391–400 of 525 posts
I can't even use Opus for a day before it runs out before. This will make it better but Antigravity has way better UI and also bug solving.
Earlier quoted context omitted.
14 months ago we had GPT-4 and now we have models that can get a gold medal at the IMO. But sure, if you curve fit to the last 3 months you could say things are slowing down, but that's hyper fixating on a very small amount of information.
Yes, that is what I'm saying, that 14 months ago the rate of change was noticeably faster. Lately the new models are much less groundbreaking and increasing in the volume of output and decreasing in cost.
Earlier quoted context omitted.
LLM APIs are more sticky than many other computing APIs. Much of the eng work is in the prompt engineering, and the prompt engineering is pretty specific to the particular LLM you're using. If you randomly swap out the API calls, you'll find you get significantly worse results, because you tuned your prompts to the particular LLM you were using. It's much more akin to a programming language or platform than a typical…
No, LLMs really are not more sticky than traditional APIs. Normal APIs are unforgiving in their inputs and rigid in their outputs. No matter how hard you try, Hyrum's Law will get you over and over again. Every migration is an exercise in pain. LLMs are the ultimate adapting, malleable tool. It doesn't matter if you'd carefully tuned your prompt against a specific six months old model. The new model of today is suffi…
It is possible to write adapters to API interfaces. Many proprietary APIs become de-facto standards when competitors start creating those compatibility layers out of the box to convince you it is a drop-in replacement. S3 APIs are good example Every major (and most minor) providers with the glaring exception of Azure support the S3 APIs out of the box now. psql wire protocol is another similar example, so many databases support it these days.
In the LLM inference world OpenAI API specs are becoming that kind of defacto standard.
There are always caveats of course, and switches go rarely without bumps. It depends on what you are using, only few popular widely/fully supported features or something niche feature in the API that is likely not properly implemented by some provider etc, you will get some bugs.
In most cases bugs in the API interface world is relatively easy to solve as they can be replicated and logged as exceptions.
In the LLM world there are few "right" answers on inference outputs, so it lot harder to catch and replicate bugs which can be fixed without breaking something else. You end up retuning all your workflows for the new model.
Earlier quoted context omitted.
> The nerf is psychologial, not actual Once I tested this, I gave the same task for a model after the release and a couple weeks later. In the first attempt it produced a well-written code that worked beautifully, I started to worry about the jobs of the software engineers. Second attempt was a nightmare, like a butcher acting as a junior developer performing a surgery on a horse. Is this empirical evidence? And this…
> Is this empirical evidence? Look, I'm not defending the big labs, I think they're terrible in a lot of ways. And I'm actually suspending judgement on whether there is ~some kind of nerf happening. But the anecdote you're describing is the definition of non-empirical. It is entirely subjective, based entirely on your experience and personal assessment.
This is gonna be game-changing for the next 2-4 weeks before they nerf the model. Then for the next 2-3 months people complaining about the degradation will be labeled “skill issue”. Then a sacrificial Anthropic engineer will “discover” a couple obscure bugs that “in some cases” might have lead to less than optimal performance. Still largely a user skill issue though. Then a couple months later they’ll release Opus 4…
You're forgetting the step where they write a nefarious paper for their marketing team about the "world-ending dangers" of the capabilities they've discovered within their new model, and push it out to their web of media companies who make bank from the ad-revenue from clicks on their doomsday articles while furthering the regulatory capture goals of the hypocritically Palantir-partnered Anthropic.
I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…
This is gonna be game-changing for the next 2-4 weeks before they nerf the model. Then for the next 2-3 months people complaining about the degradation will be labeled “skill issue”. Then a sacrificial Anthropic engineer will “discover” a couple obscure bugs that “in some cases” might have lead to less than optimal performance. Still largely a user skill issue though. Then a couple months later they’ll release Opus 4…
There are two possible explanations for this behavior: the model nerf is real, or there's a perceptual/psychological shift. However, benchmarks exist. And I haven't seen any empirical evidence that the performance of a given model version grows worse over time on benchmarks (in general.) Therefore, some combination of two things are true: 1. The nerf is psychologial, not actual. 2. The nerf is real but in a way that…
They could publish weekly benchmarks. To disprove. They almost certainly have internal benchmarking.
The shift is certainly real. It might not be model performance but contextual changes or token performance (tasks take longer even if the model stays the same).
Earlier quoted context omitted.
There are two possible explanations for this behavior: the model nerf is real, or there's a perceptual/psychological shift. However, benchmarks exist. And I haven't seen any empirical evidence that the performance of a given model version grows worse over time on benchmarks (in general.) Therefore, some combination of two things are true: 1. The nerf is psychologial, not actual. 2. The nerf is real but in a way that…
> The nerf is psychologial, not actual Once I tested this, I gave the same task for a model after the release and a couple weeks later. In the first attempt it produced a well-written code that worked beautifully, I started to worry about the jobs of the software engineers. Second attempt was a nightmare, like a butcher acting as a junior developer performing a surgery on a horse. Is this empirical evidence? And this…
Earlier quoted context omitted.
You're forgetting the step where they write a nefarious paper for their marketing team about the "world-ending dangers" of the capabilities they've discovered within their new model, and push it out to their web of media companies who make bank from the ad-revenue from clicks on their doomsday articles while furthering the regulatory capture goals of the hypocritically Palantir-partnered Anthropic.
And then Dario gives an interview on why open source models should be banned due to _____.
Earlier quoted context omitted.
I added Opus 4.5 to my benchmark of 30 alternatives to your now-classic pelican-bicycle prompt (e.g., “Generate an SVG of a dragonfly balancing a chandelier”). Nine models are now represented: https://gally.net/temp/20251107pelican-alternatives/index.ht...
I hadn't seen these before, they are so cool ! Definitely enhances the idea to see a bunch of different illustrations in the same place. Blogged about it here: https://simonwillison.net/2025/Nov/25/llm-svg-generation-ben...