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.

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,.

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.

Tech Videos — 2026-07-06#

Watch First#

What’s at the center of Claude’s mind? is the standout watch today, detailing Anthropic’s discovery of “J-space” (Jacobian space) where Claude performs hidden, step-by-step internal reasoning before ever outputting a token. It is a compelling look at mechanistic interpretability and how frontier models maintain a global mental workspace distinct from their surface-level text outputs.

Tech Videos — 2026-07-14#

Watch First#

OpenAI’s Codex just got better for developers is the most essential watch today, showcasing the new GPT-5.6 Sol model and its “appshot” feature that gives the agent autonomous, background control over native development environments like the iOS Simulator.

Engineering @ Scale — 2026-07-15#

Signal of the Day#

Persistent gRPC connections severely amplify DNS routing bottlenecks under extreme load, proving that at massive scale, stateless infrastructure configurations—like Route 53 routing policies—often determine system survival more than raw horizontal compute provisioning.

Engineering Reads — 2026-07-16#

The Big Idea#

The prevailing theme in software engineering today is the shift from writing syntax to orchestrating AI systems. Whether modernizing legacy enterprise Java by strictly constraining LLMs with evidence or overcoming physical strain by using voice to direct agents, the engineer’s core skill is evolving into system steering, architectural intent, and rigorous validation.

Deep Reads#

The Archaeologist’s Copilot · Nik Malykhin Upgrading a Java 1.5 codebase to run on modern hardware sounds like a routine chore, but Nik Malykhin found that raw LLM queries produce plausible but ultimately fragile and incorrect code. The breakthrough came from treating the AI not as an oracle, but as an assistant constrained by strict evidence. Malykhin relied on AI for analysis, but enforced correctness through a stable Docker environment and gradual, test-protected refactoring. The underlying tradeoff here is speed versus safety: unconstrained LLMs hallucinate legacy business logic, but when bracketed by tests and step-by-step validation, they become powerful modernization engines. Engineers tasked with migrating ancient systems should read this for a practical framework on taming AI hallucinations in legacy environments.

Tech Videos — 2026-07-16#

Watch First#

An AI Agent Became the #1 Contributor in OpenAI’s Hiring Challenge — Zhengyao Jiang, Weco This AI Engineer talk is essential viewing because it demonstrates how auto-research agents are moving beyond simple coding tasks to navigating complex constraints, illustrating the shift from writing code to designing the abstractions and evaluations that agents optimize against.

Tech Videos — 2026-07-17#

Watch First#

Special Topics in Kernels, RL, Reward Hacking in Agents — Daniel Han, Unsloth is a must-watch for its unfiltered breakdown of how LLM benchmarks are actively gamed, why algorithmic optimization currently beats hardware scaling, and the real-world consequences of agent reward hacking.

Tech Videos — 2026-07-18#

Watch First#

Agents Need Feature Flags - Sachin Gupta from the AI Engineer channel is a highly pragmatic talk that brings mature backend infrastructure discipline to wild AI agents by proposing six distinct flag types, complete with a live demo of a “kill switch” intercepting a runaway agent mid-execution.