Posts

The Hype Meets the Data: State of AI 2026 Results

Image
Last month, I shared the open survey for the State of AI 2026, asking you to help replace the endless industry hype with actual, ground-level field data. The results are finally out, collected from 7,258 web developers . After reviewing the deep breakdown across every section—from models and agents to demographics and real-world pain points—the verdict is clear. AI-assisted coding is no longer a bleeding-edge experiment. It has crossed the threshold to become standard engineering practice. Here is what the data actually tells us about how software development is changing in 2026. ⚡ The 50% Threshold is Shattered In 2025, developers reported that AI generated roughly 28% of their code on average. This year, that figure has doubled to 56% . The heaviest adoption growth is occurring among developers who rely on AI for over 75% of their output. Interestingly, the data shows that higher reliance on AI correlates with fewer years of professional experience. But even for seasoned vet...
Read more

Adding Session Memory Without Building a Preference Engine

Image
  I just added another feature to Kino , my educational, cinema-themed distributed systems project. The LangGraph-based agent service is one part of that platform. This time the feature was memory . But not the vague, hyped kind. I did not want Kino to pretend it knows a user's taste forever. I wanted something much narrower and much more useful: Short-term conversational memory for follow-up turns that helps the agent continue the current search without pretending to know more than it actually does That decision mattered a lot. It kept the feature small enough to trust, but still visible enough to feel like real agent behavior. What changed The new capability is simple to describe. A user can start with: Discover exactly 3 comedy movies from 2010 onward from Kino's catalog. Then follow up with: I didn't like them, please discover different ones. And Kino can continue from the current thread instead of tr...
Read more

Not Classic RAG: Building a Structured-Retrieval Discovery Agent with LangGraph

Image
  I just added a new feature to Kino , my educational movie-discovery project built with LangGraph: a prompt-driven discovery flow that finds grounded titles from a local catalog. The easy label would be RAG . More precisely, it is not classic RAG . What I built is closer to a structured-retrieval agent : the model interprets the request, a narrow service returns structured facts, and deterministic code enforces the final result. That distinction sounds academic at first. In practice, it changed almost every implementation choice. What I actually built Kino is an educational project, but this feature forced a very real architecture decision. I wanted a user to be able to type something like Discover comedy movies from 2010 onward from Kino's catalog. and get back grounded titles from the project's own data. The final flow is intentionally small: an LLM interprets the user's request a single search_titles tool turns that into a structured catalog query t...
Read more

Ubuntu 26.04 LTS: AI Toolchains in the Repo, Security in the Defaults

Image
 Last week, on April 23, 2026, Canonical released Ubuntu 26.04 LTS "Resolute Raccoon" . The interesting part is not GNOME 50 or the normal LTS cadence. It is that Ubuntu 26.04 moves more of the hard platform work into the supported distro path: TPM-backed full-disk encryption , CUDA via apt , ROCm in Ubuntu's repositories , Wayland with NVIDIA support , and Rust-based sudo and core utilities . For platform teams, the value is straightforward: less out-of-band setup, fewer per-machine exceptions, and a cleaner baseline across desktop, server, and WSL. Ubuntu 26.04 LTS matters because it turns several "extra integration projects" into supported platform defaults. What is Ubuntu 26.04 LTS? In plain English, this is the Ubuntu release for teams that want a long support window and fewer surprises. Canonical says Ubuntu 26.04 LTS will be supported until April 2031 , with up to ten years of ESM updates through Ubuntu Pro. If you are coming from Ubuntu 24.04 L...
Read more

GPT-5.5 Is Not Just a Better Model. It Is a Deployment Story.

Image
On April 23, 2026, OpenAI introduced GPT-5.5 . The obvious story is performance: better coding, stronger tool use, more persistence, fewer tokens, and GPT-5.4-class latency. But the more important story is what came with it. OpenAI did not just ship a benchmark table. It shipped a system card , a long deployment-safety write-up on misalignment and internal deployment , and a public Bio Bug Bounty . That bundle matters. GPT-5.5 is one of the clearest signs yet that frontier AI launches are becoming deployment packages: model + tools + safeguards + access policy + post-launch testing. What is GPT-5.5? In plain English, GPT-5.5 is OpenAI's current answer to "real work" AI. Not just chat. Not just autocomplete. A model that is supposed to take messy tasks, plan them, use tools, check its own work, and keep going across terminals, browsers, docs, and spreadsheets. The launch post makes that pitch directly, and the benchmark table supports part of it: 82.7%...
Read more

The Physical Agent Harness: Why Project Mirage’s 'Dune' Keypad Matters

Image
  The AI hardware conversation has spent the last year obsessed with wearables—smart pins and pendants trying to replace your smartphone.  But for developers, the real operational bottleneck isn't checking the weather on the go.  It is the physical friction of constant context-switching at the desk: jumping between IDEs, GitHub, terminals, and back-to-back meetings. This week, Project Mirage —a startup founded by former Ultrahuman VP of Hardware Apoorv Shankar—launched a piece of hardware that approaches this problem differently.  Instead of an ambient wearable, they built Dune : a highly specific, context-aware desk tool that acts as a physical extension of your agent harness. What is Dune? Dune is a minimalist, three-button keypad for Mac.  It is tiny (40mm wide), built from CNC‑machined anodized aluminum, and plugs directly and flush into the side of your laptop via USB-C, requiring no battery or external cables. Unlike a standard macro pad where you ...
Read more

Claude Mythos Preview: The Most Important AI Release Wasn't a Release

Image
Anthropic’s most important signal this month is not a benchmark chart. It is the fact that the company published a full system card for Claude Mythos Preview and then explicitly said it does not plan to make the model generally available. That is a very different kind of launch. If Anthropic’s own materials are directionally right, then we are moving from “AI can help security teams” to something more serious: frontier models can compress vulnerability discovery and exploit development enough that release governance, disclosure capacity, and patching speed become first-order engineering problems . What is Claude Mythos Preview? According to Anthropic’s Project Glasswing announcement , Claude Mythos Preview is a general-purpose, unreleased frontier model . According to the system card , it is also Anthropic’s most capable frontier model to date . The same system card says the company decided not to make it generally available. Instead, Anthropic is restricting access t...
Read more