davewiner's subscription list, hackerNewsStars category. List created by feedlandDatabase v0.9.1.
A short how-to with just the basics to get going.
Video of GPT-OSS 20B running on a phone
GPT-OSS 20B is a very good model. At launch OpenAI claimed:The gpt-oss-20b model delivers similar results to OpenAI o3‑mini on common benchmarks and can run on edge devices with just 16 GB of memory
Nexa AI just posted a video on Twitter demonstrating exactly that: the full GPT-OSS 20B running on a Snapdragon Gen 5 phone in their Nexa Studio Android app. It requires at least 16GB of RAM, and benefits from Snapdragon using a similar trick to Apple Silicon where the system RAM is available to both the CPU and the GPU.
The latest iPhone 17 Pro Max is still stuck at 12GB of RAM, presumably not enough to run this same model.
Tags: android, ai, openai, generative-ai, local-llms, llms, gpt-oss
Pluralistic: Daily links from Cory Doctorow
• Cory Doctorow
DYNOMIGHT
• dynomight
yeah probably
Jeff Geerling
• Jeff Geerling
While not an absolute requirement for modern graphics card support on Linux, Resizeable BAR support makes GPUs go faster, by allowing GPUs to throw data back and forth on the PCIe bus in chunks larger than 256 MB.
In January, I opened an issue in the Raspberry Pi Linux repo, Resizable BAR support on Pi 5.
I get a feeling that working with multiple AI agents is something that comes VERY natural to most senior+ engineers or tech lead who worked at a large company
You already got used to overseeing parallel work (the goto code reviewer!) + making progress with small chunks of work... because your day has been a series of nonstop interactions, so you had to figure out how to do deep work in small chunks that could have been interrupted
Tags: gergely-orosz, parallel-agents, coding-agents, ai-assisted-programming, generative-ai, ai, llms
Pluralistic: Daily links from Cory Doctorow
• Cory Doctorow
TL:DR Production Updates (re)Introducing the Pebble Appstore Partnered with Rebble New and improved (re)Start building apps/faces Mobile…
Troy Hunt
• Troy Hunt
You see it all the time after a tragedy occurs somewhere, and people flock to offer their sympathies via the "thoughts and prayers" line. Sympathy is great, and we should all express that sentiment appropriately. The criticism, however, is that the line is often offered as a substitute
Why not to protect your books with DRM.
Python 3.14 Is Here. How Fast Is It?
Miguel Grinberg uses some basic benchmarks (like
fib(40)) to test the new Python 3.14 on Linux and macOS and finds some substantial speedups over Python 3.13 - around 27% faster.
The optional JIT didn't make a meaningful difference to his benchmarks. On a threaded benchmark he got 3.09x speedup with 4 threads using the free threading build - for Python 3.13 the free threading build only provided a 2.2x improvement.
Via lobste.rs
Tags: gil, performance, python