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 our latest technical report: Context Rot - How Increasing Input Tokens Impacts LLM Performance Our results reveal that models do not use their context uniformly. full report in replies

Chroma

29,613 subscribers

184,747 views • 11 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Chroma11 months ago

Read the full report here:

Mobile Scanner1 year ago

Scan any documents, convert images into text, PDF files, etc. 👍

jason liu11 months ago

wow veo3 is so good

Kinjal Nandy11 months ago

Lfg @kellyhongsn

noah11 months ago

feel like we've all known this so im glad it was rigerously tested

dinos11 months ago

you guys are on fire

Chroma11 months ago

spread the news

Allan Ryan11 months ago

Is she AI?

Chroma11 months ago

100% human intelligence

sarv11 months ago

Wooo @kellyhongsn!!

Olivier11 months ago

benchmark different context engineering strategies next good content

Related Videos

It's not only about how long your context is, but how well you use it. Great to see Gemini 2.5 models dominating MRCR and other benchmarks on long context! See 2.5 Pro tackle a complex coding task by reasoning over an entire repo (>500k tokens). Performance and effective use of the (loooong) context windows are what really matter!

It's not only about how long your context is, but how well you use it. Great to see Gemini 2.5 models dominating MRCR and other benchmarks on long context! See 2.5 Pro tackle a complex coding task by reasoning over an entire repo (>500k tokens). Performance and effective use of the (loooong) context windows are what really matter!

Oriol Vinyals

27,008 views • 1 year ago

At Chevron, we’re increasing transparency by annually reporting metrics and performance data. Want to see the numbers? Click to download our latest report.

At Chevron, we’re increasing transparency by annually reporting metrics and performance data. Want to see the numbers? Click to download our latest report.

Chevron

13,225 views • 2 years ago

Excited to share the technical report for RadRotator, our latest #GenerativeAI tool, which enables the rotation of radiographs in 3D space💫 ✅Technical Report: 🔗 ✅Website: 🔗 ✅Online Demo: 🔗 (1/3)

Excited to share the technical report for RadRotator, our latest #GenerativeAI tool, which enables the rotation of radiographs in 3D space💫 ✅Technical Report: 🔗 ✅Website: 🔗 ✅Online Demo: 🔗 (1/3)

Pouria Rouzrokh, MD

23,554 views • 2 years ago

Cursor can now show your agent's context usage as an interactive report in a canvas. The context explorer breaks down where tokens go across the system prompt, tool definitions, rules, skills, and more.

Cursor can now show your agent's context usage as an interactive report in a canvas. The context explorer breaks down where tokens go across the system prompt, tool definitions, rules, skills, and more.

Cursor

36,406 views • 19 days ago

Today we released our Q4 and full year 2025 financial results, showing performance in line with our expectations. Our President and CEO, Justin Hotard takes us through some of the key takeaways. Read full report: #QComms #TeamNokia

Today we released our Q4 and full year 2025 financial results, showing performance in line with our expectations. Our President and CEO, Justin Hotard takes us through some of the key takeaways. Read full report: #QComms #TeamNokia

Nokia

27,807 views • 4 months ago

Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: Blog: Technical report:

Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: Blog: Technical report:

Simon Kohl

56,880 views • 11 months ago

This morning, we announced our Q2 2023 financial results. Check out our full earnings report, including our Letter to Shareholders:

This morning, we announced our Q2 2023 financial results. Check out our full earnings report, including our Letter to Shareholders:

Roblox

367,950 views • 2 years ago

Today, we announced $CRM Q3 FY24 results and updated guidance. Dive in to our full earnings report:

Today, we announced $CRM Q3 FY24 results and updated guidance. Dive in to our full earnings report:

Salesforce

11,403 views • 2 years ago

FramePack is out Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

FramePack is out Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

AK

31,486 views • 1 year ago

An important report by Sky News’s Becky Johnson that highlights the increasing number of children educated in unregulated educational settings and the perverse incentives that act against our most inclusive schools and nurseries. Full report below. NAHT

An important report by Sky News’s Becky Johnson that highlights the increasing number of children educated in unregulated educational settings and the perverse incentives that act against our most inclusive schools and nurseries. Full report below. NAHT

Simon Kidwell

28,426 views • 2 years ago

🚨 The State of AI in Retail and CPG: 2026 Trends report is live. • 89% say AI is increasing revenue. • 79% report open-source models and software were important to their AI strategy. 📥 Read the blog and download the full report:

🚨 The State of AI in Retail and CPG: 2026 Trends report is live. • 89% say AI is increasing revenue. • 79% report open-source models and software were important to their AI strategy. 📥 Read the blog and download the full report:

NVIDIA AI

30,497 views • 5 months ago

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,729 views • 1 year ago

Introducing DuoAttention: Our new framework slashes both memory and latency for long-context LLMs without sacrificing performance! By applying full KV cache only to critical heads, we achieve: ⚡ 2.55x memory reduction ⚡ 2.18x decoding speedup ⚡ 3.3M tokens on a single A100 GPU

Introducing DuoAttention: Our new framework slashes both memory and latency for long-context LLMs without sacrificing performance! By applying full KV cache only to critical heads, we achieve: ⚡ 2.55x memory reduction ⚡ 2.18x decoding speedup ⚡ 3.3M tokens on a single A100 GPU

Guangxuan Xiao

31,023 views • 1 year ago

Our President and CEO, Justin Hotard shares the top 3 takeaways from our Q3 2025 financial results. Read full report:

Our President and CEO, Justin Hotard shares the top 3 takeaways from our Q3 2025 financial results. Read full report:

Nokia

12,931 views • 8 months ago

Andrej Karpathy calls large language models the new computing paradigm: CPU -> LLM bytes -> tokens RAM -> context window this is the large language model OS (LMOS)

Andrej Karpathy calls large language models the new computing paradigm: CPU -> LLM bytes -> tokens RAM -> context window this is the large language model OS (LMOS)

ℏεsam

343,256 views • 1 year ago

Most conversational AI understands words, not people. Introducing Raven-1, our audio and video perception model that gives AI the ability to understand emotion, intent, and context the way humans do.

Most conversational AI understands words, not people. Introducing Raven-1, our audio and video perception model that gives AI the ability to understand emotion, intent, and context the way humans do.

Tavus

1,672,503 views • 4 months ago

Whenever someone asks how the Dow is doing, I think Emma Vigeland reading this IM last month on Majority Report. Matt Lech No Context Majority Report

Whenever someone asks how the Dow is doing, I think Emma Vigeland reading this IM last month on Majority Report. Matt Lech No Context Majority Report

Faisal Hassan

72,176 views • 3 months ago

📹 Is it worth submitting a video of a close pass? Footage can help, but context matters. Our latest blog explains how Operation SNAP works and why a short description can be as important as the video itself. 👉 Make your report count:

📹 Is it worth submitting a video of a close pass? Footage can help, but context matters. Our latest blog explains how Operation SNAP works and why a short description can be as important as the video itself. 👉 Make your report count:

Cycling UK

11,512 views • 5 months ago

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

19,236 views • 9 months ago

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,435 views • 1 year ago