Inference Time Tactics

About Inference Time Tactics

A show about AI economics and the cost of thinking. From Neurometric, on the tokenminning movement, the discipline emerging to make every unit of AI work cheaper, faster, and more reliable.

Publisher

NeuroMetric AI

Category

technology

Language

en

Explicit

No

First episode

1 Aug 2025

Latest episode

5 Aug 2026

Latest episodes

4 of 17 episodes have a transcript.

1. 

   5 Aug 2026TRANSCRIPT

   TMax: Closing the Frontier Gap With Open Data

   Calvin Cooper interviews Yash Sharma, Head of AI Research at Neurometric AI, about TMax, an open dataset and training recipe that significantly boosts small AI models' performance on complex tasks.

2. 

   10 Jul 2026TRANSCRIPT

   From Tokenmaxxing to Tokenminning: The Case for Token Engineering

   Host Calvin Cooper interviews Neurometric CEO Rob May about the emerging discipline of token engineering and its critical role for AI companies.

3. 

   16 Jun 2026TRANSCRIPT

   Automating the SLM Development Loop: Inside the Pioneer Agent Paper with Yash Sharma of Neurometric AI

   Host Calvin Cooper interviews Yash Sharma of Neurometric AI about the Pioneer Agent paper, revealing how an AI agent automates the entire small language model development loop beyond just training.

4. 

   29 May 2026TRANSCRIPT

   SLMs Beat GPT-4o: How AI Is Being Used in Hiring with Fletcher Wimbush, CEO of Discovered AI

   Host Calvin Cooper interviews Fletcher Wimbush, CEO of Discovered AI, about how fine-tuned small language models outperform GPT-4o in hiring by focusing on behavioral science and integrity.

5. 

   9 Mar 2026

   Voice Intelligence at Scale: From Call of Duty to Fraud Detection with Modulate AI

   Every day billions of voice conversations happen across games, customer service calls, and financial transactions. Almost none of them are understood by machines. In this episode of Inference Time Tactics, Calvin Cooper and Yash Sharma sit down with Carter Huffman, CTO and co founder of Modulate, to explore the AI systems that can finally understand voice conversations in real time. Modulate’s model Velma 2.0 powers voice intelligence across industries. From moderating voice chat in games like Call of Duty to detecting fraud in financial calls and analyzing customer support conversations, their system uses ensembles of specialized models to capture tone, intent, emotion, and conversational dynamics. Instead of relying on giant foundation models, Velma orchestrates over 100 specialized models to deliver higher accuracy at dramatically lower cost. We talked about: The challenge of processing a trillion hours of annual global voice traffic. Scaling real-time moderation for massive platforms like Call of Duty. Capturing nuance, tone, and sarcasm beyond basic text transcripts. Ensemble architecture utilizing over 100 specialized models. Orchestration layers that trim compute costs by identifying optimal model subsets. Achieving order-of-magnitude cost savings compared to large foundational models. Applying "exploration vs. exploitation" optimization to shifting conversation data. Future development of "context graphs" to map participant intent and causality. Resources Mentioned: NeuroMetric Audio Leaderboard: https://leaderboard.neurometric.ai/?leaderboard=audio Connect with Modulate:Website: https://www.modulate.ai/ LinkedIn: https://www.linkedin.com/in/carter-huffman-a9aba05b Velma: https://www.modulate.ai/velma Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Yash Sharma https://x.com/yash_j_sharma https://www.linkedin.com/in/yashjsharma/

6. 

   16 Jan 2026

   From GPU Scarcity to GPU Waste: Solving the Utilization Crisis

   In this episode of Inference Time Tactics, Cooper and Byron sit down with Charlie and Anil from Rapt AI to tackle one of the industry's most expensive problems: GPU underutilization. With half a trillion dollars invested in GPU infrastructure running at just 20-30% utilization, Rapt AI is building AI-powered orchestration that automatically analyzes workloads and matches them to the right compute resources—no guesswork required. We talked about: Why half a trillion dollars in GPU infrastructure runs at only 20-30% utilization—and how a 5% drop costs $200,000 per $2M investment. How Rapt AI's platform continuously analyzes workloads and auto-optimizes GPU allocation, letting customers run 4-14 models per GPU. Real results: moving workloads from H100s to A100s at 40% of the cost, and reducing GPU footprints from 184 to under 50 while improving performance. Why 2026 becomes the year of inference as agentic workloads create unprecedented infrastructure chaos. The shift from supply problems to optimization problems—and why abstraction layers matter across multi-vendor environments. Power as the next crisis: tokens-per-watt emerging as the critical metric alongside tokens-per-dollar. How intelligent orchestration frees up data scientists and ML ops teams from infrastructure tuning to focus on AI innovation. Connect with Rapt AI:Website: https://www.rapt.ai/ LinkedIn (Anil Ravindranath): https://www.linkedin.com/in/anilravindranath LinkedIn (Charlie Leeming): https://www.linkedin.com/in/charlieleeming/ Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

7. 

