Isn’t there a saying you only truly know something when you're able to explain it to someone else? When I get angry at LLMs proposing stupid solutions, I see it as a positive thing. "damn, this is garbage, here is a much better solution ..." - i know, not really efficient, but enjoyable :)
I still use my K2, which I bought in 2019 from Kickstarter, non-stop. What a piece of hardware! I have no plans to switch and will use it until it dissolves, which doesn’t seem to be happening in the next decade or so
I would be curious to know if from the enterprise / API consumption perspective, these low-performance models aren't the most used ones. At least it matches our current scenario when it comes to tokens in / tokens out. I'd totally buy the price increase if these are becoming more efficient though, consuming less tokens.
For us, it was also pretty good, but the performance decreased recently, that forced us to migrate to haiku-4.5. More expensive but much more reliable (when anthropic up, of course).
According to their benchmarks, GPT 5.4 Nano > GPT-5-mini in most areas, but I'm noticing models are getting more expensive and not actually getting cheaper?
TIL! I'll finally give Claude Code a try. I've been using Cursor since it launched and never tried anything else. The terminal UI didn't appeal to me, but knowing it has better performance, I'll check it out.
Cursor has been a terrible experience lately, regardless of the model. Sometimes for the same task, I need to try with Sonnet 4.5, ChatGPT 5.1 Codex, Gemini Pro 3... and most times, none managed to do the work, and I end up doing it myself.
very impressive. I wonder if this sends a different signal to the market regarding using TPUs for training SOTA models versus Nvidia GPUs. From what we've seen, OpenAI is already renting them to diversify... Curious to see what happens next
Can you elaborate on that? In which part of the RAG pipeline did GPT-4.1 perform better? I would expect GPT-5 to perform better on longer context tasks, especially when it comes to understanding the pre-filtered results and reasoning about them