flysurfer2's Feed · Scour

Sometimes It's Too Slow

spyglass.org·3h

Building the Future with AI That Acts

devxt.com·1d·

Discuss: Hacker News

Michael Tsai - Blog - LLMs and Software Development Roundup

mjtsai.com·2d

Intel XeSS 3 MFG mod triples Arc A380 triples performance in Cyberpunk 2077 — supercharged 6GB GPU pumps out 140 FPS at 1080p on low preset

tomshardware.com

·1d

4 Emacs packages that replaced everyday apps for me

howtogeek.com·10h

AI companies want you to stop chatting with bots and start managing them

arstechnica.com·3d

Battle of the chatbots: Anthropic and OpenAI go head-to-head over ads in their AI products

theguardian.com·1d

God, Gold and GPUs

yaroslavvb.substack.com·11h·

Discuss: Substack

Anthropic's team cut ad creation time from 30 minutes to 30 seconds

claude.com·16h·

Discuss: Hacker News

Experiments in building bespoke tools with AI

knlb.dev·1h·

Discuss: Hacker News

OpenAI launches GPT‑5.3-Codex with faster and broader agentic coding capabilities

alternativeto.net·1d

Installing OpenClaw on a Jetson Nano

brtkwr.com·5h·

Discuss: Hacker News

The Rise of Local Speech Recognition

oatmealapp.com·7h·

Discuss: Hacker News

LlamaLib: A cross-platform C++/C# library for local LLMs based on llama.cpp

github.com·2d·

Discuss: Hacker News

Extracting Xcode's Claude Code Prompt

jackpearce.co.uk·1d·

Discuss: Hacker News

Optimized LLM Inference Engines

rishirajacharya.com·4d

surfingcomplexity.blog·1d

Sign up or login to customize your feed and get personalized topic recommendations

Show HN: Seedream 5.0: free AI image generator that claims strong text rendering

seedream5ai.org·18h·

Discuss: Hacker News

Joy & Curiosity #73

registerspill.thorstenball.com·20h

Hitting 1,000 tokens per second on a single RTX 5090

blog.alpindale.net·3h·

Discuss: Hacker News

Loading more...