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.

Kostas Kryptos lists the three reasons your agent’s memory needs to move with you: geopolitics that can cut off a model overnight, regulation like GDPR, and the day a rival model simply gets better. Which of these has hit your stack?

Walrus

369,611 subscribers

12,323 Aufrufe • vor 23 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

"Overnight Haringey Council changed the business model" This comment gets to the nub of a key problem with LTNs. Overnight they can alter patterns of travel which can impact adversely on businesses and communities. We HAVE to find a better way of dealing with our traffic problems

"Overnight Haringey Council changed the business model" This comment gets to the nub of a key problem with LTNs. Overnight they can alter patterns of travel which can impact adversely on businesses and communities. We HAVE to find a better way of dealing with our traffic problems

John Stewart

71,898 Aufrufe • vor 3 Jahren

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

Cerebras

299,029 Aufrufe • vor 10 Monaten

Don't talk directly to a model. You can make your application 10x more flexible by simply adding one intermediate layer between your code and the model. This is the simplest trick you can use to improve the architecture of whatever you are building.

Don't talk directly to a model. You can make your application 10x more flexible by simply adding one intermediate layer between your code and the model. This is the simplest trick you can use to improve the architecture of whatever you are building.

Santiago

88,884 Aufrufe • vor 4 Monaten

Overnight, your Tesla gets better with a OTA update. Tesla Adaptive Headlights in action on a Legacy Tesla Model Y. Now available in the US with Software Update 2025.14.1

Overnight, your Tesla gets better with a OTA update. Tesla Adaptive Headlights in action on a Legacy Tesla Model Y. Now available in the US with Software Update 2025.14.1

Nic Cruz Patane

44,503 Aufrufe • vor 1 Jahr

Engram cofounder Jack Morris just raised $98M to build a new type of AI. He says models don't need to get smarter over time. Instead, they just need to know you better and better over time. Jack describes what he's building: "Our product is a new type of AI. We have a pretty different vision from a lot of the frontier labs, which are working on one model per lab, and trying to make that model smarter every month." "There's another way to think about it, which is that the model doesn't need to get smarter every month. It needs to know you better." "So we're working on a whole different stack, which is a way to train models that train themselves to know your world better and adjust to the things that you say." "So: new ways of training, new ways of running the models."

Engram cofounder Jack Morris just raised $98M to build a new type of AI. He says models don't need to get smarter over time. Instead, they just need to know you better and better over time. Jack describes what he's building: "Our product is a new type of AI. We have a pretty different vision from a lot of the frontier labs, which are working on one model per lab, and trying to make that model smarter every month." "There's another way to think about it, which is that the model doesn't need to get smarter every month. It needs to know you better." "So we're working on a whole different stack, which is a way to train models that train themselves to know your world better and adjust to the things that you say." "So: new ways of training, new ways of running the models."

TBPN

69,716 Aufrufe • vor 2 Monaten

Introducing Vals-Smith: turn your code base into a customized benchmark. Public benchmarks tell you which model is strongest overall, not which model is the best on your code. Vals-Smith turns your merged pull requests into real coding tasks and measures the percentage a model can actually resolve. New models ship every week. Vals-Smith tells you which one to trust with your code.

Introducing Vals-Smith: turn your code base into a customized benchmark. Public benchmarks tell you which model is strongest overall, not which model is the best on your code. Vals-Smith turns your merged pull requests into real coding tasks and measures the percentage a model can actually resolve. New models ship every week. Vals-Smith tells you which one to trust with your code.

Vals AI

45,805 Aufrufe • vor 1 Monat

Our universe is a model with twenty or so carefully fine-tuned parameters that generate all the content inside. Using these parameters and a reduced-scale model you can simulate the history of the cosmos. With the full-scale model, you get to be part of the simulation.

Our universe is a model with twenty or so carefully fine-tuned parameters that generate all the content inside. Using these parameters and a reduced-scale model you can simulate the history of the cosmos. With the full-scale model, you get to be part of the simulation.

