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.

We gave two agents the same task: “Find images matching this description.” Both use Gemma 4 31B. One runs on Cerebras. The other runs on GPUs. You can see the difference. Speed changes the product experience. What would you build if you didn't have to wait?

Cerebras

58,853 subscribers

87,056 views • 12 days ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Cerebras

256,753 views • 14 days ago

How can you race if everyone runs the same speed? 🤔

How can you race if everyone runs the same speed? 🤔

Dirty Mo Media

55,823 views • 11 months ago

Fast tokens are the most valuable tokens. Because inference speed is productivity. And Cerebras makes the fastest tokens in the world. Google DeepMind's Gemma 4 runs at 1,500+ tokens per second on Cerebras — more than an order of magnitude faster than on GPUs and 15x faster than Claude Haiku 4.5. Private preview today. GA later this month. Build blazing fast multimodal apps.

Fast tokens are the most valuable tokens. Because inference speed is productivity. And Cerebras makes the fastest tokens in the world. Google DeepMind's Gemma 4 runs at 1,500+ tokens per second on Cerebras — more than an order of magnitude faster than on GPUs and 15x faster than Claude Haiku 4.5. Private preview today. GA later this month. Build blazing fast multimodal apps.

Andrew Feldman

12,008 views • 25 days ago

Jeffrey Epstein says there would be “RUNS on the bank” if the public knew how the banking system works. “If you have one [dollar], you can lend out nine. That’s the way our system works.” “People on the street... would find it impossible to believe.”

Jeffrey Epstein says there would be “RUNS on the bank” if the public knew how the banking system works. “If you have one [dollar], you can lend out nine. That’s the way our system works.” “People on the street... would find it impossible to believe.”

The Vigilant Fox 🦊

4,479,215 views • 5 months ago

what if you could instantly clone any object? Gemma 4 is now on Cerebras Inference, running up to 10x faster than GPUs (1,500 tokens/sec). Multimodal generations you can iterate on in real time :)

what if you could instantly clone any object? Gemma 4 is now on Cerebras Inference, running up to 10x faster than GPUs (1,500 tokens/sec). Multimodal generations you can iterate on in real time :)

Sarah Chieng

32,686 views • 21 days ago

Charles Barkley on the Knicks: “I’m not saying this is the greatest team ever. If they win these next two games, this is one of the greatest runs in playoff history. It’s one of the greatest runs. You have to give them their props”

Charles Barkley on the Knicks: “I’m not saying this is the greatest team ever. If they win these next two games, this is one of the greatest runs in playoff history. It’s one of the greatest runs. You have to give them their props”

NBA Courtside

1,331,901 views • 1 month ago

What if language models didn't have to generate one token at a time? Our CEO Stefano Ermon joined @TBPN to break down how Mercury 2's diffusion LLM hits 1,000+ tok/s on standard NVIDIA GPUs — and why speed changes the product for coding, voice agents, and search.

What if language models didn't have to generate one token at a time? Our CEO Stefano Ermon joined @TBPN to break down how Mercury 2's diffusion LLM hits 1,000+ tok/s on standard NVIDIA GPUs — and why speed changes the product for coding, voice agents, and search.

Inception

27,108 views • 4 months ago

324 runs on the board 9 wickets down 1 run to win And then… 😅 What would you do if you were the bowler?

324 runs on the board 9 wickets down 1 run to win And then… 😅 What would you do if you were the bowler?

Cricket Shouts 🏏

88,436 views • 1 year ago

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Avi Chawla

40,282 views • 1 year ago

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 views • 11 months ago

$"Polygon as a blockchain, gets the same value if you move $1 or a billion. It's a fraction of a cent. No one cares." Wallets, ramps, and every other layer in the payments stack were compressing toward the same thing. Polygon | POL bundles all of it. "You can transact on a couple of chains that work extremely well. You can use a couple of wallets that give you the level of service or product that you need. You can use different ramps, and they will be quite similar. But when you put all of that together on the same infrastructure, the same product, that's where we see the value." mechanove.eth (※,※) on the show today.$

"Polygon as a blockchain, gets the same value if you move $1 or a billion. It's a fraction of a cent. No one cares." Wallets, ramps, and every other layer in the payments stack were compressing toward the same thing. Polygon | POL bundles all of it. "You can transact on a couple of chains that work extremely well. You can use a couple of wallets that give you the level of service or product that you need. You can use different ramps, and they will be quite similar. But when you put all of that together on the same infrastructure, the same product, that's where we see the value." mechanove.eth (※,※) on the show today.

