-=HACKMANS=-

New video of my game @talesofsyn showing GPT3 based NPC chat interaction with pre-prompting and custom voice synth by @elevenlabs and #vfxgraph weather system + background shaders made with AI generated wet maps #madewithunity #gamedev #indiedev #indiegame #unity3d @GeppettoAi

Dialing in real time V2V in Sentinel. No Python or venvs, just an installer. Runs locally on any 16GB+ NVIDIA GPU. Sign up for early access: ood-labs.com/sentinel/waitl…

Autechre Guitar is out today! shaneparish.bandcamp.com/album/autechre… This has been a truly magical time. From the making of this record, to seeing how many people it has connected with, and now as it leaves the nest. I’ve never experienced anything like it. 🙏

FLUX.2 is here - our most capable image generation & editing model to date. Multi-reference. 4MP. Production-ready. Open weights. Into the new.

Ok, folks. Here's Voxel Duke 3D Version 1.0! I'm gonna take a break from the internet for a bit. Have fun, I hope everything works. moddb.com/mods/voxel-duk… via @moddb

@dadabots Really enjoyed this, thanks for sharing all the fascinating info about the model and training

We gon live 👇

@janekm Huh? That is pretty odd, I’ve not encountered any blockage yet

Literally the first prompt I try with Sonnet4.5... Nah, not re-subscribing to this clown show of a company. And they have the gall to brag about improved alignment 🤣

@TomLikesRobots @VraserX If everyone is lifted from poverty we would spend less time focussed on surviving and more time engaging (in entertainment, consumerism, education, community)

@VraserX Follow the money and who controls AI. 1. Labor, so wealth and power can be consolidated. 2. Aging, so their wealth and power can be maintained. 3. Poverty? Why would those in control want to end poverty? Who would they control?

What happens first: Vote and reply why.

@TomLikesRobots Nano banana ones make more sense as a continuation of time I think

A nano banana vs SeeDream 4 showdown. Both are obviously superb models. Prompt used: "This is a still from a movie. Please provide the frame from 10 seconds after this." Which do you prefer here?

@TomLikesRobots @fablesimulation Excited to have you on the team, and we’re very fortunate to receive your creative vision and skills!

Some personal news. I'm very pleased to share that I've joined the Emmy-winning team at @fablesimulation , known for their work on Showrunner. From May 2023 until July 2025, I had the privilege of working with the talented team at Metaphysic AI, where I gained invaluable experience and learned a huge amount. Together, we worked on some truly innovative AI visual effects for major Hollywood films. At Fable, I’m stepping into a new role as a filmmaker, creating and directing stories that will become the starting point for interactive experiences. I will also be contributing my skills and experience to the newly announced Magnificent Ambersons reconstruction project - an exciting initiative where we are using the latest AI technology to restore Orson Welles’s unfinished masterpiece.

@zellah 😂 I don’t think it’s considered cool, but is part of a wider conversation about skater etiquette and inclusivity

@_hackmans_ Wait, if mall grabbing has become the next cool thing, I give up :D

Old guys rant... I feel like skateboarding’s got an image problem these days. It’s not really Skate(4)’s fault that it is what it is. We just keep looking back at the 90s and 2000s, when skating had a clear identity-rebellious kids, doing wild shit, filming parts, slamming on concrete, showing off their style. Back then it was obvious why skating was cool. Now in 2025, it’s way harder to define. That gritty street vibe isn’t there like it used to be. Filming doesn’t hit the same either, before you needed a legit video part to get seen, now it’s all iPhones, TikToks, Youtubers and instant clips. Exposure is just handed to you. Skating used to be about street spots like MACBA, Love Park, local spots with your crew. Now it it's kids at skateparks with helmets, parents dropping them off, filming them, and handing them a banana when they get hungry. It’s just… a different world. Back in the day we had skate crews bombing around, painting graffiti, claiming spots. Now it’s organizations with smiling kids on their websites and skateboarding instructors on payroll. And I don’t know, I get stuck on this when thinking about the skate game I'm making. Do I make it feel like the old days, like Skate 1–2 or Session tried to? Like what skating is to me. Or do I try to capture whatever skating even is now? That’s why Skate 4 is what it is. The devs don’t really know what skating represents in 2025. And honestly, neither do a lot of skaters and the industry, especially us older heads who can’t let go of the 90s vibe. Or maybe that’s just me, since I’m not really in the skate scene anymore. Thoughts?

