~/conference

WhatTheStack 2026

date:2026-09-14..2026-09-19
location:Skopje, North Macedonia

software engineers, AI and machine learning engineers, frontend developers, platform engineers, observability engineers, security engineers, engineering managers

local model inference without NVIDIA; LLM internals and context windows; agent memory and caching; model quantization and GGUF; AI-assisted code generation agents; observability as a product with SLOs; Angular integrations for AI and WebMCP; TypeScript operator overloading layer; portable GPU kernel compilation (tinygrad to Metal); AI deployment in hospitals; graph algorithms for voting analysis; performant TypeScript shaders

titleauthorlength
Legacy in IT: Breaking Stereotypes, Understanding Reality, and Embracing the UncoolGoran David30m
Argues that “legacy” is often misused and gives concrete evidence: COBOL handles ~80–95% of US ATM/card transactions, governments and transit systems still…
Talk on
How to not use AI. Or staying sane in a frenzied worldBogdan Ilie28m
Argues that low-cost experimentation from transformer models reduces the cost of being wrong but increases decision fatigue and burnout, citing a…
Talk on
My 30 Years of JavaScript: How I Learned to Stop Worrying and Love JavaScriptWekoslav Stefanovski32m
A 27–28 year personal history traces JavaScript from a 10-day experiment to the dominant runtime, with concrete episodes: a subtle bug that costs two days…
Talk on
Building for the Unknown: Scaling Observability as a ProductRiste Oreshkovski19m
Claims that treating observability as a product and applying platform engineering turns telemetry into consistent, self‑service insight for a portfolio of 85…
Talk on
Artful Defense: Let's Sketch Web SecurityRamona Schwering30m
Live sketch notes map front-end risks to concrete fixes: Vue auto-escapes templates but CVEs have hit i18n prototype pollution so frameworks are not a full…
Talk on
Building Angular Apps With AISam Vloeberghs34m
Angular ships concrete tools: repository-level llm.ext and llm.full.ext files that fix LLM knowledge, plus official system-prompt files and an Angular CLI MCP…
Talk on
From Portable AI Lab to Frontier ResearchNino Risteski34m
Builds a complete, inspectable research workflow on a MacBook + tinygrad and follows a tensor op from Python through compiler optimization to a generated Metal…
Talk on
What Do You Do When NVIDIA GPUs Aren't Available for Inference?Bojan Jakimovski32m
Claim: far more inference runs without NVIDIA than expected — engineered a small Mixture‑of‑Experts “Trinity mini” to avoid huge clusters while training still…
Talk on
Inside GPTs: Understanding Large Language ModelsIgor Trajkovski36m
Full pipeline from raw web to deployed assistant with concrete numbers: raw filtered Common Crawl becomes 44 terabytes of training text, tokenized into ~50k…
Talk on
Context Is Their Reality: How AI Agents Perceive the WorldElena Kolevska33m
Claim: context that an agent receives is its only reality and managing it is the builder's responsibility. Tooling demonstrated: agent memory server backed by…
Talk on
I’m a Software Engineer at Microsoft. I Don’t Write Code.Gerald Versluis33m
Claim: no meaningful code is written since November 2025 because work moves through GitHub Copilot and Copilot CLI and autonomous agents. The .NET MAUI team…
Talk on
JavaScript Doesn't Support Operator Overloading... Right?Iwo Plaza35m
Claims a practical operator-overload layer for TypeScript that keeps full type inference and normal JS ergonomics by applying surgical, procedural patches to…
Talk on
Harnessing the Model: What Coding Agents Are Really Made OfDushko Klincharov38m
Walks through the Open Code codebase and proves a coding agent is mostly harness not magic: TypeScript async/generator loops glue an LLM to tools, streaming…
Talk on
What makes AI work in a hospital, and what makes it harderDragan Shahpaski20m
Real hospital AI needs deep integration: radiology voice recognition runs as two-stream real-time transcription tied to PACS and EHR so models can be…
Talk on
One Project, Three Ways I Changed How I Write KotlinAndjelina Maksimovic14m
Built a turn‑based card game exposes three concrete lessons: a single flexible Hero class with nullable effect fields produces invalid states, replaced by a…
Talk on
Friendly Borders: Graph algorithms reveal Eurovision voting patternsDomagoj Marić35m
Claims neighborly favoritism is real and quantifies it using 2008–2024 Eurovision voting data, ingesting a community-maintained JSON dataset, building graphs…
Talk on
I Stopped Throwing Errors and My Code Finally WorksAndrej Acevski23m
Effect is a TypeScript library that makes errors part of the type so functions declare exact failure types (e.g., BoardNotFound | DBError | NotifyFailed), uses…
Talk on
A Bouncer Gang in the (Vibe) Coding PartyBozidar Spirovski32m
Claims a practical pipeline that pairs AI with deterministic scanners to speed security reviews and surface real faults. It builds three open tools: PR Bouncer…
Talk on
(When) Do We Finally Have a Unified Toolchain?Alexander Lichter24m
Claims a single CLI called V+ (vp) replaces stitching: VP migrate auto-converts ESLint/Prettier/tsup setups, runs installs and scaffolds projects. It bundles…
Talk on
Thinking in qubits, using codeSerena Sensini32m
Hands‑on Python demos use Qiskit emulator and state‑vector inspection to show concrete claims: a single Hadamard produces near 50/50 collapse (Hadamard ->…
Talk on
A Brief History of Code Review (And What's Next)Santosh Yadav32m
History traces manual inspections to email patches to GitHub pull requests and now AI agents claim to remove the human bottleneck by auto-generating PRs and…
Talk on
Performant TypeScript shaders: breaking down the Jelly SliderKonrad Reczko32m
Shows TypeScript compiled to GPU code using TypeGPU compiles TypeScript to GPU shaders, not by running JS on the GPU, and uses that to build a jelly slider…
Talk on
Building Cleaner Angular Applications with Signal FormsKiril Zafirov23m
A working booking form with organizer fields, a dynamic attendee list and nested company billing is built with Angular Signal Forms and a JSON schema; the demo…
Talk on
How TanStack AI made the hidden complexity of AI simple for youAlem Tuzlak31m
TanStack AI claims to replace dozens of pages of hand‑rolled SSE and provider‑specific parsing with a few lines: a client useChat hook, a server chat method…
Talk on
Reverse-Engineering Seniority, From Bootcamp Grad to Staff Engineer in Four YearsFaris Aziz35m
Claims a four‑year jump from bootcamp grad to staff engineer and a promotion to engineering manager by age 22, backed by specific actions not platitudes: a…
Talk on
Stop Engineering Features. Start Learning Graphs.Stefan Andonov32m
Relational tables become a heterogeneous graph using foreign keys as edges and many‑to‑many tables as weighted edges, then a GNN learns order embeddings to…
Talk on
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.