Qwen3-4B fine-tune strips AI writing tics, runs locally via Ollama

Pegasus 1.5 turns long-form video into structured, timestamped metadata, returning every segment matching a described moment. AWS announced availability on Oct 9, 2026.

Deepgram's speech-to-text, text-to-speech and voice-agent models process quadrillions of audio tokens a year for over 200,000 developers and 1,400 organizations. The AWS post details how it optimized those models on Trainium chips.

Switching from a blocking tool to a streaming tool on gemini-3.8-live cut time to the agent's first words from 14.4 seconds to 1.2 seconds in a benchmark sales-report workflow. The guide covers non-blocking FunctionTool definitions and response_scheduling in the open-source Agent Development Kit.

Projects "dumbtv" and "cleanyourtv" use AI agents to remove sponsored ads, bloatware and ACR viewing tracking from Android TV and Google TV sets over Wi-Fi. cleanyourtv's creator said a few thousand people ran his prompt on Xiaomi, TCL, Sony, Fire TV and LG sets within two days.

Two AWS posts cover KV-cache transfer techniques in vLLM's disaggregated inference: push-based transfer to cut time-to-first-token and time-per-output-token, and bi-directional transfer for multi-turn agentic workloads where clients resend growing conversation history each turn.

Meta replaced per-item IDs with a stable semantic token vocabulary, letting its Generative Ads Model reason about unseen products instead of starting from zero signal. Paired with GEM and Meta's Adaptive Ranking Model, it delivered a +0.35% conversion lift across surfaces for advertisers.

Episode features Uday Kiran Medisetty, a Distinguished Engineer at Uber, discussing codebases that improve themselves. Published as part of The Pragmatic Engineer Podcast.