Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
1.
Bend – A language that blocks AI mistakes via proof, on CPU and GPU (news.ycombinator.com)
2.
Bend – A language that blocks AI mistakes via proof and runs on GPUs (news.ycombinator.com)
3.
Nvidia announces native GPU programming in Rust (news.ycombinator.com)
4.
Gaming takes a backseat as Nvidia overhauls the RTX 5090 for maximum AI margins — RTX Pro 5500 delivers 2.6X VRAM at matching specs (tomshardware.com)
5.
Solo dev enables running CUDA on AMD hardware in Windows, getting multiple CUDA libraries running on a gaming Radeon RX 9060 XT GPU in Windows — CUDA-exclusive workloads on AMD hardware in Windows possible without virtualization or dual-booting (tomshardware.com)
6.
CUDA for AMD on Windows (news.ycombinator.com)
7.
B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams (news.ycombinator.com)
8.
DLSS 5 has already been ported to work on RTX 4000 Series graphics cards — incompatible CUDA instructions get patched to work on previous-gen hardware (tomshardware.com)
9.
OpenAI’s Jalapeño AI chip brings new 'threat' to Nvidia margins as custom silicon gains ground (cnbc.com)
10.
Hot Chips 2026: CUDA Targets RISC-V – By Chester Lam (news.ycombinator.com)
11.
What happens when a GPU reads memory (news.ycombinator.com)
12.
Geolocating a random island using geometry and CUDA programming (news.ycombinator.com)
13.
Show HN: PantheonGPU – GPU health testing and AI workload benchmarking (news.ycombinator.com)
14.
Nvidia Jetson chip found in Russian cruise missile, Ukraine claims — presence in S-71 'Monochrome' weapon may indicate use of AI tech (tomshardware.com)
15.
Better Gaussian Splatting in Julia (news.ycombinator.com)
16.
AirLLM 70B inference with single 4GB GPU (news.ycombinator.com)
17.
Microsoft laptop with Nvidia RTX Spark leaked and benchmarked before launch (techspot.com)
18.
Inflect-Micro-v2: complete voice in 9.36M parameters (news.ycombinator.com)
19.
Geekbench 7 debuts with a smarter multi-core benchmark and CUDA support (techspot.com)
20.
Geekbench 7 introduces biggest overhaul yet — real-world CPU testing, new media workloads, AI benchmarks, and CUDA support (tomshardware.com)
21.
Nvidia's first Windows on Arm GeForce driver confirms RTX Spark configurations (techspot.com)
22.
Nvidia has shipped 'hundreds of thousands of Grace standalone servers’ — GPU firm pivots messaging as CPUs take center stage in agentic data centers (tomshardware.com)
23.
Inference startup Infinity raises $15M from Touring Capital, OpenAI and Anthropic researchers (techcrunch.com)
24.
Inference startup Infinity raises $15M from Touring Capital, OpenAI and Athropic researchers (techcrunch.com)
25.
Nvidia DGX Spark as a daily driver (news.ycombinator.com)
26.
Alternative(s) to run CUDA on non-Nvidia hardware (news.ycombinator.com)
27.
A tiny London startup built a CUDA compiler that reportedly beats AMD's own tools on AMD hardware (techspot.com)
28.
Reduce GVisor Cold Starts with GPU Snapshotting (news.ycombinator.com)
29.
Zluda 6 release (run unmodified CUDA applications on non-Nvidia GPUs) (news.ycombinator.com)
30.
What happens when you run a CUDA kernel? (news.ycombinator.com)
Today's top topics: openai anthropic apple ai safety google ios 27 dario amodei iphone 18 pro nvidia microsoft
View all today's topics →