Keep on to blur preview images; turn off to show them clearly
TBH, every time the AI fails, I mentally blame it on you. Right now GPT-5.2 noticed that the parser was counting variables incorrectly, causing a linearity bug. The solution? "Ignore the parser counter and implement a separate counter." At this point, this isn't about being dumb. This is about making a bad decision that under no circumstances would be good. Either we remove the parser counter and use a separate function as the source of truth, or we keep it, and fix it. But such insane duct taping has no place in a serious codebase, and that idea would never have occurred to an intelligence evolved to learn coding from a pure blank state. It must have been corrupted by evil forces that only humans can produce. So I can't help but wonder... Who it learned that from? I blame it on you
Kind / Bend / HVM / INets / λCalculus
TBH, every time the AI fails, I mentally blame it on you. Right now GPT-5.2 noticed that the parser was counting variables incorrectly, causing a linearity bug. The solution? "Ignore the parser counter and implement a separate counter." At this point, this isn't about being dumb. This is about making a bad decision that under no circumstances would be good. Either we remove the parser counter and use a separate function as the source of truth, or we keep it, and fix it. But such insane duct taping has no place in a serious codebase, and that idea would never have occurred to an intelligence evolved to learn coding from a pure blank state. It must have been corrupted by evil forces that only humans can produce. So I can't help but wonder... Who it learned that from? I blame it on you
Kind / Bend / HVM / INets / λCalculus
TBH, every time the AI fails, I mentally blame it on you. Right now GPT-5.2 noticed that the parser was counting variables incorrectly, causing a linearity bug. The solution? "Ignore the parser counter and implement a separate counter." At this point, this isn't about being dumb. This is about making a bad decision that under no circumstances would be good. Either we remove the parser counter and use a separate function as the source of truth, or we keep it, and fix it. But such insane duct taping has no place in a serious codebase, and that idea would never have occurred to an intelligence evolved to learn coding from a pure blank state. It must have been corrupted by evil forces that only humans can produce. So I can't help but wonder... Who it learned that from? I blame it on you
Kind / Bend / HVM / INets / λCalculus
Another day of AI being a net loss. I'm a bit sad today. Usually I'd just sit down and code, but AI exists, and that crossed my motivation threshold. Instead, I just kept asking it to do a task that I know is too hard for it. Expectedly, it failed, and I did nothing useful today
just to be clear, this is obv my own fault
I don't understand why the (Anthropic | OpenAI) + (Cerebras | Groq | SambaNova) partnership isn't a thing yet. Whatever is going under the hood, everyone is losing here. Imagine Opus 4.5 running at 1000 tokens/s?
Kind / Bend / HVM / INets / λCalculus
apparently it also managed, in another tab, to fully port parallel-mode from the old HVM to the new one? that is a COLOSSAL task. I didn't even bother to try asking an AI before, because it shouldn't work. back on my mind I knew it should take days. but it did in... an hour? seems like this model just keep working and never loses track crazy times
Kind / Bend / HVM / INets / λCalculus