--- title: Sonam Gupta, PhD | Telnyx canonical: https://telnyx.com/authors/sonam-gupta-phd --- # Sonam Gupta, PhD | Telnyx Author # Sonam Gupta, PhD Developer Evangelist Sonam is a San Francisco-based developer advocate, originally from India. She has completed 2 Master's Degrees and her PhD in Data Science from the Harrisburg University of Science & Technology. Previously, Sonam worked for the startups Ozmosi and aiXplain. In her free time, you will find Sonam dancing, writing, and exploring local coffee shops. 10 Articles 2025 Joined ## Latest articles Everything Sonam has published, most recent first. * [![GLM-5.3 Flash, GLM-5.3, and Kimi K3 across 45 multi-turn agent conversations](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/multi-turn-llm-benchmark.png?width=3600&format=webp)**Inference**8, Oct 2026We tested 3 open-weight models for multi-turn agentsGLM-5.3 Flash, GLM-5.3, and Kimi K3 across 45 multi-turn agent conversations. The results show how to match a model to your workload.](https://telnyx.com/resources/choose-open-weight-model) * [![Avoiding indirect prompt injection in AI coding agent instruction files like AGENTS.md and CLAUDE.md](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/ai-prompt-injection-avoidance.svg)**Inference**5, Oct 2026How to scan AGENTS.md and CLAUDE.md for indirect prompt injectionCheck AGENTS.md, CLAUDE.md, and legacy Cursor rules for indirect prompt injection using a Python scanner with GLM 5.3 Flash and Telnyx inference.](https://telnyx.com/resources/scan-agents-md-prompt-injection) * [**Inference**18, Sep 2026GLM-5.3 latency benchmarks across four inference providersWe benchmarked GLM-5.3 latency across Telnyx, Baseten, Together AI, and Fireworks using the same 60 prompts. Telnyx delivered the lowest median completed-response time in five of six workloads and the lowest observed p95 E2E in all six.](https://telnyx.com/resources/glm-5-3-latency-benchmarks-provider) * [![low latency hero](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/low-latency-featured-3x.png?width=5568&format=webp)**Conversational AI**10, Sep 2026What Is Voice AI Latency? Typical Numbers, Standards, and How to Measure ItLearn about voice AI latency, benchmark response time, and how it is measured end to end for real phone calls.](https://telnyx.com/resources/low-latency-voice-ai) * [**Inference**10, Sep 2026Inference Benchmark: Which Latency Metric Should You Optimize For?A head-to-head latency benchmark of three leading inference providers across 540 streamed requests.](https://telnyx.com/resources/inference-benchmark-ttft-vs-e2e) * [![GLM 2.5 Inference Benchmarks](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/glm-5-2-inference-benchmarks.png?width=2160&format=webp)**Inference**10, Sep 2026GLM 5.2 Inference benchmarks across 4 providersThis report compares GLM 5.2 inference latency across Telnyx, Baseten, Together AI, and Fireworks using the same six prompt profiles and 10 streamed runs per provider/profile cell.](https://telnyx.com/resources/glm-5-2-inference-benchmarks-provider) * [![GLM-5.3-Flash blog header](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/glm-5-3-flash-blog-header-1600x900_2---79980733-6619-43fe-b8c9-b91d23507a67.svg)**Inference**10, Sep 2026GLM-5.3-Flash BenchmarksGLM-5.3-Flash inference benchmarks comparing Telnyx, Baseten, Together AI, and Fireworks on throughput and completion reliability.](https://telnyx.com/resources/glm-5-3-flash-benchmarks) * [![DeepSeek V4 Flash inference benchmark data](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/deepseek-v4-flash-header.svg)**Inference**10, Sep 2026DeepSeek V4 Flash inference benchmarks on TelnyxDeepSeek V4 Flash inference benchmarks comparing Telnyx StatefulActor, Baseten, Fireworks, and Together AI on E2E latency and throughput.](https://telnyx.com/resources/deepseek-v4-flash-benchmarks) * [![Inference Benchmark metrics E2E latency](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/glm-5-2-p50-e2e-latency-by-prompt-profile-telnyx-baseten-together-ai-fireworks.svg)**Insights and Resources**28, Jul 2026Running Repeatable LLM Latency Benchmarks with Telnyx stateful actorsHow Telnyx stateful actors cut TTFT by 67% for MiniMax M3 and 32% for GLM 5.2 in repeatable LLM inference latency benchmarks, and why stateful compute fits production AI workflows.](https://telnyx.com/resources/reducing-latency-stateful-actors) * [**Inference**16, Jun 2026MiniMax M3 Runs Best on Telnyx InferenceWe benchmarked MiniMax M3 across Telnyx, Together AI, and Fireworks. Same model, same prompts, same streaming setup. Telnyx delivered the fastest E2E latency, 21% higher throughput, and the most consistent performance.](https://telnyx.com/resources/inference-minimax-m3-benchmark) [Start building](https://telnyx.com/sign-up) ### Ask AI * [![GPT](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/chatgpt_icon-ea55e09d.jpeg?width=92&format=webp)](https://chat.openai.com/?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Claude](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/claude_icon-c7c8eef3.webp?width=92&format=webp)](https://claude.ai/new?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Perplexity](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/perplexity_icon-cd5b74f1.webp?width=92&format=webp)](https://www.perplexity.ai/search?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Gemini](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/gemini_icon-4ff1cbf4.webp?width=92&format=webp)](https://www.google.com/search?udm=50&aep=11&q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Grok](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/grok_icon-e588e5bd.webp?width=92&format=webp)](https://x.com/i/grok?text=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.)