[ 69131220.000 ] posts.x: Full talk on the OWASP Top 10 for LLM, AI-BOM, MCP exploits, and red teaming a vulnerable student chatbot live:  |   [ 69131220.000 ] posts.x: Ask a chatbot for its system prompt five times and it might refuse every time, then just hand it over on the sixth, not because you changed your…  |   [ 69121740.000 ] posts.x: Full talk on redacting sensitive documents through a self-hosted MCP server while cutting token costs:  |   [ 69121740.000 ] posts.x: Redacting a document's phone numbers and social security numbers before Claude Code ever sees the file, while also cutting token spend in the same…  |   [ 69110640.000 ] posts.x: Full talk on the attention curve, memory pointers, and keeping agent context lean instead of just large:  |   [ 69110640.000 ] posts.x: A bigger context window doesn't fix an agent that's drowning in its own tool output. @ElizabethFue12, a Developer Advocate at AWS, makes that case in…  |   [ 69100500.000 ] posts.x: Full talk on building and hardening a customer service agent with Strands Agents, then shipping it on Amazon Bedrock AgentCore:  |   [ 69100500.000 ] posts.x: A customer service agent built in under 60 lines of code, then deployed to production with a single CLI command: that's the shape of "Agent…  |   [ 69088140.000 ] posts.x: Full talk on closing the trace-to-fix loop, including the Wonder Toys live demo and Signal:  |   [ 69088140.000 ] posts.x: Your code can't tell you what your agent did on any given run, only your traces can, because the same input can produce different paths and even…  |   [ 69042300.000 ] posts.x: Full talk on building real-time multimodal voice agents with the Gemini Live API, from native audio to tool calls and live translation:  |   [ 69042300.000 ] posts.x: A voice agent that never converts speech to text, understanding and replying in audio directly across 90 languages, is the subject of @thorwebdev's…  |   [ 68963460.000 ] posts.x: @WolframRvnwlf @aiDotEngineer Mate, the time we spent chatting was among the most rewarding and delightful of the week! Looking forward to seeing you…  |   [ 68938980.000 ] posts.x: Full talk on measuring perceived latency instead of dashboard latency, and the async tool pattern that keeps a voice agent talking while it works:  |   [ 68938980.000 ] posts.x: A voice agent can measure fast and still sound slow to the person on the phone. @codeSTACKr, Staff Developer Advocate at LiveKit, takes that gap…  |  

[ 69131220.000 ] posts.x: Full talk on the OWASP Top 10 for LLM, AI-BOM, MCP exploits, and red teaming a vulnerable student chatbot live:  |   [ 69131220.000 ] posts.x: Ask a chatbot for its system prompt five times and it might refuse every time, then just hand it over on the sixth, not because you changed your…  |   [ 69121740.000 ] posts.x: Full talk on redacting sensitive documents through a self-hosted MCP server while cutting token costs:  |   [ 69121740.000 ] posts.x: Redacting a document's phone numbers and social security numbers before Claude Code ever sees the file, while also cutting token spend in the same…  |   [ 69110640.000 ] posts.x: Full talk on the attention curve, memory pointers, and keeping agent context lean instead of just large:  |   [ 69110640.000 ] posts.x: A bigger context window doesn't fix an agent that's drowning in its own tool output. @ElizabethFue12, a Developer Advocate at AWS, makes that case in…  |   [ 69100500.000 ] posts.x: Full talk on building and hardening a customer service agent with Strands Agents, then shipping it on Amazon Bedrock AgentCore:  |   [ 69100500.000 ] posts.x: A customer service agent built in under 60 lines of code, then deployed to production with a single CLI command: that's the shape of "Agent…  |   [ 69088140.000 ] posts.x: Full talk on closing the trace-to-fix loop, including the Wonder Toys live demo and Signal:  |   [ 69088140.000 ] posts.x: Your code can't tell you what your agent did on any given run, only your traces can, because the same input can produce different paths and even…  |   [ 69042300.000 ] posts.x: Full talk on building real-time multimodal voice agents with the Gemini Live API, from native audio to tool calls and live translation:  |   [ 69042300.000 ] posts.x: A voice agent that never converts speech to text, understanding and replying in audio directly across 90 languages, is the subject of @thorwebdev's…  |   [ 68963460.000 ] posts.x: @WolframRvnwlf @aiDotEngineer Mate, the time we spent chatting was among the most rewarding and delightful of the week! Looking forward to seeing you…  |   [ 68938980.000 ] posts.x: Full talk on measuring perceived latency instead of dashboard latency, and the async tool pattern that keeps a voice agent talking while it works:  |   [ 68938980.000 ] posts.x: A voice agent can measure fast and still sound slow to the person on the phone. @codeSTACKr, Staff Developer Advocate at LiveKit, takes that gap…  |