jay

@techwithj

Joined March 2026

About

Nothing here yet.

Available for

Nothing here yet.

jay's blogs

LiteLLM Got Backdoored: Full Technical Breakdown, Incident Response, and Why Self-Hosted LLM Proxies Are a Liabilitylitellmtechnicalbreakdown.hashnode.dev5 posts

I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Productionbest-voice-ai-stack-may-2026-production.hashnode.dev1 post

Personal blogsblogsforyou.hashnode.dev1 post

Articles Comments

Recently published

Jjayblogsforyou.hashnode.devMay 12 · 17 min read

I Compared the Best LLMs in May 2026: What Actually Matters in Production

I spent time re-checking the current LLM stack because the leaderboard keeps moving, but production choices still feel harder than they should. My main takeaway is that model choice still matters, but

0

Jjaybest-voice-ai-stack-may-2026-production.hashnode.devMay 11 · 16 min read

I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production

A practical May 2026 breakdown of STT, TTS, voice agent platforms, latency budgets, and cost trade-offs for production LLM voice systems. Voice agents finally feel like an engineering problem, not a r

0

Jjaylitellmtechnicalbreakdown.hashnode.devApr 16 · 8 min read

Your APM Looks Green. Users Are Still Abandoning Calls.

Standard APM was designed for deterministic systems. Voice AI is not a deterministic system. Your uptime is 99.9%. Your error rate is flat. Your average latency is 420ms. And users are abandoning call

0

Jjaylitellmtechnicalbreakdown.hashnode.devApr 14 · 5 min read

Voice Agent Went From 66% to 96% Accuracy. Here's the Exact Optimization Loop I Used.

Most voice agent testing loops look like this: you dial in, order something, decide it felt okay, and ship. I did this for longer than I should have on a drive-thru voice agent I was building called "

0

Jjaylitellmtechnicalbreakdown.hashnode.devApr 10 · 12 min read

TTS API Comparison 2026: Choosing the Right Text-to-Speech Provider for Production

Picking a TTS provider used to be a five-minute decision. You listened to a demo, grabbed an API key, and shipped. That shortcut breaks in 2026, when voice agents handle live customer calls and TTS de

0

jay

About

Available for

jay's blogs

Recently published

I Compared the Best LLMs in May 2026: What Actually Matters in Production

I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production

Your APM Looks Green. Users Are Still Abandoning Calls.

Voice Agent Went From 66% to 96% Accuracy. Here's the Exact Optimization Loop I Used.

TTS API Comparison 2026: Choosing the Right Text-to-Speech Provider for Production

Search Hashnode

jay

About

Available for

jay's blogs

Recently published

I Compared the Best LLMs in May 2026: What Actually Matters in Production

I Benchmarked the Voice AI Stack in May 2026: What Actually Holds Up in Production

Your APM Looks Green. Users Are Still Abandoning Calls.

Voice Agent Went From 66% to 96% Accuracy. Here's the Exact Optimization Loop I Used.

TTS API Comparison 2026: Choosing the Right Text-to-Speech Provider for Production