cd /news/large-language-models/ask-hk-how-are-you-building-ai-apps-… · home › topics › large-language-models › article
[ARTICLE · art-17702] src=news.ycombinator.com pub= topic=large-language-models verified=true sentiment=· neutral

Ask HK: How are you building AI apps today?

Developers are increasingly integrating large language model APIs into custom applications, moving beyond standard tools like Cursor and Windsurf. Many are building bespoke architectures that directly interface with the APIs to create unique functionalities. This trend highlights a shift toward more tailored AI solutions as the technology matures.

read1 min publishedMay 29, 2026

| |||||||||||||||| 3 points by | Generally curious how folks are using LLM APIs today. Are folks doing anything bespoke, unique or different? I think we've seen a lot of usage with harnesses, CLIs, Cursor/Windsurf etc which uses the APIs underneath. If you are using the API itself, what does your architecture look like with said API? | ||||||||||||||| |

source & further reading
news.ycombinator.com — original article Ask HN: I hate you. Don't leave me (the AI edition) Ask HN: Can someone help me understand the AI vibes on HN? Ask HN: What happened with Eureka Labs, Karpathy's startup?
── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ask-hk-how-are-you-b…] indexed:0 read:1min 2026-05-29 · —