2026-09-29 12:09 UTC
Replies (2)
-
@iLigator@lemmy.zip 2026-09-29 12:36
You may try to attack my character by implying a bot or throwaway account but my point stands and all metrics agree with what i said. I literally used the newest model of a certain company (not naming them) and the agent finished a weeks work in 2 sessions. It even found lib incompatibilities and a weird bug in codebase without even prompting for that. The models became better but the harness got really good now. Your experience may be a skill issue, your prompts may suck or even your codebase might be too big, or cope, either way we are screwed, please don’t give a false hope by moving the goalpost each time a llm evolves further, it’s better for programmers to swim with the wave and evolve with the profession than be stuck in denial and becone obsolete.
-
@percent@infosec.pub 2026-09-29 19:10
I keep trying AI When you try AI, how do to do it? And do you try for hours? Days? Weeks? There’s a learning curve to use these tools productively, and they often feel unproductive early on while developing your proficiency. I think the learning curve is often misunderstood or understood, possibly because we interface with these tools using natural language. We overestimate how “easy” it “should” be. (This was my own experience anyway, when I first started learning to use AI)