I built my own Googlebook with a Raspberry Pi, local LLMs, and old hardware
…Related I don't pay for ChatGPT, Perplexity, Gemini, or Claude – I stick to my self-hosted LLMs instead There's no point in relying on AI tools when my local LLMs…
Search
All sources
xda-developers.com
38
tomsguide.com
15
github.blog
5
macrumors.com
5
theregister.com
4
pcworld.com
3
androidauthority.com
3
cnet.com
2
neowin.net
2
androidpolice.com
2
9to5google.com
1
techradar.com
1
Videos
More videosTop stories
I gave Claude Code access to my NotebookLM sources, and it organized them better than I ever did
1d agoI wish I could ditch Gemini for Claude, but there are 4 things stopping me
6d agoI created a complex web app using Claude Code, Codex, and Antigravity, and only one acted like a tech lead
1w agoI did the math on local AI vs. Claude Pro, and the winner isn't as straightforward as you think
1w agoI tested local AI vs. ChatGPT side-by-side — here are the 7 biggest differences
…However, ChatGPT Plus, Claude Pro and Gemini Advanced all charge monthly fees in exchange for access to their most capable models. Local AI software is often free, but the catch is hardware…
I spent a month with Cursor, Google Antigravity, and Windsurf – and there is a clear winner
…For instance, you can assign Gemini 3.1 for planning and Claude 4.6 for implementation within the same project. There are a couple of cons, though. It’s a new platform…
Vibe physics: The AI grad student
…Only give text prompts to Claude Code . No editing files directly. Don’t cut and paste my own calculations into the chat. But pasting Gemini or GPT calculations was OK, as long…
Discussions and forums
Pelican on a Bicycle: Claude Fable 5 vs. GPT-5.5 Pro vs. Gemini 3.1 Pro
Pelican on a Bicycle: Claude Fable 5 vs. GPT-5.5 Pro vs. Gemini 3.1 Pro
1
Gemini CLI vs. Claude Code: Why agent capabilities matter more than prompts
Gemini CLI vs. Claude Code: Why agent capabilities matter more than prompts
3
Head to Head: Anthropic: Claude Opus 4.8 vs. Google: Gemini 3.5 Flash
Head to Head: Anthropic: Claude Opus 4.8 vs. Google: Gemini 3.5 Flash
3
A/B tested Gemini 3.1 Pro vs. Claude Opus 4.6 – usage quota and quality
A/B tested Gemini 3.1 Pro vs. Claude Opus 4.6 – usage quota and quality
2
Show HN: I built a free API cost calculator after a $340 surprise invoice
I was building a small LLM-powered side project and forgot to account for my system prompt tokens. 800 tokens × 2,000 requests/day × input token rate = $340 invoice I wasn't expecting.Built APICalculators to avoid doin…
1
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.