Andrew Côté

90,707 Aufrufe • vor 2 Jahren

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,962 Aufrufe • vor 9 Monaten

Mysten Labs (MystenLabs.sui) Co-Founder Kostas (Kostas Kryptos) argues that your AI memory could soon become more valuable than all of your historical online data combined: "Agents are amnesiacs. You start a new session, they don't remember you, and they don't know your preferences." "Everything your agent has learned from you, for your work, your preferences and your own secrets, is arguably more valuable than your data ever was in the past, including your social footprint, emails and search history." "That's why we built memory around four principles: portability, verifiability, encryption and programmability." "For the first time, people can have real cryptographic ownership of their digital identity rather than relying on passwords and fragmented accounts."

Mysten Labs (MystenLabs.sui) Co-Founder Kostas (Kostas Kryptos) argues that your AI memory could soon become more valuable than all of your historical online data combined: "Agents are amnesiacs. You start a new session, they don't remember you, and they don't know your preferences." "Everything your agent has learned from you, for your work, your preferences and your own secrets, is arguably more valuable than your data ever was in the past, including your social footprint, emails and search history." "That's why we built memory around four principles: portability, verifiability, encryption and programmability." "For the first time, people can have real cryptographic ownership of their digital identity rather than relying on passwords and fragmented accounts."

etn.

12,633 Aufrufe • vor 2 Monaten

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 Aufrufe • vor 2 Jahren

while the self-learning poll runs, here is how to actually look at what your agent has picked up: type '/journey' in Hermes Desktop and enjoy a day-by-day timeline of every skill and memory your agent has learned since day one. it also lists each node, so you can see your interconnected skills and memories.

while the self-learning poll runs, here is how to actually look at what your agent has picked up: type '/journey' in Hermes Desktop and enjoy a day-by-day timeline of every skill and memory your agent has learned since day one. it also lists each node, so you can see your interconnected skills and memories.

witcheer

38,662 Aufrufe • vor 1 Monat

The Devin CLI has a brand new model picker! You can now set your model, tune its reasoning effort, and compare costs - all in one view Try it today with `/model`

Devin Desktop

26,039 Aufrufe • vor 2 Tagen

So listen up man, these are your two options you when it comes to feeling inferior to Black men: 1. You can deny it, build resentment, and make up rumours and lies about Black people to make you feel better (which a lot of you do) 2. Or you can do what a good man does when he finds a man that has the things, attributes and characteristics that you want: you model yourself after him. You take all the good from that man, leave the bad and build a better version of you 🫵🏻

So listen up man, these are your two options you when it comes to feeling inferior to Black men: 1. You can deny it, build resentment, and make up rumours and lies about Black people to make you feel better (which a lot of you do) 2. Or you can do what a good man does when he finds a man that has the things, attributes and characteristics that you want: you model yourself after him. You take all the good from that man, leave the bad and build a better version of you 🫵🏻

MIKꙮꙮN X 🇺🇳

13,019 Aufrufe • vor 4 Tagen

✨ Added a 🧍‍♂️Poses gallery to which lets you pick any pose: like sitting, standing, or jumping Your model will follow the pose when taking photos, and you can still prompt it for example "model wearing a suit sitting"

✨ Added a 🧍‍♂️Poses gallery to which lets you pick any pose: like sitting, standing, or jumping Your model will follow the pose when taking photos, and you can still prompt it for example "model wearing a suit sitting"

@levelsio

154,556 Aufrufe • vor 3 Jahren

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 Aufrufe • vor 3 Jahren

Please do well to be with the right person that you can play with as your mate and share every single day as a memory

Please do well to be with the right person that you can play with as your mate and share every single day as a memory

Marcus

3,024,142 Aufrufe • vor 3 Monaten

3d v14 stills are here :) this one is of South America. You can see the importance of both prominence and elevation better in the 3d model. Areas that barely get submerged could still be above water - this is simply a model; a simulated rendition; a recreation.

3d v14 stills are here :) this one is of South America. You can see the importance of both prominence and elevation better in the 3d model. Areas that barely get submerged could still be above water - this is simply a model; a simulated rendition; a recreation.

Junho

16,635 Aufrufe • vor 8 Monaten