Artificial Intelligence

What AI do you use?

The choice of AI has to be an individual one. Everyone uses AI to a different degree and for different reasons. And there doesn’t have to be a single choice, often switching between AI models makes sense.

Still, at the end of the day many of these require subscriptions and often it’s necessary to make a choice on which AI to spend the most time and money working with (wait, you don’t use AI enough to subscribe to anything? Fair enough, but this is like the early days of the internet: you may not have had an ISP for a long while… but I bet you do now…)

My Choice

After extensive hands-on experience with both GPT-5, Gemini, Claude (and just about every other major AI available), Claude is now my go-to model.

That’s not to say I only use Claude. For instance I still rely on meta.ai for most of my mobile AI usage: answering questions and modal context (image understanding via cameras) queries. And of course… Nano Banana. Yeah. Ook ook.

Mobile AI with Meta.ai

While Claude anchors my desktop and agentic workflows, for mobile and on-the-go tasks, meta.ai is an indispensable companion in my daily tech routine. Integrated natively into my phone and wearables—especially the Meta Ray-Ban smart glasses—meta.ai brings hands-free, voice-based assistance wherever I go. And it helps that it’s free, and due to the nature of my work I know Llama very well: it’s an excellent all-around useful model you can consider reliable.

How meta.ai enhances my mobile experience:

Instant Queries on the Move: Whether I’m out, I can simply ask meta.ai quick questions (directions, news, reminders) with my voice. On Meta Ray-Bans, a subtle tap activates the assistant, letting me stay productive without reaching for my phone. My smartwatch (which by the way is not an apple watch) lets me ask questions by voice with a touch of one of it’s buttons.

Awareness: Meta.ai adapts its responses based on my location, schedule, and device activity.

Wearable-Specific Experiences: On Ray-Bans, rich audio prompts and gesture support allow for truly convenient, head-up computing. And the RayBan display glasses are pretty amazing. I don’t have them, because they are selling out faster than we can make them! We are encouraged to wait and let non-employees get theirs first. But it’s only a matter of time, and in the meantime my gen-1 Meta Ray Bans are still pretty sweet (and heavily discounted this coming Black Friday I bet!)

Mobile App Deep Integration: The assistant can seamlessly connect with mobile apps (maps, social media, music), making multitasking smooth and contextually relevant.

Claude at Work and Home

Claude’s versatility truly shines in both my professional and personal environments. At work, well Meta and especially Reality Labs is a bit of a futurist playground when it comes to AI and we make a point of using everything to the best extent we can. At home, Claude takes on different roles through tools like Claude Desktop and Windsurf, a VSCode variant powered by Sonnet 4.5, aiding me in personal projects and experimentation. This seamless transition between contexts and deep customization makes Claude an indispensable part of my daily routine.

Instant Access with Claude Desktop

*I don’t actually spend my time looking at financial graphs …but you get the idea. AI at the touch of a button is far more empowering than you might think.*

A standout feature is Claude Desktop’s “summon prompt” (Ctrl+Alt+Space), providing instant interaction, no matter the task at hand. This quick accessibility is something I particularly value and wish was available in my professional setting. If you take a little time to get used to it, you will soon find that there really isn’t a point in google searches any more. Bring the information you actually want to you straight off, with analysis and organized the way you prefer… not just links of dubious value to sites that may not even let you in.

Agency and Customization

Claude’s agentic capabilities offer robust tools for customization, making personalization both simple and effective. Users can seamlessly add detailed personal information and instructions, creating unique workspace hierarchies. This flexibility allows Claude to adapt instructions based on specific workspaces or folders while maintaining context awareness. As a result, Claude understands my preferences and work style, effortlessly switching communication styles as needed.

Advanced Agentic Tools: Skills and MCP Integration

With Claude’s advanced agentic tools, the possibilities for streamlining tasks are endless. Claude’s “skills” allow for combining pre-prompt instructions with executable scripts, making automation a breeze. It even includes a skill for creating new skills—describe what you want, and Claude generates it. The MCP tool integration further elevates its capabilities, with a vetted catalog of automation scripts and extensions that enhance productivity and simplify setup

I have to admit that this pretty much captures my mental image of an “AI Agent.” I blame it on being exposed to Tron at an early age.

Power User Tricks in Claude Code

Claude Code, the CLI component, opens up a world of possibilities for advanced workflows. It allows for multi-agent orchestration, enabling the simultaneous operation of multiple Claude instances or other AIs like GPT. This feature is particularly valuable for large tasks that require efficient context management. And overall Claude Code is, simply put, a development powerhouse. However, users should be mindful of data usage, as it can be demanding.

