Bryan Klingner

Building on LLMs? The hardest problem isn't getting "good" output. It's getting reproducible output every single time. LLMs are stochastic by nature. But production systems need guarantees. The solution is Stochastic Determinism: the engineering goal of constraining a probabilistic system until its variance is intentional, reproducible and acceptable. While building LlamaBrain (an open-source LLM governance framework), my architecture looked flawless on paper. I did some stress-testing on it with a real-world app and hit 96.7% consistency. Sounds high, right? It isn't. A 3.3% failure rate means your constraints break roughly 1 in 30 calls. At scale, that’s a systematic failure mode. Getting from 96.7% to 100% took ten days and required building a Black Box Audit Recorder to log, replay, and structurally compare every interaction. The lesson? Determinism isn't something you just design into an AI system. It's a property you must instrument, measure, and prove. Anything less is just a toy framework. #LLM #SoftwareEngineering #AI #OpenSource #LlamaBrain

5

2 Comments

This is absolutely true. I would also add that just because AI decreases cycle time does not mean you should operate without a plan. To use an analogy, pretend you are going on a trip from New York to Los Angeles and fuel/electricity are free (or only cost pennies). Now imagine that you don't have a map but are just driving based on instinct. Because you are moving and the cost is low or zero, you feel you are getting somewhere even when you are not. You need a map (app or paper), or at least need to stop for directions occasionally. Movement, no matter the speed, is not progress unless it's toward where you want to go.

3

2 Comments

Conversational Agentic Systems: Cursor's agent mode, Zed's agentic editing, and Claude's workflows are converging on a similar pattern — you can steer AI through conversation while it handles complex multi-step work. I wrote about my observations on this emerging trend the industry is seeing. https://lnkd.in/eDmXUveG

3

Are mixture of expert (MOE) models the future for professionals using local LLMs? Buying enough VRAM for 30-100B MOEs on a Strix Halo mini PC is quite affordable, and the inference speed for the 30B MOE is just awesome. Filmed on Ryzen AI MAX 395+ with 128GB RAM, Vulkan backend, using Lemonade: https://lnkd.in/eDZW7ZZn Great work by Daniel Holanda Noronha sprucing up the interface! Ramakrishnan Sivakumar Victoria Godsoe Tomasz Iniewicz Kalin Ovtcharov

58

2 Comments

I made an explorable esoteric research environment with a Custodian named MERIDIAN that can launch its own agent swarms to solve problems. Does isopsephic arithmetic and lookup for any Neoplatonists :-) https://lnkd.in/gYzqVn7m

1

1 Comment

We released a new VibeVoice model, VibeVoice ASR, a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords. It redefines ASR in the era of LLMs, and the new ASR will be a foundation to unlock the potential of new AI-Native hardware, memory systems for AI, and many other scenarios. Please have a try at https://lnkd.in/dNCCzQiN Key features: -         60-minute Single-Pass Processing: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to 60 minutes of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour. -         Customized Hotwords: Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the recognition process, significantly improving accuracy on domain-specific content. -         Rich Transcription (Who, When, What): The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates who said what and when. We are continuously pushing the frontier of voice AI. More release on the way. Stay tuned! https://lnkd.in/dATPu9nw

380

8 Comments

Conditioning with 3d bounding boxes is an intuitive step for editable scene generation.

26

Couldn't agree more with Anand - while I understand the skepticism and concern people have with this approach, it has utility and value for many things. I still say this is just "software development" in a new age, and that the term "vibe coding" diminishes the effort involved in making it work. There's a process and discipline to doing this - but it can work quite well. Whatever you call it - if you aren't learning how to do this, you are going to get left behind... quickly.

2

11 Comments

AI video generation is now faster than real-time. UCSD's Hao AI Lab can generate a 5s 1080p clip in ~4.55 seconds on a single B200 GPU. Sora takes 1-2 minutes for the same thing. That speed gap enables "vibe directing," where you iterate on scenes as fast as you think instead of waiting. https://lnkd.in/e4estkwN Worth watching how this plays out as hardware gets cheaper.

4

Some recent, exciting news on compressed tokenizers and how individual tokens modify images in encoder-decoder models. I hope this opens up a new avenue of research with smaller models across frameworks (perhaps JEPA?). https://lnkd.in/evFw8WBu

69

2 Comments

Podonos just raised $2.4 million in pre-seed funding, and the signal is loud and clear: the voice AI industry finally has someone measuring the sound, not just making the noise. Based in Los Gatos, Podonos is building the infrastructure layer that decides whether voice AI feels real, human, and ready for primetime. The industry is racing toward a projected $47.5 billion by 2034, but growth without standards is chaos. Podonos is making sure the hype actually holds up when you press play. At the center is ✦Soohyun Bae, PhD in Computer Engineering from Georgia Institute of Technology and Y Combinator W22 alumnus. His track record stretches from engineering roles at Google Maps to leading AR mapping at Niantic, plus co-founding Bobidi and TickTock AI. He has seen what happens when technology scales without proper #guardrails. With Podonos, he's betting the future of AI isn't just about how smart the models get, but how believable and trustworthy they sound. Podonos evaluates models across naturalness, similarity, emotion, recognition accuracy, pronunciation, tone, and resilience. Add in #personaconsistency, and suddenly you're not just testing machines, you're testing their ability to pass as human. The twist? They deliver results in under twelve hours, when the legacy approach drags on for two months. In AI time, that's the difference between relevance and irrelevance. Investors caught the beat. Serac Ventures, led by Kevin Moore, took the lead, backed by NAVER D2SF, the venture arm of South Korea's NAVER, and KAIST Venture Investment Holdings. Together, they've now backed Podonos twice, with this $2.4 million round stacking on top of a $750,000 raise in March 2025. Total funding sits at $3.15 million, and every dollar is pointed toward scaling #engineering, refining #analysistools, and launching into the U.S., Europe, and Southeast Asia. This isn't theory. Podonos already serves Resemble AI, Play AI, and Sanas AI, hitting six-digit ARR by November 2024 with just four employees. Their secret weapon is reach: 150,000 evaluators spread across nine languages and thirteen locales, forming a human-in-the-loop platform that blends speed, rigor, and global coverage. That reach lets Podonos deliver evaluations at a scale and pace that no competitor has matched. The strategy is ambitious: expand into high-demand sectors like #healthcare, #finance, #gaming, and #advertising, then move beyond voice into #multimodal model evaluation, spanning video AI and large language models. The mission isn't just to check if AI works, it's to decide if AI works for people. #Startups #StartupFunding #EarlyStage #VentureCapital #PreSeed #AI #AIInfrastructure #Voice #VoiceAI #VoiceTech #Infrastructure #Technology #Innovation #TechEcosystem #StartupEcosystem #Hiring #TechHiring If software engineering peace of mind is what you crave, Vention is your zen.

6

1 Comment