In Ramzor, Hefer survives a high-tech job with zero technical skills using one move: forward everything to Shraga. It works beautifully — until Shraga... Read More

Caching is a cornerstone of application performance, but are we truly leveraging its full potential? With increasing complexity in modern systems, s... Read More

I believe the most interesting problems live between fields, not inside one. As a cellist, I became convinced music and the brain deserved to be one c... Read More

Seth Godin gave developers a rule in 2005: don't shave that yak. As a team lead, I found a good reason to break it. My engineers' status updates ke... Read More

At Amazon Devices, I worked on a product launch where conversion looked strong, and we were sure we found a winning solution. Until we started reading... Read More

For thirty years we built the web for human eyes. That era is ending. Agents now consume the web headlessly and hand us only the last mile, visually. ... Read More

A simple employee at a cyber security company in Agrabah finds a lamp. The genie inside (a Large Language Genie) promises to solve his impossible job:... Read More

Autoscaling gets slapped onto nearly every deployment, and the usual results are surprise bills and cascading failures. Here's the uncomfortable part:... Read More

You need to know if your LLM lies to your users behind your back. So you appoint another LLM to keep an eye on it. The classic LLM-as-a-judge. But... Read More

Cloud-based AI is powerful, but it comes with latency, cost, and privacy trade-offs. What if you could run autonomous AI agents directly on the user's... Read More

Scale LLM tasks to thousands of items without a giant prompt! Generative AI can feel like magic: you hand the model everything it might need and le... Read More

You’re stuck. You’ve tried everything. You’re circling the same dead end. You've considered abandoning tech to become a goat herder in the Alps. No... Read More

Running conversational agents in production is expensive, but analyzing their unstructured logs at scale using LLMs introduces a painful "double-token... Read More

We're engineers. We measure, we benchmark, we run postmortems. We pride ourselves on not taking things on faith. So why do we quote advice we've neve... Read More

Generating a few seconds of video can easily take a minute of compute. Closing that gap isn't AI - it's engineering. A layered stack of low-level opti... Read More

Have you written an LLM skill? It starts simple: define its goal, give it a tool, and it works. But what happens when you drop that isolated skill int... Read More

From BlackHat to WhiteHat is a technical and personal journey from breaking systems out of curiosity, ego, and adrenaline, to using the same mindset t... Read More

When my father was diagnosed with a terminal illness, I discovered that finding relevant clinical trials is a broken process: outdated interfaces, unr... Read More

Sound is just a wave - and a wave has parameters you can bend: pitch, frequency, amplitude. All it takes is open-source tools and a laptop. Turns out,... Read More

The rise of AI tools like Claude hasn’t just changed our daily git commits—it has completely rewritten the playbook for what makes a great developer a... Read More

Codenames: the spymaster gives one clue word and a number, and the team guesses their cards without hitting the assassin. In an era when we bolt an LL... Read More

Google Chrome’s Dinosaur game is one of the most popular in the world, everybody has seen it at least once, but did you really see it? I mean, it’s co... Read More

Two companies merged. So did their clouds — and their cultures. One company grew up cloud-native: spot instances, managed-everything, move fast and t... Read More

There has never been a better time to build something on the side. AI has dramatically lowered the cost of turning an idea into a real product, and su... Read More

While AI enthusiasts were publishing blog posts, demos, and browser extensions showing how easy it is to summarize hotel reviews with LLMs, we were bu... Read More

Engineering organizations are built on the promise of meritocracy: that good work speaks for itself. Often it does not. Long before anyone talks about... Read More

I became a data scientist because I liked getting my hands dirty with data, building models, and slowly turning a mess into something understandable. ... Read More

We are adding AI to our workflows, our IDEs, our incident response, and sometimes even our production investigation process. But AI does not see produ... Read More

Cloud-native applications mean cloud-native testing, and at the end of each month, cloud-native billing for this testing. We present minicloud, a h... Read More