Windsurf : The Hidden Gem

That said, if you want a VScode IDE experience with deep agency out of the box and seamless flow, you can’t get better than windsurf and it’s AI wrapper Cursor. It’s a joy to use and you have all the benefits of Claude Sonnet and Opus without having to worry so much about context lengths or setting up MCP tools straight out the gate. Ok, now wait you say: Google bought Windsurf, it’s now “Antigravity” right? Yeah. And they have some great ideas and improvements. BUT…. as of this writing, Antigravity is, from my experience, a hot mess. I look forward to what it CAN be… but right now, it isn’t that. I like my codebase intact, thanks. I’ll be sticking with Windsurf, and while I love Gemini for deep research and image operations I don’t trust it with agentic coding just yet.

Best-in-Class Reasoning and Planning

Claude’s prowess in complex reasoning, planning, and deep research sets it apart. When tackling intricate or multi-step projects, it consistently outperforms its counterparts, making it the clear winner for those challenges. I’m not talking about just benchmarks, but the entire holistic experience. The customization, styles, skills and planning mode compliments the thinking and reasoning of the model as well as its responsiveness and speed. Other models have their advantages, for instance Gemini’s multimodal capabilities raise the bar, but when it comes to the complete package Claude is, from my perspective, the most capable and versatile AI for my personal use.

Will it remain so? It’s hard to say, Anthropic has some serious momentum and I admire them but I also get to see some of what’s cooking for the future, and all I can say is wow. If pressed I would predict that like most broadly applicable new technologies the AI landscape will settle into a complex ecosystem of options and taxonomies as opposed to a single monolithic entity dominating a myriad of use cases.

Embracing Openness

To my way of thinking, this is for the best. While Apple has certainly demonstrated that walled garden paradigms and tight control can lead to huge profits it is also now demonstrating the downside of being a monolithic entity: slow stagnation of innovation due to the need to maintain tight control and ever increasing energy spent stifling competition. From my work at Reality Labs I have a fresh appreciation of the value of competitive ecosystems and especially the potential of cooperative effort to improve through open source, shared standards, and academic discourse. Sure there is a degree of competition between my employer and Anthropic. But there is far more overlap of interests. Claude Sonnet and Opus are excellent models worth embracing, just as we hope people will embrace Llama Maverick or Segment Anything. Friends can compete to the benefit of all. Bring on the complex AI landscape and evolve together. Those who close themselves -and their user base- off from the wild world of evolving AI are doomed in the long term.

Caveats

Despite its many strengths, Claude does have some drawbacks. Its context window is large but varies according to plan. And Claude is pretty verbose when it’s thinking… meaning Claude can quickly run through available context, particularly with the desktop app. Desktop users doing more complex tasks should anticipate the need to frequently compress or restart conversations. Additionally, token consumption and cost can add up, especially if Sonnet 4.5 or Opus is not reserved for the most demanding tasks. Yes, customizations allow for mitigation of many issues, but also require real effort to get things to where they work best for you. The setup process also demands time, with a minimum of four hours needed to overcome verbose and overly proactive default settings.

Recommendations

For standard workflows involving organization, research, document writing, or minor coding, ChatGPT remains a robust choice. However, for power users who require deep customization, agentic automation, advanced research, and scalable application development, Claude proves, for me, to be superior.

To sum it up, Claude is a highly customizable, agentic AI that is most suitable for those prepared to invest time and resources into their AI solutions. For serious, all-in AI workflows, I believe Claude is positioned as the top choice for 2026 and likely beyond. I’m quite excited about the next developments cooking at Meta too, and look forward to getting to use them at home in a released state, particularly in the areas of mobile AI and content creation. This is an amazing future we find ourselves in. Embrace it and as always have fun.

Empowering Creativity: Emerging AI Tools for Game Developers and Technical Artists

AI, Creative Work, Tech Art / By andy

When it comes to game development, technical artists are always on the lookout for tools that can make their lives easier and their work more efficient.

Enter AI.

From automating repetitive tasks to enhancing asset creation, AI tools can help streamline workflows and free up time for creativity. Technical artists can already use AI tools in a number of helpful ways:

Asset generation, including 3d models, animations, rigs, textures, audio and skydomes.
Creative inspiration and conceptualization – this can go beyond simple image generation and get more specific with tools like comfyUI, to allow for the creation of specific art styles and applications such as character model sheets, sprite atlases, equirectangular skydomes, and so on.
Code exploration and generation. It’s hardly a secret at this point that software development has changed dramatically with LLM tools like Copilot, Windsurf, Codeium, Bolt and Mutable.
AI customization and automation is getting very interesting, with resources like huggingface, tensorflow, zapier and more.
AI is also a game changer when it comes to communicating ideas and collaborating. I have had some great experiences with Descript and Ryter being particularly notable.
And last but perhaps most importantly, AI is a game changer when it comes to research and learning. I regularly use Meta.ai to explore technical topics and other go-to tools are Consensus and Perplexity. If you are using google to try to learn about something or research a topic, you are missing out on the power of AI in helping you obtain the information you need to access and understand.

