Viewing profile — petra

Is there a way in Wolfram to check whether all function names exist ? And than give it as feedback to the llm?

Microsoft's taste was "good enough". They lost because of an app ecosystem, and because of Apple's brand power, the same way beautiful Chinese shoes will lose to Nike.

Maybe AMD will do a 3D memory layer for this chip for the kv cache. Possibly even something more dense than SRAM, like cgram, when it's ready. Could this enable a reasonable contex…

You could probably do real-time deep research using that method, and than summarize and ask questions about the results. That is a probably a significant jump in search quality for…

They can do 7nm. But they use multiple patterning(printing the same pattern multiple times to get to 7nm), which is expensive. So it's not comparable on cost to western single-patt…

AMD can let the SRAM be on a different chip. Maybe even something similar to their 3D cache. that could increase density to 20B[1]. They could also move from 6nm to 2nm. that would…

I'm sure Europe currently uses the surveillance capabilities of those systems to prevent bad shit from happening. So maybe they prefer another solution to the sovereignty issue.

Creation of nuclear reactors that are useless for terrorists could help

Software engineers are in a decades long project of automating everyone and everything else, and getting the financial rewards out of that. So...

So maybe your friend need a role reversal: A prompt guiding the llm to act as a consultant, guiding people in implementing a software project, asking questions, creating a shared u…

They probably took our skills and reuse them. That's why skills do not matter anymore.

It can follow instructions well. Just give it a spec in a formal, well defined language. runnable language and some reinforcement learning. It can also handle vague stuff. That's c…

// makers want to make not ask ai to make, It probably changes from person to person, some people are just interested in seeing how their idea comes to life and maybe does somethin…

Also weird old hardware.

But this guy will probably get hired because of this.

And besides llm's memory requirements: -HBM has a lot of room to grow(bandwidth/power/density). And an HBM memory takes 3x the amount of wafers of regular DRAM. -HBM + better DRAM …

Given the limits of LLM's regarding context, why is zero dependencies the goal ? Shouldn't something like maximum reuse/abstraction, minimal written code, should be a better goal ?…

The other side of llm's is the need for rich feedback, often by simulations of various things. And memory latency is a big bottleneck there. So this chip nicely complements the llm…

LoL.maybe the question is not phrased in the best way, English as a second language and laziness, but it's a pretty decent question.

Given LLM's is being smarter still a worthwhile to optimize with supplements?

I wonder what perf. this cpu can get in bit/ternary inference, and whether the 512AVX units(or whats it's called on AMD), get throttled.

You're right. I've used reader mode(the paper in the url bar in Firefox) to solve this.