Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

65,515 subscribers

142,167 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche 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

282,043 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 2 Monaten

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 🦊

4,481,062 Aufrufe • vor 7 Monaten

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

32,811 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 2 Monaten

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 🏏

88,442 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

Dylan Patel of SemiAnalysis says speed is the moat in AI inference, and getting there runs through new compute (Groq/Cerebras), KV-cache offload, and networking optimization (Aria). "Most of the infrastructure is pretty optimized for high throughput, I would say, but more and more people want to pay for speed. It turns out agents are very sequential, task-oriented, and models running in sequential tasks." "Trying something, verifying it, checking if it's right, and you do that in a loop. It ends up being very slow." "And speed is the moat. The faster you go, speed is the moat." "So a lot of the workloads and high-end use cases that people are developing now are all focused on high interactivity, and the infrastructure there is quite different." "So let's break that down into a few components." "One is you can do new compute: you can do Groq or Cerebras-style compute, which is very much focused on high interactivity." "But even with existing GPUs you can do a few things. One, if you're focused heavily on time to first token, you might offload KV cache to storage, keep it cached, move it back into the compute whenever you need it, much faster than recomputing." "And the third thing you can do is you have to optimize the network."

Dylan Patel of SemiAnalysis says speed is the moat in AI inference, and getting there runs through new compute (Groq/Cerebras), KV-cache offload, and networking optimization (Aria). "Most of the infrastructure is pretty optimized for high throughput, I would say, but more and more people want to pay for speed. It turns out agents are very sequential, task-oriented, and models running in sequential tasks." "Trying something, verifying it, checking if it's right, and you do that in a loop. It ends up being very slow." "And speed is the moat. The faster you go, speed is the moat." "So a lot of the workloads and high-end use cases that people are developing now are all focused on high interactivity, and the infrastructure there is quite different." "So let's break that down into a few components." "One is you can do new compute: you can do Groq or Cerebras-style compute, which is very much focused on high interactivity." "But even with existing GPUs you can do a few things. One, if you're focused heavily on time to first token, you might offload KV cache to storage, keep it cached, move it back into the compute whenever you need it, much faster than recomputing." "And the third thing you can do is you have to optimize the network."

Fireside Alpha

282,905 Aufrufe • vor 1 Monat

$"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

12,066 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 11 Monaten

Andrew Feldman on AI model selection: Shop like you're at Costco. You don't need to buy everything. You don't need the biggest thing on the shelf. And somehow you definitely don't need the 400 oz tub of mayo. Same with AI. Not every problem needs the biggest, most expensive model.

Andrew Feldman on AI model selection: Shop like you're at Costco. You don't need to buy everything. You don't need the biggest thing on the shelf. And somehow you definitely don't need the 400 oz tub of mayo. Same with AI. Not every problem needs the biggest, most expensive model.

Cerebras

35,342 Aufrufe • vor 2 Monaten

Can AI really replace SaaS? We asked Codex Spark to build a simple Salesforce clone. It generated a build plan, then wrote all the code in 29 seconds. And it works! Add contacts, live search, full pipeline dashboard – all unit tests passed. The same task on full Codex took ~5× longer. For rapid prototyping and self-contained work, nothing beats Spark. ✨

Can AI really replace SaaS? We asked Codex Spark to build a simple Salesforce clone. It generated a build plan, then wrote all the code in 29 seconds. And it works! Add contacts, live search, full pipeline dashboard – all unit tests passed. The same task on full Codex took ~5× longer. For rapid prototyping and self-contained work, nothing beats Spark. ✨

Cerebras

16,831 Aufrufe • vor 4 Monaten

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

114,966 Aufrufe • vor 2 Monaten

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 Aufrufe • vor 2 Monaten

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

5,053,785 Aufrufe • vor 3 Jahren

“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

81,937 Aufrufe • vor 1 Jahr