81–90 of 95 posts
Maybe I'm a control freak, but asking agents to one-shot random apps is nothing like how I actually use AI in software engineering.
Maybe I'm a control freak, but asking agents to one-shot random apps is nothing like how I actually use AI in software engineering.
Grok redeemed? But I wonder how long they will keep it cheap
It constantly ignores explicit instructions (e.g. do NOT remove existing comments) and it's not nearly as intuitive in knowing the right questions to ask as gpt, claude or gemini in my experience from using all of them.
"One honest caveat", "no glitches, no color changes" good tests and I read it to the end but I wish it was written by a human.
> Separate question, separate table. This is our standard latency harness (three short prompts, five reps, 400-token cap), not the build tasks. tok/s is output tokens over wall-clock, uniform for all. > so their tok/s is a ceiling, not a true decode rate. The clear read: the GPT-5.6 tiers are the snappiest models here on short prompts (Luna answers in about a second), Qwen is absurdly cheap and fast, and DeepSeek and…
For the arguments sake: What if that is the authors natural voice?
"One honest caveat", "no glitches, no color changes" good tests and I read it to the end but I wish it was written by a human.
I hear "Honestly" more often from Anthropic than I ever do from all humans.
"One honest caveat", "no glitches, no color changes" good tests and I read it to the end but I wish it was written by a human.
I hear "Honestly" more often from Anthropic than I ever do from all humans.
Earlier quoted context omitted.
> how hard would it have been really to type these two sentences by hand, in your own natural voice On the other hand, do we have to complain about every seemingly AI written text?
It is just horrible writing style. It doesn't particularly matter that AI wrote it.