taosu_la

(removed)

(removed)

Ok I'll admit it. At this point, Fable is good enough that I question what the point of me being a software engineer is other than "You're cheaper than Fable... for now.

Holy shit they're not stochastic parrots after all.

The article says that this ability was discovered around opus 4.5, but open-source models like deepseek and glm have already surpassed the capabilities of opus4.5. But why hasn't this been discovered before? Is it because the scale of computing power is not large enough?

so where is gemini ? are u alive?

i love k9s, it iss the best tui I've seen before the AI era(there are too many TUIs in the AI era, I can't keep up with them)

so cooooooooool bro

sry but at first, I thought it was about Anthropic's authentication.

The "second me" developed by the Chinese team can be checked out (it's open-source and also has commercial products), although I feel they haven't found the corresponding profit point and PMF.

I'm really feeling a bit tired of these models. I feel that since opus 4.1, I haven't been able to clearly feel the intelligence improvement from the model upgrades (except for gpt 5.5 and opus4.6 being able to speak like a human)

Can someone tell me if the current sub-agent of codex is available now? There used to always be a spinning issue.

Is this a new trend? Why are everyone starting to do desktop runtime? For example, I recently saw Bun Electron, and then I saw this project.