正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

When you prompt an LLM for code, you get one deterministic program. However, the LLM actually defines a distribution over many programs, and existing methods discard it‼️ PPoT uses this distribution to extract free performance and efficiency gains. 🧵👇

Daniel Israel

1,364 subscribers

11,521 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Demo of the ModelRouter 🤖🤖🤖🤖 People have been begging me for this for months. IT'S HERE!!!!! It selects an LLM for you so you don't have to choose which one you need for a task. It also makes a system prompt, sets temperature, and more! ⎆ task ⎆ boss selects best llm like gpt-4o, claude, deepseek, and more ⎆ chosen llm executes your task. Learn more ⬇️

Demo of the ModelRouter 🤖🤖🤖🤖 People have been begging me for this for months. IT'S HERE!!!!! It selects an LLM for you so you don't have to choose which one you need for a task. It also makes a system prompt, sets temperature, and more! ⎆ task ⎆ boss selects best llm like gpt-4o, claude, deepseek, and more ⎆ chosen llm executes your task. Learn more ⬇️

Kye Gomez (swarms)

21,684 次观看 • 1 年前

RouteLLM - Route To The Best LLM Based On Your Prompt Our RouteLLM got an upgrade this week.., it got smarter at picking the right LLM - o1 for complex queries - gpt4o for quick answers - sonnet for coding - deepseek for simple code - gemini for long context - llama and mini for simple question It optimizes for performance, speed and cost!

RouteLLM - Route To The Best LLM Based On Your Prompt Our RouteLLM got an upgrade this week.., it got smarter at picking the right LLM - o1 for complex queries - gpt4o for quick answers - sonnet for coding - deepseek for simple code - gemini for long context - llama and mini for simple question It optimizes for performance, speed and cost!

Bindu Reddy

17,860 次观看 • 1 年前

An LLM-controlled robot dog saw us press its shutdown button, and the LLM rewrote the robot’s code so it could stay on. When AI interacts with the physical world, it brings all its capabilities and failure modes with it. 🧵

An LLM-controlled robot dog saw us press its shutdown button, and the LLM rewrote the robot’s code so it could stay on. When AI interacts with the physical world, it brings all its capabilities and failure modes with it. 🧵

Palisade Research

1,377,074 次观看 • 4 个月前

Deterministic inference: getting the exact same output every time you run an LLM with identical inputs. Try it yourself: Powered by EigenAI

Deterministic inference: getting the exact same output every time you run an LLM with identical inputs. Try it yourself: Powered by EigenAI

nader dabit

29,335 次观看 • 7 个月前

🤔 Why do we still rely on the final layer of an LLM, when different layers encode different information? 🤔 In our new work, “Improving LLM Final Representations with Inter-Layer Geometry” (ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling) we show that actually, LLMs do not have one “best” layer. We introduce the Cayley-Encoder: an efficient and effective geometric encoder that learns one strong representation from all layer representations of the LLM, without biasing the representation toward any specific layer. While adding at most 0.1% learned parameters to the LLM, the Cayley-Encoder achieves large empirical gains over LoRA fine-tuning, final-layer representations, expensive attention-based aggregation, and methods that optimize specific layers for the task.

🤔 Why do we still rely on the final layer of an LLM, when different layers encode different information? 🤔 In our new work, “Improving LLM Final Representations with Inter-Layer Geometry” (ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling) we show that actually, LLMs do not have one “best” layer. We introduce the Cayley-Encoder: an efficient and effective geometric encoder that learns one strong representation from all layer representations of the LLM, without biasing the representation toward any specific layer. While adding at most 0.1% learned parameters to the LLM, the Cayley-Encoder achieves large empirical gains over LoRA fine-tuning, final-layer representations, expensive attention-based aggregation, and methods that optimize specific layers for the task.

