Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖 - mahimairaja/voiceai

Anyone who works with computers has been here though, far before AI. When something goes wrong, we’re as likely as anyone to assume the computer is cursed, has it out for us specifically, or needs to be appeased in some way. And at that moment, the computer does have an interiority that is hidden from us. There certainly is something we haven’t seen or don’t understand! A good programming tool or computer language, though, is a means for us to find and dissect that interiority, stripping away the illusion. AI actively worsens it instead.

A great summary of why people feel anger towards AI and in general the CEOs pushing it.

How I built a structured AI-assisted development workflow as a Tech Lead, where the real work happens before a single line of code is written.

A new open source API provider, which may have really good pricing.

A new agent harness that claims to save tokens.

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local - tobi/qmd

llm-wiki. GitHub Gist: instantly share code, notes, and snippets.

A great explanation of the most burning problem of LLM usage in science: a novice, by relying on LLMs to do the work, will skip the learning process that would have turned them into a scientist.

via: https://lobste.rs/s/gpqkcx/eight_years_wanting_three_months

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro. - fikrikarim/parlor

By Rohit Patel. Intuitive explanation of how LLMs work using only middle school level math concepts - covers embeddings, self-attention, transformers and training.

An excellent write-up on the current and future potential (or lack thereof) of AI / LLMs in science.

via: https://news.ycombinator.com/item?id=47550282