Feed aggregator

Article URL: https://www.nytimes.com/2024/05/04/arts/frank-stella-dead.html

Comments URL: https://news.ycombinator.com/item?id=40262289

Points: 1

# Comments: 0

Article URL: https://man.exherbolinux.org/syd-oci.1.html

Comments URL: https://news.ycombinator.com/item?id=40262274

Points: 1

# Comments: 0

Article URL: https://yuanchuan.dev/time-based-css-animations

Comments URL: https://news.ycombinator.com/item?id=40262236

Points: 1

# Comments: 0

Article URL: https://www.livescience.com/space/space-exploration/controversial-paper-claims-satellite-megaconstellations-like-spacexs-could-weaken-earths-magnetic-field-and-cause-atmospheric-stripping-should-we-be-worried

Comments URL: https://news.ycombinator.com/item?id=40262226

Points: 1

# Comments: 0

Article URL: https://notes.mtb.xyz/p/fintech-stack-open-source

Comments URL: https://news.ycombinator.com/item?id=40262221

Points: 1

# Comments: 0

Article URL: https://thereader.mitpress.mit.edu/buddhist-economics/

Comments URL: https://news.ycombinator.com/item?id=40262218

Points: 2

# Comments: 0

A while back there was a post about running stable diffusion on a Raspberry Pi Zero 2 [1] which was slow but incredibly impressive! And that sparked my curiosity with this question, what is considered affordable hardware for running large language models locally today? I'm aware that there's a lot of work underway to make inference cheap to run at the edge but I'm curious to understand the landscape at present that anyone could purchase. I seen people running models on flagship smartphones but those are more expensive then a mac mini with worse performance.

By affordable I mean no greater then the cost of a current gen base model mac mini ($599) but ideally around the price of a raspberry pi 5 ($79) which when searching for budget PC gets mentioned[2]. Both devices have the same amount of ram in my case (8gb) but different performance observed given the importance of memory bandwidth. I mention these two because I've had experience running llama 3 via ollama on both with success although of slower speeds compared to a full workstation with a commodity GPU i.e. RTX 4090 which starts at ($1599). I'm interested in learning about what other devices are out there that people consider cheap and use for LLMs locally.

[1]: https://news.ycombinator.com/item?id=38646969

[2]: https://www.pcmag.com/picks/the-best-budget-desktop-computers

Comments URL: https://news.ycombinator.com/item?id=40262206

Points: 1

# Comments: 0

Article URL: https://www.theverge.com/24147569/apple-notes-ios-iphone-how-to

Comments URL: https://news.ycombinator.com/item?id=40262199

Points: 1

# Comments: 0

Article URL: https://arstechnica.com/tech-policy/2024/05/judge-mulls-sanctions-over-googles-shocking-destruction-of-internal-chats/

Comments URL: https://news.ycombinator.com/item?id=40262190

Points: 4

# Comments: 0

Article URL: https://fridaydeployment.co/

Comments URL: https://news.ycombinator.com/item?id=40262182

Points: 1

# Comments: 0

Article URL: https://twitter.com/SterlingCooley/status/1786835641059496060

Comments URL: https://news.ycombinator.com/item?id=40262168

Points: 2

# Comments: 1

These days I realized I am a bad programmer. I'm sure this is not imposter syndrome.

I graduated in CS at 26, working since age of 24 only in web development, mostly front-end, but more recently full stack.

I sort of coasted through various jobs in the last 13 years.

Managed to became tech lead 5 years ago, but went back to just development due to burnout.

I have never applied any algorithm or particular data structure and I have never worked really really hard, beyond "just" coding.

Now I feel I have wasted all my best years and left with some coding skills that will become obsolete in a few years (if I 'm lucky).

I don't have any satisfaction from my job and I did not develop other soft skills that might help me...

I'm not exactly sure on what to do now... Study DSA? Transition to management? Construction?

Comments URL: https://news.ycombinator.com/item?id=40262152

Points: 1

# Comments: 2

Article URL: https://coryd.dev/posts/2024/single-points-of-failure/

Comments URL: https://news.ycombinator.com/item?id=40262135

Points: 1

# Comments: 0

Article URL: https://github.com/hybridgroup/cylon

Comments URL: https://news.ycombinator.com/item?id=40262115

Points: 3

# Comments: 0

Article URL: https://github.com/Serial-Studio/Serial-Studio

Comments URL: https://news.ycombinator.com/item?id=40262112

Points: 2

# Comments: 0

Article URL: https://9to5google.com/2024/05/04/google-fit-api-shutdown/

Comments URL: https://news.ycombinator.com/item?id=40262082

Points: 2

# Comments: 0

Article URL: https://projectneo.adobe.com/

Comments URL: https://news.ycombinator.com/item?id=40262078

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=Lu56xVlZ40M

Comments URL: https://news.ycombinator.com/item?id=40262065

Points: 2

# Comments: 0

Article URL: https://www.wired.com/story/nick-bostrom-fear-ai-fix-everything/

Comments URL: https://news.ycombinator.com/item?id=40262060

Points: 2

# Comments: 0

Article URL: https://cleantechnica.com/2024/05/03/elegant-wind-turbine-blades-made-of-wood-can-outperform-composites/

Comments URL: https://news.ycombinator.com/item?id=40262059

Points: 2

# Comments: 0