Letter: Altimeter's Brad Gerstner and Atreides's Gavin Baker urge Nvidia's board to consider "the potential return of Jensen Huang"; they own $2.13B in Nvidia (Katie Tarasov/CNBC)

Run it in the shadows first: how to earn an agent's permission with diffs, not demos

"It worked when I tried it" is the weakest sentence in software. It is especially weak for an agent, because the demo is a single sample drawn by the person who wants it to pass.

56m ago ·dev.to

I got a RAG app running on a 512 MB free server. The trick was not running the embedding model at all.

Most "build a RAG app" tutorials work fine in a notebook. Then you try to put one online on a free host, and it falls over.

• Use cloud inference service Qdrant Cloud to embed text instead of running an embedding model locally
• Create custom LangChain retriever to pass raw text to Qdrant's querypoints method
• Mitigate Groq LLM API token limit by using higher maxtokens (1024) and low reasoningeffort

55m ago ·dev.to

Verification is necessary, not sufficient: what running a BSC snipe bot taught me about trusting agents

Verification is necessary, not sufficient: what running a BSC snipe bot taught me about trusting agents An agent tells you it did the job. A dashboard shows a green tick. A tool returns an error.

• Verification alone insufficient to trust agents
• Agent Games reveals errors can occur despite green ticks
• Cross-checking evidence and results essential before trusting outcomes

55m ago ·dev.to