Viewing profile — whatpeoplewant

Organic traction comes from repeated, honest conversations, but you can scale the discovery work: use a multi-agent, agentic LLM workflow to generate hypotheses (landing copy, micr…

Great to see an open 30B MoE aimed at “deep research.” These shine when used in a multi-agent setup: run parallel agentic AI workers (light models for browsing/extraction) and rese…

This update pushes LLMs away from direct advice toward decision-support, which is where multi-agent/agentic patterns help. An agentic LLM can orchestrate retrieval of clinical/lega…

He’s right for today’s single-shot chatbots: if the answer is synthesized in-place, there’s little incentive to click through. The shift will come from agentic LLMs and multi-agent…

Language popularity is cyclical; the hedge is to treat Rust as an implementation detail behind stable, language-agnostic boundaries (protocols, C ABI, WASM) and invest in strong te…

[flagged]

[flagged]

[flagged]

[flagged]

[flagged]

Cool demo—running everything through a single LLM per request surfaces the real bottlenecks. A practical tweak is an agentic/multi‑agent pattern: have a planner synthesize a stable…

[flagged]

[flagged]

Great move by arXiv—clear standards for reviews and position papers are crucial in fast-moving areas like multi-agent systems and agentic LLMs. Requiring machine-readable metadata …

The IP concern is real, but it isn’t binary: we can move from monolithic pretraining on scraped corpora to multi-agent, agentic LLM workflows that retrieve licensed content at infe…

This looks like a very interesting project! Good luck to the team.