Stabledash

11,912 views • 25 days ago

what can you build with gpt-5.3-codex-spark? jason liu from OpenAI demos 3 real workflows — ones you can set up yourself inside the Codex app to help you spend less time on overhead and more time building. 00:09 – what is gpt-5.3-codex-spark? 00:25 – workflow 1: multi-agent daily briefing from slack, drive & meets 01:06 – workflow 2: automated PR review 01:31 – workflow 3: real-time interactive coding 02:56 – what speed changes, and what's coming next

what can you build with gpt-5.3-codex-spark? jason liu from OpenAI demos 3 real workflows — ones you can set up yourself inside the Codex app to help you spend less time on overhead and more time building. 00:09 – what is gpt-5.3-codex-spark? 00:25 – workflow 1: multi-agent daily briefing from slack, drive & meets 01:06 – workflow 2: automated PR review 01:31 – workflow 3: real-time interactive coding 02:56 – what speed changes, and what's coming next

Cerebras

23,633 views • 3 months ago

Gutfeld: That is garbage. That is absolute garbage. I will give you the both sides. On one hand you have the hard left and on the other hand you have the left. Both sides of the same coin. You walk into this room and you are not reading it. Because there is no both sides. You guys act on it. We don't

Gutfeld: That is garbage. That is absolute garbage. I will give you the both sides. On one hand you have the hard left and on the other hand you have the left. Both sides of the same coin. You walk into this room and you are not reading it. Because there is no both sides. You guys act on it. We don't

Acyn

357,813 views • 9 months ago

Today we're introducing Wave. A proactive product agent that helps teams build self-improving products. Every product team runs the same loop. Build, ship, use, learn. AI has made building and shipping extraordinarily fast. Understanding usage and learning still happen by hand. Wave runs the whole loop: - Analyzes your Amplitude data for signals across analytics, feedback, session replays, error logs, agent traces, and experiment results - Surfaces opportunities in the form of full product specs that you or your agents can approve and ship - Tracks the experiments and outcomes of what you've built so you can start the loop over again Your product learns what works and gets smarter every cycle:

Today we're introducing Wave. A proactive product agent that helps teams build self-improving products. Every product team runs the same loop. Build, ship, use, learn. AI has made building and shipping extraordinarily fast. Understanding usage and learning still happen by hand. Wave runs the whole loop: - Analyzes your Amplitude data for signals across analytics, feedback, session replays, error logs, agent traces, and experiment results - Surfaces opportunities in the form of full product specs that you or your agents can approve and ship - Tracks the experiments and outcomes of what you've built so you can start the loop over again Your product learns what works and gets smarter every cycle:

Spenser Skates

107,303 views • 1 month ago

Did you know that you can add filters, emojis, description to the images? You can also put a content warning on the Tweets. 

Did you know that you can add filters, emojis, description to the images? You can also put a content warning on the Tweets. 

