175K+ publicly-exposed Ollama AI instances discovered
(news.ycombinator.com)
91.
93.
Sampling at negative temperature
(news.ycombinator.com)
94.
Show HN: EuConform – Offline-first EU AI Act compliance tool (open source)
(news.ycombinator.com)
95.
97.
99.
Llamafile Returns
(news.ycombinator.com)
100.
New coding models and integrations
(news.ycombinator.com)
101.
Launch HN: LlamaFarm (YC W22) – Open-source framework for distributed AI
(news.ycombinator.com)
102.
103.
104.
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
(news.ycombinator.com)
105.
Finding thousands of exposed Ollama instances using Shodan
(news.ycombinator.com)
107.
I clustered four Framework Mainboards to test LLMs
(news.ycombinator.com)
108.
109.
110.
111.
Ollama's new app
(news.ycombinator.com)
112.
Ollama has a native front end chatbot now
(news.ycombinator.com)
113.
Nvidia Launches Family of Open Reasoning AI Models: OpenReasoning Nemotron
(news.ycombinator.com)
114.
Meta reportedly hires four more researchers from OpenAI
(techcrunch.com)
115.
116.
Structured Output with LangChain and Llamafile
(news.ycombinator.com)
117.
Show HN: Elelem, a tool-calling CLI for Ollama and DeepSeek in C
(news.ycombinator.com)
118.
Show HN: Tool to Automatically Create Organized Commits for PRs
(news.ycombinator.com)
119.
Meta's Llama 3.1 can recall 42 percent of the first Harry Potter book
(news.ycombinator.com)
120.
Too much social media gives AI chatbots ‘brain rot’
(feeds.nature.com)