Skip to content
WritingToolsCodexResourcesAbout
SearchFor agents
Menu
WritingToolsCodexResourcesAboutFor agentsContact
Back to newsletter

April 25, 2026

AI News for Developers #21: GPT-5.5, Images 2.0 & Real Production Agents

Hey Devs!

Original on SubstackView on LinkedIn

On this page
  1. GPT-5.5 released to ChatGPT and Codex
  2. ChatGPT Images 2.0
  3. Google AI Agent Clinic lessons
  4. Hermes Agent + Ollama: How to Install Hermes Locally Fast

Hey Devs! During this week, several important AI announcements were made that directly affect developers. Let’s jump into it. ;)


GPT-5.5 released to ChatGPT and Codex

OpenAI released GPT-5.5 to ChatGPT Pro and Codex users on 23 April 2026. The GPT-5.5 keeps the 1 M-token context window of GPT-5.4 but is priced at $5 per 1 M input tokens and $30 per 1 M output tokens, roughly double the price of GPT-5.4. Despite the price, GPT-5.5 improves performance on 9 of 10 benchmarks (e.g., ARC-AGI-2, MCP Atlas, Terminal-Bench 2.0) and completes the same Codex tasks with fewer tokens and similar per-token latency.

Read more: https://openai.com/index/introducing-gpt-5-5/


ChatGPT Images 2.0

OpenAI released ChatGPT Images 2.0, describing it as a complete rethink of its image‑generation model. The new model expands the product from a fun, creative tool into a visual workflow platform. PetaPixel notes that OpenAI designed Images 2.0 to be available across ChatGPT, Codex, and the API so that developers can incorporate it into code‑generation and research workflows

Read more: https://openai.com/index/introducing-chatgpt-images-2-0/


Google AI Agent Clinic lessons

Google’s AI Agent Clinic series published a post on 21 April 2026 that shares lessons from refactoring a monolithic sales‑research agent. The article is written for developers building complex agents and recommends:

  • Break up monolithic agents

  • Force structured outputs

  • Use dynamic Retrieval‑Augmented Generation (RAG)

  • Add observability and cost control

These lessons help developers design more maintainable and cost‑efficient AI agents that can survive in production.

Read more: https://developers.googleblog.com/production-ready-ai-agents-5-lessons-from-refactoring-a-monolith/


Hermes Agent + Ollama: How to Install Hermes Locally Fast

Run Hermes Agent locally with Ollama in just 1 minute, no API, no cloud, no cost. In this tutorial, I’ll show you how to install a fully local AI agent, how it works, and real use cases to boost your workflow.

Watch on YouTube: Hermes Agent Locally with Ollama


See you next week! Cheers, proflead!

A note for your inbox

AI news, useful tools, and what I’m building.

The weekly newsletter, with an archive you can read first.

Subscribe Read the archive

Vladislav Guzey / proflead

Let’s build and learn.

Let’s build something

Code, research, and lessons
from building and teaching.

Explore

WritingToolsCodexResources

Connect

AboutContactNewsletterSupport my work

Follow the source

YouTube · @profleadVideosGitHubLinkedInRSSFor agents

© 2026 proflead. All rights reserved. Attribute shared content with a link to proflead.dev.

PrivacyTermsCopyright