Videos — All · 24 cards

AI Engineer · English · 09/18/2026

AI Engineer · English · 09/17/2026Computing/Software · Internet Technology

— Replacing TCP or RoCE with HOMA reduces 99th percentile tail latency by an order of magnitude for small AI cluster messages by implementing receiver-driven congestion control and Shortest Remaining Processing Time scheduling.

AI Engineer · English · 09/16/2026Computing/Software · Internet Technology

— Multi-scale indexing and Reciprocal Rank Fusion eliminate the limitations of fixed chunk sizes, increasing retrieval recall by 20% to 40% across diverse datasets.

AI Engineer · English · 09/16/2026Small Business/Startups · Computing/Software

— Applying reinforcement learning to search sub-agents reduces retrieval costs by 100x and speeds up execution from minutes to 5 seconds.

AI Engineer · English · 09/16/2026

AI Engineer · English · 09/16/2026Management · Computing/Software

— DocuSign partners with NVIDIA to process million-agreement scales by combining Agreement Manager with the NemoTron parse model, turning unstructured PDF and PNG contracts into queryable data 20x faster.

AI Engineer · English · 09/16/2026Management · Computing/Software

— Designing AI agents as knowledge workers rather than coding agents enables scalable information retrieval through multi-tiered task decomposition and hybrid search orchestration.

AI Engineer · English · 09/16/2026Computing/Software · Internet Technology

— The rise of autonomous personal assistants and specifications like MCP Apps is shifting the web from human-centric browsing to a nearly headless model where agents interact via APIs and dynamic UI fragments.

AI Engineer · English · 09/16/2026

AI Engineer · English · 09/16/2026Computing/Software · Internet Technology

— BM25 drives efficient agentic search because powerful models generate long, specific queries that leverage exact lexical matching alongside grep tools.

AI Engineer · English · 09/16/2026Computing/Software · Internet Technology

— Pinecone's Nexus shifts agent architectures from heavy prompt-based tooling to a runtime coding engine that generates and executes code directly, reducing token consumption by up to 90% and improving response speeds by up to 77%.

AI Engineer · English · 09/15/2026Consumer Electronics · Computing/Software

— Optimizing conversational behaviors under uncertainty using an outcome user cost heuristic minimizes user friction and improves voice assistant satisfaction without requiring underlying model accuracy gains.

AI Engineer · English · 09/15/2026Computing/Software · Internet Technology

— Voice AI systems fail when treated as simple pipeline software instead of a real-time joint activity, requiring an interdependent linguistic framework across sound, word, interaction, and mental model layers to retain context and avoid live-agent escalations.

AI Engineer · English · 09/15/2026Computing/Software · Internet Technology

— Combining streaming speculative transcription, background tool calling, and prefix-cached text-to-speech synthesis enables real-time conversational voice agents with frontier-level intelligence.

AI Engineer · English · 09/15/2026

AI Engineer · English · 09/15/2026Management · Computing/Software

— Voice agent reliability remains the primary bottleneck for scaled deployment, with a 10 percent real-world error rate and vulnerability to adversarial exploits that bypass verification steps.

AI Engineer · English · 09/15/2026Small Business/Startups · Computing/Software

— Building a voice-first AI companion requires sub-two-second latency, robust retrieval memory systems, model routing by stakes, and autonomous agent fleets that co-author the codebase.

AI Engineer · English · 09/15/2026Computing/Software · Internet Technology

— Multi-stream language models and hybrid architectures solve the latency, turn-taking, and intelligence trade-offs of voice agents by decoupling full duplex naturalness from background reasoning engines.

AI Engineer · English · 09/15/2026Computing/Software

— GPT real-time 2 brings reasoning, native audio processing, and parallel tool calling to voice agents, shifting interaction modes beyond speech-to-speech into speech-to-action and event-to-speech.

AI Engineer · English · 09/15/2026Consumer Electronics · Computing/Software

— Achieving advanced conversational AGI requires a single promptable speech-to-speech model supporting low-latency multilingual lip-syncing, multimodal visual output, and real-time tool calling.

AI Engineer · English · 09/14/2026Computing/Software · Internet Technology

— Agent architectures shift from complex Python orchestration and hardcoded loops to file-based workflows, markdown system instructions, and isolated cloud sandboxes.

AI Engineer · English · 09/14/2026Small Business/Startups · Computing/Software

— Vercel solved internal agent building by transitioning from complex multi agent chains to a sandboxed file system agent architecture powered by the newly released open source framework Eve.

AI Engineer · English · 09/14/2026Management · Computing/Software

— Managing enterprise agent memory within a multi-model database eliminates data fragmentation and solves context coordination bottlenecks across distributed teams.

AI Engineer · English · 09/14/2026Small Business/Startups · Computing/Software

— Securing agentic CLI tools that execute bash commands requires deterministic mechanical enforcement rules combined with automated supply-chain content scanning.