iterate as you grow. High-growth startups like Replicate, , and Modal and more are already using Attio's object architecture to perfectly match their businesses and accelerate their growth. To get all the details, check out our blog post 👇

Attio

26,904 views • 2 years ago