Muse and DeepSeek are fighting over API prices while Luna gets bundled into increasingly ridiculous subscriptions.
Tagged Content
Tagged “AI”
32All posts tagged with #AI.
-
-
After using Claude Code at work and Codex + Antigravity for personal dev, Codex on the $20 plan is clearly the best bang for the buck right now.
-
A local LLM post did better than expected, and the site crossed 5k users.
-
A practical guide to hardware, OS, and llama.cpp tuning, built from a year of experiments on a single consumer CUDA workstation.
-
Local benchmarks comparing Gemma 4 26B under standard, QAT, MTP, and combined QAT+MTP configurations on an RTX 4070.
-
End-to-end Gemma 4 setup with official MTP assistant drafter models on llama.cpp.
-
A messy still-frame trailer experiment, and the weirdly practical lessons hiding inside it.
-
I burned API credits comparing ChatGPT Images 2.0, Nano Banana, and Imagen on prompts designed to be annoying.
-
End-to-end Qwen3.6-35B-A3B MTP setup on llama.cpp with throughput notes and MTP speculative decoding speedups.
-
-
-
-
-
Practical Qwen3.6 setup on 12 GB VRAM using llama.cpp.
-
A data analyst's mostly futile quest for the perfect workflow.
-
-
End-to-end Gemma 4 setup on mainline llama.cpp with text and vision throughput notes.
-
-
aidar tracks stylistic signals associated with AI-era writing across the web
-
-
You probably don't need >$100 plans for coding nowadays.
-
Squeezing every token per second - the sequel
-
Ramblings on what gets quietly lost when intelligence becomes a utility.
-
A lazy person's guide to exploratory data analysis that actually produces something at the end
-
-
-
-
-
It's irresistibly fun, and yet, something doesn't sit quite right.
-
-
-
See all tags.