Sources

Tech Videos — 2026-06-18#

Watch First#

The Production AI Playbook: Deploying Agents at Enterprise Scale — Sandipan Bhaumik, Databricks is the single most valuable watch today because it skips the agent hype to deliver a rigorous, production-tested framework for observability, behavioral evaluation, and multi-agent orchestration.

2026-06-19

Youtube, Tech

Artificial Intelligence, Developer Tools, Machine Learning, Software Engineering

Sources

Tech Videos — 2026-06-19#

Watch First#

Dwarkesh Patel’s The data black hole at the center of AI is today’s standout watch because it rigorously unpacks the massive sample efficiency gap between human learning and LLMs, demonstrating why scaling parameters alone won’t solve the problem.

2026-06-23

Youtube, Tech

Artificial Intelligence, Developer Tools, Ai-Agents, Machine Learning

Sources

Tech Videos — 2026-06-23#

Watch First#

Closer to the Material, Ryo Lu | Compile 26 from Cursor is a highly recommended watch that rejects the “black box” slot-machine model of AI dev tools in favor of a transparent “Glass” UI paradigm. It offers a sharp, philosophical architecture discussion on why exposing an agent’s planning, state, and tool execution is necessary to preserve engineering judgment and taste as software generation costs approach zero.

2026-06-24

News, Tech

Artificial Intelligence, Cloud Architecture, System Design, Machine Learning

Sources

Engineering @ Scale — 2026-06-24#

Signal of the Day#

Microsoft’s Talos pipeline consciously traded maximum algorithmic recall for extreme specificity—surfacing just 1.3 candidate genomic variants per patient—to respect the severe operational bottleneck of human expert review time. This highlights a crucial architectural principle for deploying AI at scale: optimizing models for peak theoretical accuracy is counterproductive if the resulting false-positive rate overwhelms the human-in-the-loop workflow.

2026-06-25

Youtube, Tech

Ai-Agents, Developer Tools, Machine Learning, Hardware, Cloud Infrastructure

Sources

Tech Videos — 2026-06-25#

Watch First#

The Miranda Hypothesis: How Hamilton Poisoned Persona Evals is a rigorous, must-watch takedown of current LLM benchmarks, demonstrating that persona evaluations measure fluency and pop-culture composites rather than historical accuracy.

2026-06-25

News, Tech

Ai-Agents, Cloud Infrastructure, Machine Learning, Software Architecture

Sources

Engineering @ Scale — 2026-06-25#

Signal of the Day#

The “lost in the middle” context window problem is not just a training artifact to be smoothed out with more compute, but a fundamental geometric property of transformer architecture where causal mask primacy biases and position encoding recency biases cancel out in the middle. To build reliable agentic systems, engineering teams must stop relying on massive context windows as stateful databases, and instead treat the LLM as an ephemeral pipe by externalizing state to disk and forcing fresh reads at the point of action.

2026-06-26

Youtube, Tech

Ai-Agents, Developer Tools, Machine Learning, Cloud Computing

Sources

Tech Videos — 2026-06-26#

Watch First#

Stop Writing Tone Instructions. Layer Them. Isadora Martin-Dye delivers a production-tested masterclass on managing AI agents, arguing against standard prompt engineering in favor of a rigid 4-layer architectural stack that ends in a deterministic, non-LLM veto.

2026-06-29

Youtube, Tech

Ai-Agents, Developer Tools, Infrastructure, Machine Learning

Sources

Tech Videos — 2026-06-29#

Watch First#

Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs (AI Engineer). This is an excellent, pragmatic breakdown of why probabilistic agentic models break when run on deterministic infrastructure, focusing heavily on how recursive reasoning loops and uncontrolled retries trigger massive compute incidents,.

2026-07-01

Youtube, Tech

Ai-Agents, Developer Tools, Machine Learning, Infrastructure, Software Engineering

Sources

Tech Videos — 2026-07-01#

Watch First#

Continual Learning for Long-Running Agents: Agents That Keep Getting Better from NVIDIA Developer is a pragmatic must-watch for anyone building AI workflows. It cuts through the “1 million token” hype to address real-world context rot, arguing that long-running agents shouldn’t be fed massive walls of text, but rather handle context programmatically via recursive sub-agent delegation.