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.

Introducing TALES - Text Adventure Learning Environment Suite A benchmark of a few hundred text envs: science experiments and embodied cooking to solving murder mysteries. We test over 30 of the best LLM agents and pinpoint failure modes +how to improve 👨‍💻pip install tale-suite

Prithviraj (Raj) Ammanabrolu

8,221 subscribers

16,463 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Arcade Adventure, a new suite of tools designed for seamless, personalized, and beautiful storytelling at scale.

Introducing Arcade Adventure, a new suite of tools designed for seamless, personalized, and beautiful storytelling at scale.

Arcade 🕹️

12,784 views • 2 years ago

Introducing Lovable’s new toolbar. Shift between four modes to annotate, select elements, edit text, and add comments.

Introducing Lovable’s new toolbar. Shift between four modes to annotate, select elements, edit text, and add comments.

Lovable

63,223 views • 21 days ago

I don’t know if you noticed, but the last few versions of Codex Remote went from jumpy scrolling to smooth streaming. I really like how it turned out. And also, the best way to test and debug that? Ask Codex for an endless wall of text.

I don’t know if you noticed, but the last few versions of Codex Remote went from jumpy scrolling to smooth streaming. I really like how it turned out. And also, the best way to test and debug that? Ask Codex for an endless wall of text.

Thomas Ricouard

40,712 views • 29 days ago

To best support its merchants, DoorDash is building an intelligence system with a suite of AI agents. From Andy Fang:

To best support its merchants, DoorDash is building an intelligence system with a suite of AI agents. From Andy Fang:

Modal

15,860 views • 1 month ago

react-native-enriched 🤝 <EnrichedText> We just dropped a dedicated text component, making it a complete rich-text solution. Now it only takes a few lines of code to get your inputs and display text working seamlessly together using the exact same format.

react-native-enriched 🤝 <EnrichedText> We just dropped a dedicated text component, making it a complete rich-text solution. Now it only takes a few lines of code to get your inputs and display text working seamlessly together using the exact same format.

Software Mansion

19,379 views • 2 months ago

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Alec Helbling

94,095 views • 6 months ago

Get beautiful text animations. We built a hand-crafted collection of text animations and wrapped them as a SKILL for your AI agent. Use it with Remotion, Motion, GSAP, WAAPI, or any animation library. It comes with clear animation specs - pacing, curves, transitions - so your output looks great from the first prompt. Install it with: npx skills add pixel-point/animate-text --skill animate-text Use it /animate-text apply soft-blur-in to hero section text

Get beautiful text animations. We built a hand-crafted collection of text animations and wrapped them as a SKILL for your AI agent. Use it with Remotion, Motion, GSAP, WAAPI, or any animation library. It comes with clear animation specs - pacing, curves, transitions - so your output looks great from the first prompt. Install it with: npx skills add pixel-point/animate-text --skill animate-text Use it /animate-text apply soft-blur-in to hero section text

Alex Barashkov

123,885 views • 2 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

A quick way to improve how text behaves in your app is to use `text-wrap: balance`. It distributes text evenly across each line, avoiding orphaned words. It is only supported for a limited number lines (<6-10 depending on the browser), which means it's best used for headings or short paragraphs.

A quick way to improve how text behaves in your app is to use `text-wrap: balance`. It distributes text evenly across each line, avoiding orphaned words. It is only supported for a limited number lines (<6-10 depending on the browser), which means it's best used for headings or short paragraphs.

Jakub Krehel

58,413 views • 4 months ago

seedance video cloning is so good you can create 100s of versions of the same ad in a few minutes and test different geo/demographic video with text is the original one

seedance video cloning is so good you can create 100s of versions of the same ad in a few minutes and test different geo/demographic video with text is the original one

MAX

119,747 views • 1 month ago

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.

Ostris

19,095 views • 1 day ago

HOW TO TEXT A GIRL AT NIGHT (AND ACTUALLY GET A REPLY) 👀🔥 Threads 👇 Don’t text “you up?”

