AI

OpenAI, ChatGPT, Gemini, Claude, Deepseek, Open Source, Generative AI, LLM, Ollama, Prompt Engineer, Prompts, Open Source, AI Agents, Vibe Coding

Feeds to Scour
SubscribedAll
Scoured 158 posts in 12.5 ms

local AI agents for Cursor with pre-tuned marketplace/commu

 🤖ChatGPT
locaible.com··Hacker News

aksika/abtars: Self-hosted AI agent bridge - connects LLMs to Telegram/Discord/IRC with memory, tools, scheduled tasks, agent-swarm and self-healing supervision.

 🏠Self-hosted apps  Content type: Code
github.com··Hacker News

Purpose-built local AI agents

 💬Prompt Engineering  Content type: Blog

Notice from SASAC and MIIT on jointly launching the 2026 Special Action Plan for Real-Scene Training of Humanoid Robots and Embodied Intelligence

 🔒Digital Privacy
threadreaderapp.com·

Show HN: One API Key for 45 AI Models – Pay per Token, OpenAI Compatible

 Gemini

DESi — Deterministic governance for LLM pipelines

 💬Prompt Engineering
hstre.github.io··Hacker News

Large companies can add a local LLM filter layer to considerably reducing their AI costs

 💬Natural Language Processing

AI Video Generation Benchmark: 11 LLMs Compared

 🎨Generative AI

"Vibe coding" is the new "Internet dating"

 🤖AI Coding
joecmarshall.com··Hacker News

Claude Fable - Rush Test - Compare vs Opus 4.8 vs ChatGPT 5.5 - 2026-06-09

 🤖AI Coding

The Vibes Were Never the Point. On the Push-and-Pull of AI Usage

 🤖AI Coding  Content type: Blog
blog.ewancroft.uk··Hacker News

I Built a Private AI That Answers Questions From My Own PDFs — Entirely on My Laptop

 🤖AI Tools
pub.towardsai.net
·

DeepSeek enters the fight for token volume, Anthropic continues to dominate spend

 💻Tech News  Content type: Blog
vercel.com··Hacker News

Twenty Year Old Unicorn Goes AI-First Without Mass AI Layoffs

 🤖AI Coding

Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them

 🤖AI Coding
ea.rna.nl··Hacker News

Fixing a stuck Ollama runner and building a GPU watchdog

 🏠Self-hosted apps

Riemann-bench | Surge AI

 🤖AI Tools
surgehq.ai··Hacker News

The AI Agents Stack (2026 Edition)

 🤖Multi-Agent Systems  Content type: Blog
oreilly.com·

Token4Token — pay-per-token inference on Gnosis + Swarm

 🤖AI Tools

Re-quantizing a local LLM 14x faster by skipping the tensors that didn't change

 🧠LLM  Content type: News  Content type: Blog

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help