@zellah Even small things like “Mall Grabbing” come up a lot in skateboarding discussions within the social communities

Very interesting problem about representation. As someone who returned to skating as an older person after a ~15 year gap, I agree that the entire scene feels very different, but there is still negative stigma around things like wearing safety gear. Maybe try involve younger skaters in the process of crafting the identity of your game. You might potentially help to steer it in a new direction, but that also brings risks since many skate games have established tropes.

@CoffeeVectors The common pitfall I see is overestimating the tech, thinking it is a one click money saving solution rather than something that is quite immature and involves pretty complex workflows to be anything close to manageable - to meet the requirements needed for professional work.

Coming from trad video it’s interesting being in team AI pipelines as someone who knows the tools well. I wonder how challenging being a trad director/editor might be coming into the space when you don’t know the tech, the problems your team deals with, or what limitations to expect. While there’s always talk about AI disrupting Hollywood and advertising, a lot of projects will still require team coordination and knowing how to distribute/scale effort. And if your org isn’t AI first (or even AI second), you’ll eventually have to foster communication between AI artists & trads. And it can be tough for everyone if there aren’t enough “bilingual” people available. These crossover generalists will be incredibly valuable to teams in AI transition. Most videographers/directors I know aren’t learning AI, but some are and I think they’re going to survive/dominate in the coming market because they can thrive in multiple environments, not to mention help smooth things out in mixed teams.

@runwayml What is the cost, and for unlimited tier users?

Select third party models will now be available directly within Chat Mode, allowing you to choose between a more robust set of pipelines to better accommodate your specific needs. Among our first integrations is Veo 3 Image to Video and Text to Video with audio generation support. Simply choose "All" from the model selector menu, and Chat Mode will choose the best model for your specific task. (2/5)

Today we're releasing a number of updates and new features to bring even more control, flexibility and speed to your creative workflows within Runway. Learn more below. (1/5)

Real-time visual effects, running 100% locally in your browser! 🚀 I created a demo where you can just drop your video and watch it analyze feature points and optical flow for some cool visual effects! Have fun 😊 Demo: whenistheweekend.com/vfx.html #ComputerVision #VFX

@CoffeeVectors Main benefit of wan models is being able to control the camera through other forms of guidance. Uni3C, Fun Control, VACE all allow it to do far more motions that you can prompt for, very spatially consistent

More Wan 2.2 tests on wavespeed.ai. Here I wanted to compare it directly to Veo 3 and also see how tight into the eye I could get with complex zooms. Again I’m really surprised by what Wan 2.2 can do. The prompts are the same across models, so Wan seems to be able to do more with the text, at least with camera moves and optics. 🧵

@TomLikesRobots Thanks, it's definitely interesting that Pika have the social focused content, helps to separate them from the other video platforms

@_hackmans_ I think it's the YouTube style - this is the direct output. I've tested most of the models and it's pretty cool. It listens when you tell it not to overract - head to stay still etc.

Ooh. I'm very impressed by Pika's new lipsync model. I've had a chance to check it out - very fast and listens to prompts. Check it out. Voice here from ElevenLabs.

@TomLikesRobots Yeah it's obviously far from SOTA, but it's a pretty wild experience scrolling through as images generate and then turning them into vids in seconds. Very fast for ideation.

Cool. Imagine Video has now arrived on Grok. It has a bit of catching up to do in terms of quality, but the inference speed is very impressive.