No slides, no hype. I teach by building live on YouTube and X: AI agents, local models, and AI workflows, mistakes included. Join live and ask questions in chat, catch the replays on YouTube, and follow on X for the latest AI updates.
people trained through talks, workshops, and mentoring
2.2k+
GitHub stars on the open-source tools I teach with
25+
years shipping software, the context behind every video
Workshops & talks
Bring an AI workshop to your school or organization.
The same way I teach on the livestreams, run for your students, faculty, or team: hands-on sessions on AI Agents, Local Models, and AI Workflows, in plain language. Online via Zoom, with on-site options on request.
The Abu Dhabi Media Office said (Nov 2) that Crown Prince Sheikh Khaled bin Mohamed bin Zayed Al Nahyan met OpenAI CEO Sam Altman and witnessed four agreements between Abu Dhabi entities and OpenAI. ADNOC, G42’s Inception42, and OpenAI signed an agreement the office calls the first in the energy sector to deploy OpenAI’s frontier technology, using OpenAI’s GPT models on in-country inference infrastructure in the UAE. Abu Dhabi Government and OpenAI launched a Machine-Readable Government initiative that turns a defined set of policies and regulations into machine-readable form so AI systems can assist officials with routine compliance checks, including permits and certificates. Each assessment is traceable to the governing rule, and officials keep the final decision. The Department of Government Enablement leads it. The first pilot is already in production with the Abu Dhabi Agriculture and Food Safety Authority on food imports, with model computation on GPUs in UAE data centers. Mubadala, Inception42, and OpenAI signed an agreement to apply AI to investment analysis, opportunity identification, and risk assessment. Inception42 and OpenAI also signed a five-year agreement to support frontier AI in UAE government, enterprise, and education. Altman said Abu Dhabi and the UAE are setting a standard for AI integration in the public and private sectors. Distinct from OpenAI’s separate fundraising reports.
Meituan’s LongCat team introduced LongCat-2.5, a native multimodal model for long-horizon agent tasks, with 1.6 trillion total parameters and about 48 billion activated per token. The technical post is dated November 1. Meituan’s newsroom and the LongCat API changelog both list the model as available on November 2. It builds on LongCat-2.0 with stronger visual understanding and agentic coding for complex codebases, full-project builds, visual coding, design, and 3D tasks. Visual inputs are multi-level discrete tokens in the same stream as text. LongCat says long-context training and W4A4 inference are optimized for domestic AI accelerators. In its online stress tests, 4-bit expert weights and activations improved prefill throughput 43.3% and decode throughput 42.77% versus its W8A8 INT8 baseline, and cut time to first token 15.91% and time per output token 19.72%. On LongCat’s own table, with thinking on, LongCat-2.5 scores 88.4 on Terminal-Bench v2.1 and 91.9 on BrowseComp. Comparison scores marked with an asterisk are taken from public reports, LongCat says; the rest of the comparison runs are its own. The API changelog says the model works with Claude Code, Codex, Hermes, and other agent harnesses. Those scores are LongCat’s. Distinct from the LongCat-2.0 release.
OpenAI said (Nov 2) it is launching Grid Protectors, a program to arrange for future compute campuses to reduce electricity demand when the grid is under strain, working with utilities, regulators, and policymakers. How much demand can be reduced, how quickly, and for how long will differ by site. OpenAI also says campuses may supply power from on-site generation or storage where equipment and local rules allow. For the planned Effingham County, Georgia campus, OpenAI says it has committed to pay the full infrastructure and electric-service costs, and that its Georgia Power agreement includes up to 1,000 megawatts of flexible demand response, which OpenAI equates to the average demand of about 700,000 households. OpenAI says Georgia Power projects about $950 million in annual customer savings beginning in 2029 from its portfolio of large-load agreements and expected growth, including Project Camellia, and at least $15 a month for a typical residential customer using 1,000 kilowatt-hours. OpenAI cites a projection that U.S. data center capacity will exceed 100 gigawatts by 2030. The campus is still in development, and OpenAI says flexibility does not replace new supply and transmission. Those savings figures are as OpenAI presents Georgia Power’s estimates. Distinct from the July Project Camellia announcement.
Source: OpenAI
Updated November 2, 2026
What I teach: AI Agents, Local Models & AI Workflows
AI Agents
Autonomous agents with memory, tools, and skills that do the work, not just chat about it.
I teach AI Agents, Local Models, and AI Workflows to people who want to use AI, not just read about it. Before the channel: senior engineering roles at Standard Chartered Bank and Ohmyhome (Nasdaq), then a run of AI products built and shipped end to end. That's why every video, talk, and post is grounded in what actually ships.
Livestreams AI builds on YouTube and X
Speaker at NTU Singapore, PSIA, and DICT Philippines
300+ trained through workshops and mentoring
Open-source maintainer: Codex orchestrator, Local Evals, Agent Monitor
Subscribe on YouTube for the next livestream and follow on X for the latest AI updates. Want a workshop for your school or organization, or help with a product? Book a call.
