@ScriptedAlchemy You do not have enough VRAM for any of the large open weight models. Example GLM 5 is 1.5 TB on disk which will 1.7 loaded into ram. Then you will need a large context window so you are probably looking at close to 2TB of ram needed for fine tuning.
@davepl1968 Dave, totally respect your prepective most of the time. In 1986 the estimated population of the US was 240M. Based on Nelson reporting an estimated 40M people including 2.5M students watched the desaster live. So we are looking at 85% that did not watch it live.
@MaMoMVPY Look up neural networks which trys to mimic the human brain. Our brain is a complex prediction engine. But the thing that makes us human is not our brains but our soul or spirit. Things that a prediction engine will never achieve.
@MaMoMVPY Look up neural networks which trys to mimic the human brain. Our brain is a complex prediction engine. But the thing that makes us human is not our brains but our soul, spirit. Things that a prediction engine will never achieve.
OK Pokรฉmon ppl my son grabbed these on eBay $100. Seems like the seller didn't know what he had or these are fake. What is the best path to get the authenticity of these? PSA?
in either technology or management technique, which by itself promises even one order of magnitude improvement in productivity, in reliability, in
simplicity.
From a paper by Frederick Brooks, No Silver BulletโEssence and Accident in Software Engineering 1986.
Even though it is 40 years ago seems to still ring true today. Maybe even more so.
๐งต๐
So we hear desperate
cries for a silver bullet, something to make software costs drop as rapidly as computer
hardware costs do.
But, as we look to the horizon of a decade hence, we see no silver bullet. There is no single development
๐