Loading video...

Video Failed to Load

Go Home

We released physics-intern: a simple harness for science problems! It gets models like Gemini 3.1 Pro to go from 17.7 -> 31.4, thus beating GPT 5.5 Pro. The physics-intern harness can wrap any model and via dedicated subagent boost the performance of the vanilla reasoning models. While I think...

lvwerra's profile picture

Leandro von Werra

12,245 subscribers

97,432 views • 3 months ago •via X (Twitter)

Health & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GPT-5.5 by Reasoning Effort: I've asked it in Codex to create a physics-based visualisation of RL cycles for different sized models (70b, 1t, 10t), to demonstrate how the amount of RL you can do differs by model size. My assessment of each: - Low: weird slop - Medium: kinda cooked - High: sort of tried but ultimately incoherent - Extra High: elite - really nice idea and well executed Obviously this is just one shot, but worth trying different reasoning levels for the new models, medium seems to be pretty good for GPT-5.5 and it was really bad for many previous GPT models.
0:15

GPT-5.5 by Reasoning Effort: I've asked it in Codex to create a physics-based visualisation of RL cycles for different sized models (70b, 1t, 10t), to demonstrate how the amount of RL you can do differs by model size. My assessment of each: - Low: weird slop - Medium: kinda cooked - High: sort of tried but ultimately incoherent - Extra High: elite - really nice idea and well executed Obviously this is just one shot, but worth trying different reasoning levels for the new models, medium seems to be pretty good for GPT-5.5 and it was really bad for many previous GPT models.

Peter Gostev (SF: 22-26 June)

209,258 views • 4 months ago

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.
0:14

Big win for open-source LLMs! DeepSeek V4 Pro holds the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.

Avi Chawla

44,124 views • 2 months ago

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🪨 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🪨:
0:11

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🪨 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🪨:

Dan Shipper 📧

354,559 views • 3 months ago

Qwen 3.8 27B feels SO GOOOOOD! Here’s the thing, it’s thinking a lot, but for the first time it may be that the verbose thinking is less of a mistake than a lot of other local models. It’s basically doing a full build, like a model would in a harness, but entirely within its reasoning trajectory. So the final result will be as close as possible to a final output. There’s much less second guessing itself in reasoning than with Qwen 3.6. It’s very confidently peacing this together so it can have the full picture for the output. This might be the play for smaller models. If the completeness of thought can overcome the increase in wall time, I’m pumped, we can always make it run faster! I think this is going to be really exceptional, I will post the output soon 😎
0:18

Qwen 3.8 27B feels SO GOOOOOD! Here’s the thing, it’s thinking a lot, but for the first time it may be that the verbose thinking is less of a mistake than a lot of other local models. It’s basically doing a full build, like a model would in a harness, but entirely within its reasoning trajectory. So the final result will be as close as possible to a final output. There’s much less second guessing itself in reasoning than with Qwen 3.6. It’s very confidently peacing this together so it can have the full picture for the output. This might be the play for smaller models. If the completeness of thought can overcome the increase in wall time, I’m pumped, we can always make it run faster! I think this is going to be really exceptional, I will post the output soon 😎

Kyle Hessling

65,585 views • 25 days ago

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.
0:18

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

244,990 views • 2 months ago

Okay... this is actually insane. OpenCodex feels like the open-source breakthrough I've been waiting for. The best part : You can plug multiple providers into the same OpenAI Codex harness and switch between models depending on the task. Running low on tokens? No problem. Use another provider. OpenRouter free model today? Plug it in. This completely changes how I think about AI coding workflows. And yes... it even works on mobile. OpenCodex might be one of the most useful open-source AI projects I've seen this year. OpenAI built an incredible harness. The open-source community just made it universal.
0:10

Okay... this is actually insane. OpenCodex feels like the open-source breakthrough I've been waiting for. The best part : You can plug multiple providers into the same OpenAI Codex harness and switch between models depending on the task. Running low on tokens? No problem. Use another provider. OpenRouter free model today? Plug it in. This completely changes how I think about AI coding workflows. And yes... it even works on mobile. OpenCodex might be one of the most useful open-source AI projects I've seen this year. OpenAI built an incredible harness. The open-source community just made it universal.

CHOI

42,894 views • 1 month ago

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 views • 20 days ago

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.
0:14

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

864,665 views • 1 year ago

GOOGLE 🔥: An upcoming Gemini Omni video model from Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀
0:10

GOOGLE 🔥: An upcoming Gemini Omni video model from Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀

🚨 AI News | TestingCatalog

179,938 views • 4 months ago

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.
0:10

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.

CDG

15,388 views • 16 days ago

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.
0:16

Fable 5 totally crushed our new contest, but it cost 6x more than Opus 4.8! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: — A train derailing off a broken bridge into the water — Two cars jumping off ramps and colliding mid-air over a canyon — A monster truck crushing a row of parked cars Outputs: Fable 5: 62,158 tokens, $3.12 GPT 5.5: 37,753 tokens, $1.14 Opus 4.8: 22,280 tokens, $0.56 GLM 5.2: 36,246 tokens, $0.08 Fable 5 did all three scenes at A+. The crashes looked real, things fell and broke the right way, and nothing went through the ground or floated. GPT 5.5 was the closest to Fable. In the Bigfoot show, we think GPT was even a little better. GLM 5.2 did not win any scene, but it was the cheapest by far. Fable is the best pick for quality, but you pay more for it.

atomic.chat

2,839,437 views • 2 months ago

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.
0:19

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

Brian Roemmele

57,454 views • 9 months ago

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.
0:15

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

57,554 views • 1 year ago

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:
0:10

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 views • 1 month ago

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.
0:15

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

Peter Gostev

105,642 views • 4 months ago

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.
0:15

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.

elvis

37,757 views • 1 month ago

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.
0:19

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.

elvis

47,678 views • 4 months ago

✨ I can now generate 3d assets for my drone sim at directly from Cursor (sponsor of #vibejam) I need buildings that you'd see in a war torn city, like warehouses in ruins, broken down abandoned houses, bombed out bridges etc. Nano Banana Pro or 2 can generate them really well and then you can put them in an image-to-3d model and you get a GLB or FBX That one you can then import into your Three.js game, the models might be big though, in my case like 16MB, so I ask it to compress it and make it more low poly so it loads fast ThreeJS then loads the individual GLBs on page load and puts them in my drone sim somewhere randomly, I think I should remove some of the grass and match the sandy color of the ruins though to make it fit in more
0:20

✨ I can now generate 3d assets for my drone sim at directly from Cursor (sponsor of #vibejam) I need buildings that you'd see in a war torn city, like warehouses in ruins, broken down abandoned houses, bombed out bridges etc. Nano Banana Pro or 2 can generate them really well and then you can put them in an image-to-3d model and you get a GLB or FBX That one you can then import into your Three.js game, the models might be big though, in my case like 16MB, so I ask it to compress it and make it more low poly so it loads fast ThreeJS then loads the individual GLBs on page load and puts them in my drone sim somewhere randomly, I think I should remove some of the grass and match the sandy color of the ruins though to make it fit in more

@levelsio

134,777 views • 5 months ago

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?
0:15

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

Lumina

72,213 views • 1 month ago