I used to think being a good engineer meant writing code that worked. Then I started working on systems that move real money. When the cost of a mista... Read More

"Quantum computers (QCs) are faster because they try all options in parallel", we've all heard that trope at some point, but is it any true? This sess... Read More

The era of human-written code and manual pull request reviews is over. In the shift toward Agentic Software Engineering, we are no longer typists; we ... Read More

AI researchers and security researchers never really had a reason to collaborate closely - until the agentic revolution. In this lightning talk we - a... Read More

You know how it works :) (Previous songs: https://youtube.com/playlist?list=PLvv1VJsbJ2I62N7VmIy_PcEU9wFmEOVTi&si=duBIRWxO9v0Y4hnq)

Ever wondered why Rubber Duck Debugging actually works? It doesn't work because the duck is smart. It works because it forces us to unpack the implic... Read More

Image generation works beautifully in demos and fails the moment real users hit it. Latency spikes, models collapse under specific prompts, and low ... Read More

For Waze, accurate road closure data is critical. Minor errors can cause failed routes and erode user trust. Much of this data comes from public sourc... Read More

Think HTTPS makes you safe? Think again. From poisoned dependencies to deep‑link traps, we’ll peel back the layers of a React Native stack and reveal ... Read More

A new breed of frontend frameworks is proposing an alternative to client-side and server-side rendering and server-side rendering. In both, the app co... Read More

Six months ago I stopped playing with AI agents and started living with one. It runs 24/7, has persistent memory, sub-agents for dedicated roles, in... Read More

Who’s watching your production system at 2 a.m.? For us, it’s an autonomous AI agent. At UVeye, we scan over 3 million vehicle scans monthly across... Read More

Be honest: that last project you built with AI? You think it's a lot better than it actually is. So does the developer next to you, and so does every ... Read More

Our best engineer never sleeps. It's first responder when production breaks, QA when a bug shows up, architect when we redesign, and the knowledge bas... Read More

Suddenly everyone is talking about “taste.” As AI makes writing code dramatically cheaper, more and more people argue that an engineer’s real value... Read More

What does it take to turn AI glasses into your very own drawing teaching tool? We integrated Meta Ray-Ban AI glasses into our hand-drawing teaching a... Read More

An agent that drafts text is a demo. An agent that sends invoices, messages clients, and books meetings for a real business, while its owner is asleep... Read More

Getting laid off in tech is tough, but the "toxic positivity" and social media noise that follow can be even harder. Drawing from personal experience ... Read More

I work at a company that builds a couples-therapy platform. So when I found myself fighting with my agent again, it hit me: what if I applied the prin... Read More

Every game has a winning strategy, and it's never written in the rulebook - it emerges from the rules. Change a rule, and a different strategy wins. T... Read More

A few years ago I gave a talk on protecting your focus: every interruption costs ~23 minutes, busy ≠ productive, guard the block. Then I spent a year ... Read More

Welcome to the Reversim ultimate tech reality check game: "Production Drop or AI Flop?" In this fast-paced interactive lightning session, a live game... Read More

3:12 AM. A cloud cost alert wakes up the on-call engineer. No deployment is running, no campaign is live, our users are asleep. And yet - something on... Read More

Agent memory got better this year. Awareness of the human is still unsolved. Your Claude Code doesn't know you slept four hours and need to take it sl... Read More

Every team does the same thing. Agent behaves weirdly in production - retries endlessly, drops tasks, returns confident nonsense. First reaction: swap... Read More

"We need domain experts." Everyone agreed. Nobody knew what we should actually ask them... While building AI financial and business advisors at Int... Read More

יומיים אחרי 7.10, לפני שהתברר היקף האסון, התארגנו עשרות מתנדבות ומתנדבים מקולנוע תיעודי, צילום, טיפול ומחקר, והתחילו להקליט עדויות של ניצולים. כך נו... Read More