avatar
Antiqueight @antiqueight.bsky.social

Technically it's every session when i sit down to use them. Eventually I either give up or get what i needed. Earlier models were actually better than now.

aug 6, 2025, 4:59 pm • 0 0

Replies

avatar
Transmental Me @transmentalme.bsky.social

I completely disagree. Early models, as shown in the chart, were statistically and quantifiably much worse. I'm glad you're experimenting with AI, but you clearly want to blame it for its failure rather than take equal ownership of your partnership in that failure. AI isn't always right.

aug 6, 2025, 5:06 pm • 0 0 • view
avatar
Antiqueight @antiqueight.bsky.social

I have worked with it a fair bit and was enthusiastic as it would simplify things extensively. But I've found llms just aren't trustworthy for handling data. AIs can be great. I haven't been impressed with llms for data.

aug 6, 2025, 5:09 pm • 0 0 • view