====== Today in AI: April 22, 2026 · 4 min read ======
**OpenAI just reclaimed the image generation crown with ChatGPT Images 2.0, and it's not even close.**

OpenAI shipped [[https://www.therundown.ai/p/openai-reclaims-the-image-crown|ChatGPT Images 2.0]] today, and the architecture is absurdly ambitious. The model bakes in integrated planning, web search, and automated quality verification—meaning it checks its own work before handing it to you. [[https://simonwillison.net/2026/Apr/21/gpt-image-2/|Early benchmarks show]] it's leaving competitors in the dust on photorealism and prompt adherence. The real flex: it understands context in ways single-pass generators simply can't. For builders: image generation just became a reasoning problem, not just a diffusion problem.

🚀 **Databricks kills hand-coded CDC pipelines with AutoCDC declarative abstractions.** [[https://www.databricks.com/blog/stop-hand-coding-change-data-capture-pipelines|Databricks shipped AutoCDC]], a declarative framework that automates Change Data Capture and Slowly Changing Dimension patterns. No more sequencing hell, no more deduplication nightmares—the system handles late-arriving data, incremental processing, and all the boring edge cases automatically. For data engineers: this is the difference between writing 500 lines of Spark logic and declaring intent in 50.

🔬 **LightOn dropped a 149M dense retrieval model that punches like a 7B heavyweight.** [[https://news.smol.ai/issues/26-04-21-image-2/|LightOn LateOn]] is open-source (Apache 2.0), implements ColBERT-style multi-vector retrieval, and [[https://arxiv.org/abs/2004.12832|achieves competitive accuracy]] with models orders of magnitude larger. The kicker: it's fast enough for real-time RAG pipelines. For builders embedding search: open-weight retrieval just got genuinely good.

🤖 **Claude Opus 4.7's self-verification flips the agent stack upside down.** [[https://alphasignalai.substack.com/p/a-closer-look-at-harness-engineering|AlphaSignal reports]] Opus 4.7's native verification capabilities eliminate the need for separate evaluator agents in multi-agent workflows. You're no longer stuck orchestrating three models to do one job. For agentic architects: your harness just got simpler and cheaper.

🛠️ **Exa's Deep Max search agent is faster and more accurate than existing tools.** Deep Max combines autonomous research with improved retrieval metrics and substantially faster execution. It's designed specifically for agents that need to hunt information without human intervention. For agent builders: better search = better reasoning downstream.

Still no word on Gemini 3.5 or Llama 4. Meta remains quiet.

That's the brief. Full pages linked above. See you tomorrow.