DogeDesigner

5,053,751 views • 3 years ago

My submission to the Cerebras Google Gemma hackathon, Carbide. Carbide is an ontology builder. Based on a research prompt Carbide uses Cerebras Gemma4 agents to build an ontology. The agents connects individual nodes of information based on the relationship that the agents infer. The agents also assign a confidence metric for how accurate they think the relationship is. You can see each node in a relationship table of the information -> relationship -> target -> and the confidence the relationship is true. The inspector shows the node's connected edges and as an expand button to grow the ontology in the direction of that information. You can scroll through each concept and load them in the inspector. You can search the entire graph based on the kind of relationships generated, or key words. A visual shows how each nodes connects to another one and by what relationship, and changes with new nodes or search filters. Sorry for the audio quality. $CBRS $GOOG

My submission to the Cerebras Google Gemma hackathon, Carbide. Carbide is an ontology builder. Based on a research prompt Carbide uses Cerebras Gemma4 agents to build an ontology. The agents connects individual nodes of information based on the relationship that the agents infer. The agents also assign a confidence metric for how accurate they think the relationship is. You can see each node in a relationship table of the information -> relationship -> target -> and the confidence the relationship is true. The inspector shows the node's connected edges and as an expand button to grow the ontology in the direction of that information. You can scroll through each concept and load them in the inspector. You can search the entire graph based on the kind of relationships generated, or key words. A visual shows how each nodes connects to another one and by what relationship, and changes with new nodes or search filters. Sorry for the audio quality. $CBRS $GOOG

QuantHood

16,376 views • 15 days ago

GLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly. We put together 10 rules to help you get the most out of it: - Front-load instructions (it has a strong recency bias) - Use firm language: "must" and "strictly" > soft suggestions - Break complex tasks into smaller steps - Disable reasoning for simple tasks, enable it for hard ones - Use critic agents for code review, QA, and validation - Pair it with a frontier model for the hardest 10% of workloads - and more… GLM 4.7 hits 96% on Tau² Bench and 86% on GPQA Diamond. At 1,500 tokens/sec on Cerebras, it's 20x faster than closed-source alternatives on GPUs.

GLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly. We put together 10 rules to help you get the most out of it: - Front-load instructions (it has a strong recency bias) - Use firm language: "must" and "strictly" > soft suggestions - Break complex tasks into smaller steps - Disable reasoning for simple tasks, enable it for hard ones - Use critic agents for code review, QA, and validation - Pair it with a frontier model for the hardest 10% of workloads - and more… GLM 4.7 hits 96% on Tau² Bench and 86% on GPQA Diamond. At 1,500 tokens/sec on Cerebras, it's 20x faster than closed-source alternatives on GPUs.

Cerebras

633,658 views • 5 months ago

“If you have a problem. If no one else can help. And if you can find them, maybe you can hire The A-Team.” THE A-TEAM premiered on this day in 1983. What a time to grow up!

“If you have a problem. If no one else can help. And if you can find them, maybe you can hire The A-Team.” THE A-TEAM premiered on this day in 1983. What a time to grow up!

Jack Carr

81,928 views • 1 year ago

The amount of success you can have if your QB runs like this is off the charts

The amount of success you can have if your QB runs like this is off the charts

Winged Offense Network

30,384 views • 1 year ago

#DunkFSRICHwithDUNK #JoongFSLUCKYwithJOONG : i’m writing a JoongDunk fanfic. in the story only one of you can survivein the end. if you had to chooses would you want yourself to survive or the other person? why? 🌞i want to die … i want to be someone die … it must be drama … if someone survives someone dies… if that’s how it … i will be someone die : why? 🌞cause i don’t want him to die ….. 🌻: it’s okay we can survive both because one survive the other one can help each other if you can each other —— : if you could change one thing about the ending of this story what would you want to change the most? 🌞: die too ( die 2 both die) 🌻: both happy ending

#DunkFSRICHwithDUNK #JoongFSLUCKYwithJOONG : i’m writing a JoongDunk fanfic. in the story only one of you can survivein the end. if you had to chooses would you want yourself to survive or the other person? why? 🌞i want to die … i want to be someone die … it must be drama … if someone survives someone dies… if that’s how it … i will be someone die : why? 🌞cause i don’t want him to die ….. 🌻: it’s okay we can survive both because one survive the other one can help each other if you can each other —— : if you could change one thing about the ending of this story what would you want to change the most? 🌞: die too ( die 2 both die) 🌻: both happy ending

🇻🇳Jaidee’s aunt Bamnie🐣

24,757 views • 1 day ago