   22 Dec 2025

   Lessons from the Leading Edge: What 420 AI Deployments Reveal About Enterprise Success

   In this episode of Inference Time Tactics, Rob, Cooper, and Byron sit down with Shawn Rogers, CEO of BARC US to unpack fresh data from 421 organizations actively deploying AI in production. Shawn shares what separates the 20% of AI leaders from everyone else, why cost surprises are hitting harder than expected, and how the pressure to "just do AI" is causing companies to skip critical foundations—often to their detriment. We talked about: Why multi-model strategies and small language models are becoming essential for enterprise AI. The seven foundational areas that help AI leaders deploy twice as many projects as everyone else. Why 51% of deployments face unexpected cost overruns—and which expenses hit hardest. Data quality jumping to the #1 challenge, affecting 44% of production deployments. The IT satisfaction paradox: top resource at the start, lowest satisfaction scores at scale. How responsible AI priorities shifted as human-in-the-loop dropped from 36% to 21%. Resources Mentioned: Lessons from the Leading Edge: Successful Delivery of AI/GenAI https://barc.com/research/successful-ai-genai-delivery/ Connect with BARC:Website: https://barc.com/ LinkedIn (Shawn Rogers): https://www.linkedin.com/in/shawnrogers/ Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

8. 

   16 Dec 2025

   The Thinking Algorithm Leaderboard: Why No Single Model Wins

   In this episode of Inference Time Tactics, Cooper and Byron break down NeuroMetric's Thinking Algorithm Leaderboard and what it reveals about building production-ready AI agents. They share why prompt engineering with a single model won't cut it for enterprise use cases, explore the impact of inference-time compute strategies, and discuss what they learned from testing 10 models across real CRM tasks—from surprising token inefficiency to catastrophic failures in SQL generation. We talked about: Why NeuroMetric built the first leaderboard combining models with inference-time compute strategies. How Salesforce's CRMArena-Pro reflects real multi-step business tasks better than pure reasoning benchmarks. The jagged frontier: no single model or technique dominates across all tasks. Why GPT 20B was surprisingly token inefficient—twice as slow as GPT 120B for similar accuracy. How GPT-5 nano's conversational style broke SQL generation tasks completely. Trading accuracy for speed: two-model ensembles versus five, and saving 20+ seconds per task. Throughput constraints as a hidden bottleneck when scaling to production volumes. Future directions: LLM-guided search, task clustering, and compression to specialized small models. Resources Mentioned: CRMArena-Pro from Saleforce: https://www.salesforce.com/blog/crmarena-pro/ Thinking Algorithm Leaderboard: https://leaderboard.neurometric.ai/ Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Guest/s: Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

9. 

   5 Nov 2025

   Benchmarking Generalization: How AI Learns Beyond Training Data

   In this episode of Inference Time Tactics, Rob and Cooper from Neurometric sit down with Yash Sharma, an AI researcher whose work is reshaping how we understand model generalization. Yash recently completed his PhD at the Max Planck Institute for Intelligent Systems and has held research roles at Google Brain, Meta AI, Amazon, Borealis AI, and IBM Research. His studies on compositional generalization, adversarial robustness, and long-tail benchmarks reveal when and why models succeed—or fail—at reasoning beyond their training data. If you’re designing inference-time systems, building agents that need reliability, or just want to understand what “generalization” actually means in practice, this conversation bridges deep theory with actionable insight—clear, technical, and strategically grounded. Key Topics What it really means for AI systems to generalize beyond their training data Why large language models still fail in novel or unpredictable scenarios How inference-time compute can both amplify and reveal generalization limits What these limits mean for building reliable, agentic AI systems How to benchmark generalization in real-world settings Yash’s “Let It Wag!” benchmark for testing long-tail and under-represented concepts Why genuine scientific breakthroughs (like curing cancer) require more than scaling test-time compute Connect with Yash Sharma: Yash Sharma Let It Wag! Benchmark Paper: Pretraining Frequency Predicts Compositional Generalization of CLIP (NeurIPS 2024 Workshop) Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc

10. 

