They are orthogonal; preference optimization like RLHF can be done on the base model which can later be quantized, or it could be done on a new LoRA that is then converted to QLoRA.
First they tried to approve software patents during an agriculture and fisheries council session, now they are bending procedural rules to hack it in before summer vacations. Some weird form of democracy™.
Math is static, CS is dynamic. In math you describe static idealized "worlds", in CS you look at any discrete dynamic process in detail via algorithms. Many folks doing math can't understand algorithms, and many coders can't understand math. Just ask a mathematician what does A = A + 1 mean. There is some inherent impedance mismatch.
I tried to use it while biking but it's extremely confusing for bike trails (colors and parallel routes display, not highlighting real bike trails). I vastly prefer mapy.com in just showing a simple red dashed line for any official bike trail. The elevation is also displayed in 50m increments which is too little for bikes.
Why are they using neural nets to model observed behavior (different parts activated) and then applying them to biological neurons that work completely differently? Real neurons communicate using precisely timed spikes and each neuron does a bunch of local computation as well.
No, the real reason for the code review is to protect the moat of senior engineers/leaders that would nitpick on minute details of code while ignoring the big picture to make sure they can gatekeep any promotions and their competition.
Do you think the current AI automated menial work and left only the fun parts? It seems like the opposite, it took any fun from coding and left the drudgery of debugging code one didn't write intact.
Try to run your prompts through Claude to pinpoint any ambiguous parts that can be interpreted in multiple ways, or self-contradictory sections. I typically resolve any prompt-ignoring issues with that.
Tabata is the craziest workout ever, with Tabata sprints I couldn't feel my legs 3 minutes in and after 4 minutes all I could do was to vomit while shaking on the ground. 7-minute workout with as many reps as possible (even if not in perfect form) helped more overall.
This sounds like adding way too much complexity for something that will likely be covered fully by the next gen of frontier models within a single prompt. It also makes it all opaque and difficult to trace.
I noticed the same with me after a few years working; my solution was to take all hard mathy online MS degrees/grad certs available one after the another. Now I can understand how does the generative AI math work while designing an electric motor for my own robot. Though the latest AI can do it all better than me.