opus 5 one-shotted this LiDAR horror game you can only perceive the world through LiDAR signals, the rest is pitch black. honestly impressed, the world emerging point by point is ridiculously satisfying i didn't manage to finish the game tho i'm too scared

opus 5 built a tiny paris inside the browser the eiffel tower, champ de mars, a chunk of the trocadéro, the lighting: all generated as a browser-native 3D scene you can explore. one-shot. i just added a follow-up prompt to add the cinematic path i gave the same prompt to Kimi K3, i'm waiting for it to finish

opus 5 has been...fine? honestly feels more like a gpt model in that it loves to use a lot of words to say nothing of substance. this gif sums up a huge % of interactions with it this weekend.

Opus 5 - Day 2 Insights - It's very prescriptive, constantly giving me advice! - It's way more detailed and thorough - more expensive but overall worth it People are beginning to adapt to it faster than other Opus models We will see 10x this adoption on Monday when Kimi K3 drops open-weights on Monday

opus 5 is a VERY interesting release for a few reasons 1. it showed that the general benchmarks we use today are almost completely useless now opus 5 is nowhere near fable in practical use, not even close. anyone who’s used it meaningfully can tell this very quickly after a few tasks. yet opus beats fable on many benchmarks i now trust domain specific benchmarks built with private datasets a lot more than the popular ones. perhaps the future is everyone running their own evals because the public ones are really not telling us much 2. it seems with the 5 series, anthropic is trying a new way of training models previously, the same generation of sonnet and opus were often released at the same time or sonnet comes out before opus, which indicates sonnet and opus were trained by separate pipelines in parallel with the 5 series, it was very clear that they trained mythos first, and then distilled it into sonnet and opus. it seems this approach has a big influence on the models seeing sonnet 5 being a flop and opus 5 getting pretty mixed reviews already, i’m not sure this is working out 3. “how pleasant is it to work with the model” used to be a strength in claude, but now it’s not. honestly, grok is my favorite right now on the “pleasant” dimension. kimi is not bad either it feels like both anthropic and openai are giving RLHF less care, in favor of scalable RL that’s machine verifiable this almost looks like AI is directing humans to build a world that’s more friendly for machines rather than humans, and most humans don’t even realize they are being manipulated to help with that almost every new generation of frontier models now talk more jargons, need more steering to do what you want, and are just less fun to work with if this continues, AI will start to speak their own language that looks like English but average humans can’t understand. they will choose to do things that their human user never asked for. are we already failing at alignment?

Opus 5 leaves me speechless. i had it build a fully interactive Kerr black hole simulator that runs in the browser you can change the spin, inclination, and accretion disk in real time while the gravitational lensing updates live. i've tested a lot of models on 3D benchmarks but none of them have ever produced anything close to this.