    3 Oct 2025

    Solving the Cold Start Problem in AI Inference

    In this episode of Inference Time Tactics, Rob, Cooper, and Byron sit down with Prashanth Velidandi, co-founder of InferX, to explore how serverless inference is tackling the AI “cold start problem.” They dig into why 90% of the model lifecycle happens at inference—not training—and how cold starts and idle GPUs are crippling efficiency. Prashanth explains InferX’s snapshot technology, what it takes to deliver sub-second cold starts, and why inference infrastructure—not just models—will define the next era of AI. We talked about: Why inference represents 90% of the model lifecycle, compared to the training focus most of the industry has. How cold starts and idle GPUs create massive inefficiencies in AI infrastructure. InferX’s snapshot technology that enables sub-second model loading and higher GPU utilization. The challenges of explaining and selling deeply technical infrastructure to the market. Why enterprises care about inference efficiency, cost, and reliability more than model size. How serverless inference abstracts away infrastructure complexity for developers. The coming explosion of multi-agent systems and billions of specialized models. Why sustainable innovation in AI will come from inference infrastructure. Connect with InferX Prashanth Velidandi https://inferx.net https://x.com/pmv_inferx https://www.linkedin.com/in/prashanth-velidandi-98629b115 Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

11. 

    30 Sept 2025

    From MIT Decoding Research to Today’s Inference Tradeoffs

    Check out the latest episode of Inference Time Tactics. Our guest is Pawan Deshpande, founder, product leader, and angel investor in companies like Anthropic and Toast, with roles at Google, Scale AI and Domino Data Lab. Hosts Rob May & Calvin Cooper sit down with Pawan to cover: Early MIT NLP research applied to today’s inference-time tradeoffs How to evaluate enterprise agents in practice Training data plus inference filtering in real deployments Open source adoption realities in the enterprise Where durable value lives in the stack Connect with Pawan Deshpande Website: https://pawandeshpande.com/Academic / Research Works & ThesisDecoding Algorithms for Complex Natural Language Tasks (MIT thesis, 2007)Randomized Decoding for Selection-and-Ordering Problems Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc

12. 

    22 Sept 2025

    Drag, Drop, and Deploy: Rethinking How We Build AI Systems

    In this episode of Inference Time Tactics, Rob, Cooper, Byron, and Dave share product updates for Neurometric’s Inference Time Compute Studio and what they reveal about the shift from single models to full AI systems. They discuss why wiring models together at scale is so challenging, how a drag-and-drop interface can make experimenting with inference strategies easier, and why open source, benchmarking, and community feedback are key to building the next generation of composable AI systems. We talked about: Why AI is shifting from single models to full systems and what that means for builders. The challenges of wiring multiple models together at scale and running them in production. How Neurometric’s drag-and-drop interface simplifies testing inference strategies without code. Why open-source models are becoming increasingly competitive with commercial solutions. The lack of standardization in AI stacks and why the industry still feels like the “early web” era. How inference-time compute can balance performance, cost, and latency across different tasks. Why benchmarks alone are insufficient and how domain-specific evaluations can fill the gap. The role of community feedback in shaping priorities for benchmarks and new primitives. Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Guest/s: Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith Dave Rauchwerk https://x.com/elevenarms https://www.linkedin.com/in/dave-rauchwerk-0ba82822

13. 

    8 Sept 2025

    Beyond Vibe Testing: Smarter Eval for Agentic AI

    In this episode of Inference Time Tactics, Rob, Cooper, and Byron explore Salesforce’s CRMArena-Pro benchmark and what it reveals about the limits of enterprise AI agents. They share why benchmark scores often fail in production, how inference-time tactics like best-of-N can improve reliability, and what NeuroMetric is building to make eval easier—from an ITC Test Engine to a drag-and-drop interface for rapid visualization and experimentation. We talked about: Why Salesforce’s CRMArena-Pro benchmark highlights the gap between lab benchmarks and real-world agent reliability. How leading models perform inconsistently across single-turn and multi-turn enterprise tasks. Why benchmark scores are weak predictors of operational success in production. The role of inference-time tactics in reducing variance and improving stability. NeuroMetric’s new platform: ITC Test Engine and drag-and-drop interface for experimentation. Challenges in building agentic systems, from database integration to managing multi-prompt complexity. Why large language models’ stochastic nature conflicts with business demands for reliability. Latency, cost, and rate limits as major bottlenecks in scaling agentic workflows. The limits of “vibe testing” and why rigorous evaluation frameworks are essential. How Google’s Stacks tool speeds up evaluation with LLM-as-judge, and why it still falls short for enterprise needs. Resources Mentioned: CRMArena-Pro from Saleforce: https://www.salesforce.com/blog/crmarena-pro/ Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Guest/s: Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

14. 

