HN user

HalfCrimp

18 karma
Posts0
Comments9
View on HN
No posts found.

Running an llm on a PC running a desktop environment really isn't that bad. You lose a bit of ram & vram but that only matters if you _reaaaally_ want to push to the max model size your hardware can handle.

The biggest issue I've found is absent mindedly opening YouTube or the like that spike ram requirements and freezing the system up. But that's a me problem

Claude Sonnet 4.6 5 months ago

A reference to one of the hall of fame Robber Barons does seem pretty apt right now..

Keras 3.0 3 years ago

I'm a bit of a novice in the space, if keras isn't for inference, what's the intended workflow?

Train with keras and then?

If you are comfortable with C++ already then look at Thrust. It's nvidia's analogue to the standard library arrived at GPU computing.

Writing and launching raw cuda kernels is too low level for me, but writing with Thrust makes it feel pretty similar to writing regular C++ code. You still need to deal with moving data from host to device and back, but that's as simple as assigning a `thrust::device_vector` to a `thrust::host_vector`

Improving sleep 3 years ago

It certainly did for me.

I was a regular espresso drinker, one in the morning with my wife before work and giving it up has made a world of difference. Even a coffee at 7am was impacting my sleep, I suspect I just metabolise caffeine slowly.

I can still have a tea in the morning to replace the ritual, and chocolate doesn't cause me any issues (in moderation) so I'm not 100% caffeine free, but it's made a huge difference to my sleep quality and overall mood. The first week or so felt very sluggish, but one I was sleeping properly I now feel more alert and productive without coffee than I ever did with it.

I still have one occasionally (~2 a month I guess) because I enjoy it, but I definitely notice the sleep impact that night and feel crap the next day.