Cheese and coffee lover, Start-upper and follower of all things tech and politics. I have a secret crush on Tesla and I'm known to eat organic and enjoy whisky.
So I decided it was about time I jumped on the "Let's get the AI to explain something" bandwagon, and here we are! Claude spent 2.5 hours on a single prompt to create this, explaining in plain terms how a locally installed AI model without internet, still works and fits. on a PC.
@elonmusk It’s really great, but why spend so much time and effort on the video and narrative, and then so little effort on the voice and sound quality? Suno for example easily enables crisp human voices and music, instead of this.
This is good advice for now to think about working with models like Opus 5.5.
But it is often best to build in checkpoints where the model reports back to you with interim ideas or prototypes so you can guide & give feedback on the process, rather than one-shotting on your goal.
@RobertJBye I still cannot work in voice mode using my native language, Danish. This is surprising as GPT Sol/Astra works perfectly in Danish using voice mode.
I did however notice significant improvements in transcribing.
@RobertJBye When I’m out of tokens, using credits, a warning covers the bottom 1/4 th of my screen and it cannot be removed. Using iPhone 17e. This leaves me with significantly less screen space while using the app. Learned to live with it. Not happy with it.
If you haven’t made sure to turn on two-factor authentication on all accounts, have passwords with family in case you get voice calls asking for money, etc, now would be a good time.
AI gains mean the costs of mass targeting individuals with sophisticated attacks are dropping.
I was reflecting on how many random contingencies went into creating the current accelerating AI moment and had Opus 5.5 put together a video, inspired by old science show Connections, to try and point out how a series of initially unrelated ideas led to the moment we are in now.
Hey Claude, "Pick a problem or mystery that obsesses you and solve it as best you can & make a movie we can share on social media about it"
So it took a crack at the Voynich Manuscript & failed. Then it made this movie, which is pretty interesting to watch and a good explainer.
@MatthewBerman@LLMJunky@bot I would love this! Tried it already with something simple and had it cancel a subscription, but good idea with the school stuff 😁
We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all.
I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand.
Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.
@trq212@ClaudeDevs I just ran into this in the middle of a large project, mid-coding. Restarting Claude will loose all uncommitted work. Will anthropic compensate credits used to end the ongoing task so Claude can be shut down?
@thsottiaux@jxnlco Honest answer: I used to run my game dev pipeline purely on Claude Code. Now GPT-5.6 Sol is an indispensable part of it. Code review on the engine, 2D asset generation (amazing!), optimization passes. Not a religious switch yet, just using what's best for the job. @OpenAI