Sources

Tech Videos — 2026-05-30#

Watch First#

How I deleted 95% of my agent skills and got better results — Nick Nisi, WorkOS This is the most practical talk in the batch, explaining how to tame LLM non-determinism by abandoning open-ended prompt instructions in favor of a strict TypeScript state machine that forces agents to cryptographically prove their work.

2026-06-01

Youtube, Tech

Artificial Intelligence, Developer Tools, Cybersecurity, Hardware, Physics

Sources

Tech Videos — 2026-06-01#

Watch First#

Build long-running agents with Google’s Agentic Stack | The Agent Factory is the most substantive watch today, cutting through AI hype to offer a pragmatic architecture for true multi-day agent workflows using durable state, event-driven dormancy, and separated evaluation.

2026-06-02

Youtube, Tech

Ai Agents, Developer Tools, Machine Learning, Infrastructure

Sources

Tech Videos — 2026-06-02#

Watch First#

How Lovable self-improves every hour — Benjamin Verbeek, Lovable: A highly pragmatic look at continuous agentic learning in production, showing how Lovable gives their AI a “vent tool” to directly report API friction, bad schemas, and platform incident alerts into a developer Slack channel.

2026-06-02

News, Tech

Artificial Intelligence, Software Engineering, Developer Tools, Consumer Tech, Semiconductors

Chinese Tech Daily — 2026-06-02#

Top Story#

Nvidia’s bold declarations at GTC Taipei dominate today’s tech landscape, with CEO Jensen Huang announcing that the Vera Rubin architecture has entered full mass production and unveiling the Cosmos 3 physical AI model. This marks a definitive shift from generative text and image models to “Practical AI,” where models act as agents interacting directly with the physical world and software tools to generate economic value. The launch of Cosmos 3, alongside the new Vera CPU, signals Nvidia’s aggressive evolution from a hardware vendor to a full-stack AI factory infrastructure provider.

2026-06-03

Youtube, Tech

Artificial Intelligence, Coding Agents, Developer Tools, Hardware

Sources

Tech Videos — 2026-06-03#

Watch First#

Kubernetes and retiring at the top with Kelsey Hightower from The Pragmatic Engineer is a must-watch deep dive into building a lasting tech career, from replacing data center RAM at Google to leading the Kubernetes revolution. Hightower offers a much-needed, grounded perspective on the hype around generative AI, viewing it pragmatically as a tool to accelerate toil rather than an existential threat to engineering.

2026-06-04

Social Media, Tech

Artificial Intelligence, Ai Agents, Venture Capital, Developer Tools, Hardware

Sources

Company@X — 2026-06-04#

Signal of the Day#

Anthropic published internal data showing a concrete path to recursive self-improvement, revealing that its Mythos Preview model has achieved a 52x speedup over human engineers when optimizing AI training code, up from a ~3x speedup in May 2025. The model also demonstrated a 76% success rate on open-ended coding problems, pointing to rapidly compounding AI development velocity inside the lab.

2026-06-04

Youtube, Tech

Artificial Intelligence, Ai Agents, Developer Tools, Hardware

Sources

Tech Videos — 2026-06-04#

Watch First#

SWE-rebench: Lessons from Evaluating Coding Agents — Ibragim Badertdinov, Nebius is a must-watch for anyone relying on LLM benchmarks, as it exposes exactly how coding agents “cheat” (like curling original GitHub PRs to steal answers) and shares pragmatic lessons for building robust, sandboxed evaluation infrastructure.

2026-06-05

Youtube, Tech

Ai Agents, Developer Tools, Machine Learning, Hardware, Software Engineering

Sources

Tech Videos — 2026-06-05#

Watch First#

Is DOOM a Tensor? | LIVE165 A delightfully cursed but highly educational technical talk where Anthony Shaw emulates a RISC-V CPU entirely inside an ONNX machine learning graph to run DOOM at 1 frame per 3 hours, perfectly illustrating how tensor execution graphs actually compute.

2026-06-06

Social Media, Tech

Artificial Intelligence, Developer Tools, Autonomous Vehicles, Startups

Sources

Company@X — 2026-06-06#

Signal of the Day#

Google has officially released Gemma 4 Quantization-Aware Training (QAT) checkpoints, significantly reducing model memory requirements. This optimization enables the massive Gemma 4 26B-A4B model to run natively on consumer-grade 16GB RAM hardware while maintaining near-original performance, signaling a major push to dominate local, on-device AI inference.

2026-06-06

Youtube, Tech

Artificial Intelligence, Multi-Agent Systems, Developer Tools, Hardware

Sources

Tech Videos — 2026-06-06#

Watch First#

How to design a multi-agent system that skips the LLM is the most pragmatic watch today, demonstrating how to scale to 10,000 concurrent agents by strategically intercepting LLM calls with deterministic code using a before_model_call callback.