HOW TO TEXT A GIRL AT NIGHT (AND ACTUALLY GET A REPLY) 👀🔥 Threads 👇 Don’t text “you up?”

shija Habib

60,410 views • 1 month ago

introducing: text decrypt scroll effect for Framer add this to reveal text with a sleek decryption animation as you scroll. comment "DECRYPT" and I'll send you the component :)

introducing: text decrypt scroll effect for Framer add this to reveal text with a sleek decryption animation as you scroll. comment "DECRYPT" and I'll send you the component :)

Framer University

16,369 views • 1 year ago

We’re excited to released our first DocC interactive tutorial for the Composable Architecture. It walks you through the basics of creating a feature, layering on some side effects, and writing a full test suite. And we have more coming soon! 👉

We’re excited to released our first DocC interactive tutorial for the Composable Architecture. It walks you through the basics of creating a feature, layering on some side effects, and writing a full test suite. And we have more coming soon! 👉

Point-Free

24,334 views • 3 years ago

I put 9 of the top AI text-to-video generators to the test with a tough prompt. The results? We ArE sO cOoKeD. JK but for reals, take a look.

I put 9 of the top AI text-to-video generators to the test with a tough prompt. The results? We ArE sO cOoKeD. JK but for reals, take a look.

Pizza Later

171,511 views • 1 year ago

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.

We’re excited to introduce Text-to-LoRA: a Hypernetwork that generates task-specific LLM adapters (LoRAs) based on a text description of the task. Catch our presentation at #ICML2025! Paper: Code: Biological systems are capable of rapid adaptation, given limited sensory cues. For example, our human visual system can quickly adapt and tune its light sensitivity to our surroundings. While modern LLMs exhibit a wide variety of capabilities and knowledge, they remain rigid when adding task-specific capabilities. Traditionally, customizing these models requires gathering large datasets and performing often expensive, time-consuming fine-tuning for specific applications. To bypass these limitations, Text-to-LoRA (T2L) meta-learns a “hypernetwork” that takes in a text description of a desired task, as a prompt, and generates a task-specific LoRA that performs well on the task. In our experiments, we show that T2L can encode hundreds of existing LoRA adapters. While the compression is lossy, T2L maintains the performance of task-specifically tuned LoRA adapters. We also show that T2L can even generalize to unseen tasks given a natural language description of the tasks. Importantly, Text-to-LoRA is parameter-efficient. It generates LoRAs in a single, inexpensive step, based solely on a simple text description of the task. This approach is a step towards dramatically lowering the technical and computational barriers, allowing non-technical users to specialize foundation models using plain language, rather than needing deep technical expertise or large compute resources.

Sakana AI

403,067 views • 1 year ago

Text-to-image generators are incredible! But why must we use *plain text* as the interface? 🤔 Check out Rich Text-to-Image generation! Rich Text offers an intuitive and expressive way to explore your visual imagination. Some of my favorite examples. 👇

Text-to-image generators are incredible! But why must we use plain text as the interface? 🤔 Check out Rich Text-to-Image generation! Rich Text offers an intuitive and expressive way to explore your visual imagination. Some of my favorite examples. 👇

Jia-Bin Huang

73,372 views • 2 years ago

🚀 Big announcement! I’ve teamed up with Yunfei He to launch Vue AI — an unofficial Vue community dedicated to empowering Vue.js developers with a full suite of AI tools and support. We’re now polishing Agents Skills for Vue and cooking up even more exciting stuff. Stay tuned! 💚

🚀 Big announcement! I’ve teamed up with Yunfei He to launch Vue AI — an unofficial Vue community dedicated to empowering Vue.js developers with a full suite of AI tools and support. We’re now polishing Agents Skills for Vue and cooking up even more exciting stuff. Stay tuned! 💚

SerKo

17,355 views • 5 months ago

Drag & Drop to build AI agents 🤯 Introducing n8n, a visual UI for building AI agents with LangChain without writing a single line of Python code. Now build automation around LLM apps with NoCode and give superpowers to ChatGPT.

Drag & Drop to build AI agents 🤯 Introducing n8n, a visual UI for building AI agents with LangChain without writing a single line of Python code. Now build automation around LLM apps with NoCode and give superpowers to ChatGPT.

Shubham Saboo

547,731 views • 2 years ago

Team, meet Cobot The first suite of AI agents built to accelerate your team. Made by Mainframe.

Team, meet Cobot The first suite of AI agents built to accelerate your team. Made by Mainframe.

Cobot

81,629 views • 1 year ago