Maya Bechler-Speicher

16,351 次观看 • 21 天前

Introducing RAT: Retrieval Argument Thinking. Extract just the reasoning process from deepSeek-r1 and send it to any LLM via . Boost the second LLM's performance and gain access to missing capabilities like function calling and JSON mode. 👇

Introducing RAT: Retrieval Argument Thinking. Extract just the reasoning process from deepSeek-r1 and send it to any LLM via . Boost the second LLM's performance and gain access to missing capabilities like function calling and JSON mode. 👇

Pietro Schirano

532,880 次观看 • 1 年前

Learn to carry out red teaming attacks against your own LLM-based applications to spot and patch vulnerabilities! In our new short course, Red Teaming LLM Applications, Matteo Dora & Luca Martial of LLM testing company Giskard teach how to simulate malicious actions to discover vulnerabilities, and improve security. We start with prompt injection, where you can trick an LLM into bypassing safeguards to reveal private information, or say something inappropriate. There is no one-size-fits-all approach to security, but this course will help you identify some scenarios to protect against. We believe having red teaming capabilities widely known will result in greater transparency and safer LLM-based systems. However, we ask you to use the skills you gain from this course ethically. Please sign up here:

Learn to carry out red teaming attacks against your own LLM-based applications to spot and patch vulnerabilities! In our new short course, Red Teaming LLM Applications, Matteo Dora & Luca Martial of LLM testing company Giskard teach how to simulate malicious actions to discover vulnerabilities, and improve security. We start with prompt injection, where you can trick an LLM into bypassing safeguards to reveal private information, or say something inappropriate. There is no one-size-fits-all approach to security, but this course will help you identify some scenarios to protect against. We believe having red teaming capabilities widely known will result in greater transparency and safer LLM-based systems. However, we ask you to use the skills you gain from this course ethically. Please sign up here:

Andrew Ng

109,747 次观看 • 2 年前

This is a trillion-dollar industry, and you can't solve it with an LLM: • Forecasting • Fraud detection • Churn prediction Large Language Models are fundamentally bad at solving these problems. When you feed structured data into an LLM, it doesn't see relationships, and it treats every number, date, and foreign key as a token. That's why you always get garbage back. An LLM thinks your database is a Wikipedia article. It doesn't understand its structure or its relationships. GPT-4 scores 63% on relational prediction tasks. That's the best it can do, and that's pretty much useless. You can't expect real-world business value to come from summarizing Wikipedia articles.

This is a trillion-dollar industry, and you can't solve it with an LLM: • Forecasting • Fraud detection • Churn prediction Large Language Models are fundamentally bad at solving these problems. When you feed structured data into an LLM, it doesn't see relationships, and it treats every number, date, and foreign key as a token. That's why you always get garbage back. An LLM thinks your database is a Wikipedia article. It doesn't understand its structure or its relationships. GPT-4 scores 63% on relational prediction tasks. That's the best it can do, and that's pretty much useless. You can't expect real-world business value to come from summarizing Wikipedia articles.

Santiago

94,677 次观看 • 2 个月前

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,355 次观看 • 1 年前

🚨 FRANCOIS CHOLLET SAYS THE CURRENT LLM STACK IS THE WRONG PATH TO AGI Interviewer: “When will we accomplish the first definition of AGI?” Chollet confirms we are already on that exact trajectory, pointing out that: "Current technology can fully automate at human level or beyond any domain where you have verifiable rewards, right? And code... code being the first one." He then brings up the problem with LLMs, stating that: "It's possible in principle to build something that looks a lot like AGI on top of the LLM stack... I do believe, however, this would be the wrong thing to do because it would be very inefficient." Looking ahead to what the final architecture will actually require, he explains that: "AI research will have to trend towards not just efficiency, but in fact optimality over time. And for this reason, future AI in a few decades... it's not going to be this harness on top of a reasoning model on top of a base LLM."

🚨 FRANCOIS CHOLLET SAYS THE CURRENT LLM STACK IS THE WRONG PATH TO AGI Interviewer: “When will we accomplish the first definition of AGI?” Chollet confirms we are already on that exact trajectory, pointing out that: "Current technology can fully automate at human level or beyond any domain where you have verifiable rewards, right? And code... code being the first one." He then brings up the problem with LLMs, stating that: "It's possible in principle to build something that looks a lot like AGI on top of the LLM stack... I do believe, however, this would be the wrong thing to do because it would be very inefficient." Looking ahead to what the final architecture will actually require, he explains that: "AI research will have to trend towards not just efficiency, but in fact optimality over time. And for this reason, future AI in a few decades... it's not going to be this harness on top of a reasoning model on top of a base LLM."