    30 Aug 2025

    GPT-5, The $100B Gap, and The Economics of Inference

    In this episode of Inference Time Tactics, Rob and Cooper unpack the launch of GPT 5.0 and what OpenAI’s new routing layer signals about the shifting AI landscape. They explore the tradeoffs of cost, latency, and accuracy, zoom out to programmable inference in an agent-driven world, and track the ripple effects on chips, data centers, and energy use. We talked about: Why GPT 5.0’s launch felt more like refinement than a revolution in AI progress. How OpenAI’s new routing layer reframes the race around inference control. The tradeoffs routing enables between cost, latency, and accuracy across models. Why the “one model to rule them all” view is giving way to multi-model orchestration. The strategic role of programmable inference in an agent-driven world. How router companies are becoming a strategic layer in the AI technology stack. The impact of inference compute on chips, accelerators, and data center design. Why energy use at scale is driving a push for more efficient AI systems. Why inference optimization may be the next big competitive edge. Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc

15. 

    18 Aug 2025

    When AI Overthinks: Lessons from the Illusion of Thinking Paper

    In this episode of Inference Time Tactics, Rob, Cooper, and CTO Byron unpack Apple’s “Illusion of Thinking” paper—why it split the AI community, what it reveals about reasoning model limits, and how hidden thinking traces shape performance. They share insights from building an open-source tool to reproduce the study, explain why models loop, overthink, or stall, and outline what it will take to build more reliable reasoning systems for real-world use. We talked about: Why Apple’s Illusion of Thinking paper sparked heated debate in the AI community. How reasoning models work, including hidden “thinking” phases and token budget limits. Key findings on when reasoning improves results, when it degrades them, and where it stalls. Reasons models loop, overthink, or abandon tasks. Building an open-source tool to replicate the study and test local reasoning models. What real-time reasoning traces reveal about model behavior and limits. Challenges in scoring reasoning quality and treating “I don’t know” as a valid output. Why reasoning models must be matched carefully to specific tasks. The ongoing debate over scaling vs. new architectures for advancing reasoning. Developing a benchmarking platform to help enterprises choose models for IP-sensitive applications. Resources Mentioned: Illusion of Thinking Paper https://machinelearning.apple.com/research/illusion-of-thinking Neurometric Illusion of Thinking Tool https://github.com/NeurometricAI/illusion-of-thinking Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Guest/s: Byron Galbraith https://x.com/bgalbraith https://www.linkedin.com/in/byrongalbraith

16. 

    12 Aug 2025

    The Strategic Trade Offs Behind Inference Time Compute Decisions

    In this episode of Inference Time Tactics, Rob and Cooper dig into the strategic trade-offs driving a major shift in AI: why some enterprises start with closed models like OpenAI or Anthropic, then move to open-source stacks. The team breaks down the challenges of switching and how inference-time compute is becoming a competitive differentiator. They also unpack why pricing is shifting, how governance will evolve for this new layer, and what Rob learned from reviewing 250 research papers on reasoning algorithms. We talked about: Insights from reviewing 250 research papers on reasoning algorithms. Why enterprises start with closed models like OpenAI or Anthropic before moving to open-source stacks. Challenges of switching stacks, including model fragmentation, capability gaps, and hardware choices. Cost-performance trade-offs when choosing inference architectures. How inference-time configuration can become a competitive differentiator. The role of pricing shifts and vendor lock-in in AI adoption. Emerging governance considerations for inference workflows. The growing variety and complexity of inference-time techniques.. Benchmarking challenges for multi-step and reasoning tasks. Why the lack of best practices makes inference optimization harder to operationalize. Connect with Neurometric:Website: https://www.neurometric.ai/ Substack: https://neurometric.substack.com/ X: https://x.com/neurometric/ Bluesky: https://bsky.app/profile/neurometric.bsky.social Hosts: Rob May https://x.com/robmay https://www.linkedin.com/in/robmay Calvin Cooper https://x.com/cooper_nyc_ https://www.linkedin.com/in/coopernyc Comment end

17. 

    1 Aug 2025

    Why Inference Time Compute Is the Future of AI

    Welcome to the very first episode of Inference Time Tactics — the podcast for builders, researchers, and engineers pushing the limits of AI performance. In this kickoff conversation, hosts Rob May and Cooper (co-founders of Neurometric AI) break down why inference time compute is emerging as the third scaling law of AI — and why it matters more than ever. They unpack: What “inference time compute” really means (and how it differs from training and fine-tuning) Why reasoning algorithms like best-of-N, chain of thought, and beam search are reshaping performance How recent research — and OpenAI’s 2024 reasoning model — sparked an explosion of interest The challenge of reliability (“three nines” and beyond) in multi-step agent workflows Why open-source models may win big, and where inference fits at the edge This is a technical, tactical deep-dive — but without the heavy math. If you’re building the next generation of AI systems, or just want to understand where the field is really headed, this episode is your starting point. 🔗 Learn more at neurometric.ai

Who has been a guest on Inference Time Tactics

Names identified in recent episode analyses. Showing up to five guests.

• Yash Sharma
• Rob May
• Fletcher Wimbush

Contact Inference Time Tactics

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.

Questions about Inference Time Tactics