The number and nature of the AI tools available are rapidly changing. They’re not just about saving time; they’re also about pushing the boundaries of what’s possible in technical art. Currently we are in a period where we are confronted with many different tools but have yet to bring them together into cohesive workflows. As such, I’m just going to touch base on a few areas I’m keeping an eye on. Think of this article as a starting point, I’ll add more to this later and hopefully end up with some tangible assets and workflows worth considering.

Unity ML-Agents

Unity ML-Agents are a powerful toolkit that allow developers to create intelligent agents within their games. By leveraging machine learning techniques, developers can simulate complex behaviors and decision-making processes.

Intelligent Agent Creation: Unity ML-Agents enables developers to train agents using reinforcement learning, allowing them to learn from their environment and improve their performance over time. This can lead to more realistic and responsive non-player characters (NPCs).
Machine Learning Applications: Examples include creating NPCs that adapt to player behavior, developing dynamic difficulty adjustments, and simulating realistic character interactions.
Gameplay Experience Enhancement: By integrating intelligent agents, developers can create more immersive and engaging gameplay experiences that respond to players in real-time, ultimately leading to higher player satisfaction. For more information, visit the Unity ML-Agents documentation.

NVIDIA GameWorks

NVIDIA GameWorks provides a suite of tools and technologies designed to enhance the graphical fidelity and performance of games.

Key Features: GameWorks offers tools such as PhysX for realistic physics simulations, NVIDIA HairWorks for lifelike hair rendering, and NVIDIA Flow for fluid simulations.
AI-Driven Solutions: One of the standout features is Deep Learning Super Sampling (DLSS), which utilizes AI to upscale lower-resolution images in real-time, providing stunning visuals without compromising performance. For more details, check out NVIDIA GameWorks.
Successful Implementations: Popular titles like “Cyberpunk 2077” and “Control” have successfully implemented NVIDIA GameWorks, showcasing the dramatic improvements in graphics and performance that these tools can achieve.

Houdini

Houdini is a 3D animation and visual effects software known for its procedural capabilities and integration of AI features, making it invaluable for technical artists.

AI-Integrated Features: Houdini offers tools that leverage AI for tasks such as automating texture generation, enhancing simulations, and optimizing workflows. This can greatly reduce the time artists spend on repetitive tasks. Of particular note are the
Procedural Generation and Simulation: The procedural nature of Houdini allows artists to create complex environments and effects efficiently. This streamlining can significantly reduce the time spent on manual adjustments.

Of particular note, the Houdini node collection known as MLOPS are hugely useful to technical artists. Houdini version 20 also added their first official machine learning node, the ONYX inference SOP.

For further details, visit the Houdini documentation.

Meta Developer AI Tools

Meta developer AI tools, such as Llama, represent a significant advancement in how developers create and manage their workflows. These tools utilize large language models (LLMs) to automate and enhance various aspects of game development. Meta has embraced an open source and collaborative stance with developers which is worth watching closely as fertile ground for useful tools, SDKs and APIs.

Llama Overview: Developed by Meta, Llama is a family of state-of-the-art open-source LLMs that can assist developers in a myriad of tasks, from coding to documentation.
Applications in Game Development:
- Code Generation: Llama can generate code snippets or entire functions based on natural language prompts, facilitating rapid prototyping and reducing the time spent on boilerplate code.
- Debugging Assistance: Developers can input error messages or code snippets, and Llama can suggest potential fixes or improvements, streamlining the debugging process.
- Documentation Creation: By summarizing code and generating comments, Llama aids in creating and maintaining documentation, which is crucial for team collaboration.
Integration: Llama can be integrated into various IDEs and development environments, enhancing the overall workflow without disrupting existing processes. For example, integrating Llama with Unity or Unreal Engine can significantly improve productivity by allowing developers to focus on creative tasks rather than repetitive coding.

For more details, you can explore the Meta Llama documentation.

Additional AI Tools

In addition to the previously discussed tools, several other AI solutions can enhance the game development process:

Windsurf: This tool assists in optimizing and automating the development of game assets, improving workflow efficiency. Learn more.
ComfyUI: An intuitive interface for managing UI elements in games, allowing for rapid prototyping and adjustments.
Rytr: This AI writing assistant can help developers and writers generate engaging narratives and dialogue for their games. Visit Rytr.
Descript: A powerful tool for audio editing that utilizes AI to streamline the process of creating and editing voiceovers and sound effects. Explore Descript.
Zapier: Automation software that can connect various applications and tools used in game development, helping to manage workflows and tasks more efficiently. Find out more.