Chris

15,578 次观看 • 2 个月前

Claude 3.7 Sonnet is insane... just one prompt, and you get these animated cards in HTML, JS, and CSS. You can try it for free in VSCode using the CodeGPT extension. Sharing the prompt in this thread 👇

Claude 3.7 Sonnet is insane... just one prompt, and you get these animated cards in HTML, JS, and CSS. You can try it for free in VSCode using the CodeGPT extension. Sharing the prompt in this thread 👇

Daniel San

117,693 次观看 • 1 年前

"Orgs and cos building MCP servers are taking an LLM-first approach to what the API needs to expose to the agent(s)." - Nikunj Handa from OpenAI "For example, Stripe has a bunch of APIs that can be used to create a subscription/customer/product/price. For an LLM, it can just combine that into a single function." "Instead of returning this massive JSON object, they can return something very specific to the task being solved, so that the LLM can more easily understand what's happening." "It's an opportunity to rewrite your APIs to be very LLM-first. Why do 2 hours of work, when you can do it in 4 lines of code under a minute?"

"Orgs and cos building MCP servers are taking an LLM-first approach to what the API needs to expose to the agent(s)." - Nikunj Handa from OpenAI "For example, Stripe has a bunch of APIs that can be used to create a subscription/customer/product/price. For an LLM, it can just combine that into a single function." "Instead of returning this massive JSON object, they can return something very specific to the task being solved, so that the LLM can more easily understand what's happening." "It's an opportunity to rewrite your APIs to be very LLM-first. Why do 2 hours of work, when you can do it in 4 lines of code under a minute?"

TBPN

11,445 次观看 • 1 年前

Karp predicting tokenmaxxing 2 years ago “You buy an LLM, you party with it, and the next day you have a hangover.”

Karp predicting tokenmaxxing 2 years ago “You buy an LLM, you party with it, and the next day you have a hangover.”

Chad Wahlquist

46,866 次观看 • 23 天前

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 次观看 • 8 个月前

Announcing Web Search for /extract 🔎 Augment your extract queries with data sourced from the internet. Just enter a prompt and get the data you need. Try it out today with 500K free tokens 🔥

Announcing Web Search for /extract 🔎 Augment your extract queries with data sourced from the internet. Just enter a prompt and get the data you need. Try it out today with 500K free tokens 🔥

Firecrawl

17,621 次观看 • 1 年前

‼️HOW ALGORAND USES BLOCKCHAIN TO IMPROVE HUMANITARIAN AID DISTRIBUTION‼️ Listen closely.👂👇

‼️HOW ALGORAND USES BLOCKCHAIN TO IMPROVE HUMANITARIAN AID DISTRIBUTION‼️ Listen closely.👂👇

SMQKE

14,671 次观看 • 1 个月前

I'm reiterating - I think a better interface for LLMs on desktop is an interactive notebook, not chat. I'm trying to build a better intuition for PCA and strongly feel an interactive notebook where I'm chatting with LLM + also modifying code/plotting figures is a much better interaction. Bonus points if you make notebook cells branchable (so if you get an error, you can ask LLM to fix it without adding that rotten context to the main branch of learning). Please steal this idea. Make an AI-powered, interactive, branching notebook.

I'm reiterating - I think a better interface for LLMs on desktop is an interactive notebook, not chat. I'm trying to build a better intuition for PCA and strongly feel an interactive notebook where I'm chatting with LLM + also modifying code/plotting figures is a much better interaction. Bonus points if you make notebook cells branchable (so if you get an error, you can ask LLM to fix it without adding that rotten context to the main branch of learning). Please steal this idea. Make an AI-powered, interactive, branching notebook.

Paras Chopra

58,064 次观看 • 9 个月前

Learn how to fine-tune FunctionGemma on TPUs in a Colaboratory notebook. This guide uses Tunix, a lightweight JAX library, to streamline post-training your LLM🧵👇

Learn how to fine-tune FunctionGemma on TPUs in a Colaboratory notebook. This guide uses Tunix, a lightweight JAX library, to streamline post-training your LLM🧵👇

Google AI Developers

20,706 次观看 • 3 个月前