"impossible standards" every time something like this happens i am deeply disgusted by the amount of vulgarity displayed in the name of nationalism. every such episode makes the task of anyone trying to do good a hundred times harder. you celebrate incompetence and deserve to suffer its consequences not others.

this is insane, i cannot fathom even any 8B param model making such a mistake, this is beyond imagination. everyone involved with the eMudhra shitshow should have equivalents of perma-ban and/or investigations to this degree of neglect.

ideas that are non-negotiable for building an ai that actually learns with experience (part 2): > agents love creating tests but they are useless and more often than not, net negative. passing these tests is like placebo. it serves no more value than giving your agent morale boost. > counterfactuals are your friend, you are looking for ways to get surprised. so in curation or synthesis, you want to explore in ways like what if agent used a differrent path than earlier. this is clear superiority over the approach where historical traces yield little value because they may only contain happy paths or select few issues. > your extraction per experience needs to be a structured and meaningful process. some of the things we use that are highly effective are - correctness, error detection/blame assignment, action-level credit, flagging possible sub-trajectories for reuse. one expensive and painful execution can support several cheap learning operations. > when is human involvement actually useful? primarily the delta i have seen in this area is where we teach the system how to construct and evaluate new experiences. correcting one answer is often weak value and thus you need to have a way to ask your human abstract questions and let the agent backtest strategies applying what it infers from those abstractions. > you want to checkpoint or version control everything. you are going to use fork/replay/diff/reset a lot if you are working on anything serious. > your evals need to be robust and diverse enough that you can identify regressions nicely. because in a continual learning environment, you are going to face random unexplained forgetfulness at times and that is why you need checkpointing, to do iterative merge and eval loops in such cases. > promotion to a new improved version should be much harder than training. think of it like how you have to use your finger multiple times to ensure it is properly being detected. useful insights gathered to make a proper update may take weeks and continual learning isn't going to look like a daily or weekly checkpoint update. > continual learning in the most practical way i look at it, is a plumbing problem.

if i understand this correctly, this says modern LLMs may naturally develop specialized neurons for coherent concepts, rather than arbitrarily mixing unrelated concepts into the same neurons. so it means given sufficiently large network and enough data/compute, everything should get its clean abstraction. which is quite convenient and if it was intuitive to some people they would have started working on capabilities isolation six months ago, oh wait.