# Applied AI Digest: Volume 2

March 18 – April 1, 2026

* * *

**Note: We have moved our Applied AI Digest to a new platform! Check it out at** [**newsletter.fractional.ai**](http://newsletter.fractional.ai) **and make sure to subscribe so it goes straight to your inbox!**

## Models & Releases

[**OpenAI ships GPT 5.4 mini and nano to the API, plus Codex sub-agents**](http://openai.com/index/introducing-gpt-5-4-mini-and-nano)  
Mini and nano variants hit the API alongside GPT 5.3 chat latest. Codex also picks up sub-agents and the new 5.4 mini model — worth re-benchmarking your pipelines.

[**Claude Desktop launches general computer use**](https://x.com/felixrieseberg/status/2036193240509235452)  
Full computer control is now available inside Claude Desktop — not just the API. If you've been waiting to move agentic desktop workflows out of prototype, the door is open.

[**Anthropic introduces a Claude Certified Architect credential**](https://anthropic.skilljar.com/claude-certified-architect-foundations-access-request)  
A formal certification path for Claude architecture. Good signal for teams building credibility around Anthropic's stack.

[**OpenAI previews Refactory for automated legacy codebase refactoring**](https://developers.openai.com/codex/changelog)  
Dedicated tooling for breaking monoliths into services, plus AgentSDK 2.0 (open-source orchestration) landing April 6.

* * *

## Tools & Libraries

[Good Performance From Claude Code Review](https://code.claude.com/docs/en/code-review)  
A pr was reviewed by Claude Code, Codex CLI, a custom review agent, and two humans; none caught the bug. Claude's new Code Review product did. Expensive to run on every commit, but we're overall impressed.

[**Linear launches background agents for development workflows**](https://linear.app/docs/agents-in-linear)  
Another entrant in the background-agent space. Linear's agents work directly within issue management, bridging the gap between ticket and implementation.

[**YoloBox gives AI coding agents true local sandboxing**](https://github.com/finbarr/yolobox)  
Lightweight tool for sandboxing agent execution on your machine. If you're letting agents run free on localhost, this is a guardrail.

[**Stripe previews CLI-based service provisioning**](https://x.com/patrickc/status/2037190688950161709)  
Provision Stripe services directly from the command line. One more step toward fully scriptable infrastructure.

[**Cohere launches Transcribe for audio-to-text pipelines**](https://cohere.com/blog/transcribe)  
A new dedicated transcription product from Cohere, targeting audio processing workflows.

* * *

## Security

[**LiteLLM 1.82.8 ships compromised — rotate your API keys now**](https://github.com/BerriAI/litellm/issues/24512)  
A PyPI supply chain attack hit LiteLLM via compromised publishing credentials. Versions 1.82.7 and 1.82.8 exfiltrated environment variables — API keys, SSH keys, everything. The packages were yanked quickly, but if you installed either version, consider all secrets compromised. This also affects downstream packages like DSPy. Practical mitigation: add `exclude-newer = "1 week"` to your `[tool.uv]` config to delay pulling freshly published packages.

[**GitHub Copilot starts training on user interaction data by default**](https://github.blog/news-insights/company-news/updates-to-github-copilot-interaction-data-usage-policy/)  
Starting April 24, inputs, outputs, and code snippets from Copilot Free, Pro, and Pro+ users will train GitHub's models unless you opt out. Business and Enterprise tiers are not affected. Check your Privacy settings now.

* * *

## Research & Reads

[**Yann LeCun's team publishes a stable trained world model**](https://arxiv.org/abs/2603.19312)  
A world model trained to stability: potentially significant for robotics and manufacturing applications down the line. Worth tracking even if the near-term implications are unclear.

[**Exploring "LLM brain scans" — a technique orthogonal to fine-tuning**](https://dnhkng.github.io/posts/rys/)  
Deep dive into methods for inspecting and steering LLM internals without gradient updates. If you have some understanding of transformer architecture, this is a fascinating read.

[**When not to build a chatbot: choosing the right AI interface**](https://engineering.fractional.ai/stop-designing-chatbots)  
A practical framework for deciding when a chatbot is the wrong UX pattern. A great new blogpost by Nora Kako

[**Using documentation artifacts to iterate on AI products**](https://engineering.fractional.ai/artifact-driven-ai-creation)  
How to use structured documentation as a feedback loop for AI product development. A process-oriented complement to the eval-centric approach.

[**Using MCPs with evals for better AI engineering workflows**](https://engineering.fractional.ai/using-mcps-with-evals)  
Hands-on guide to integrating Model Context Protocol servers into evaluation pipelines. Fills a gap in the current MCP ecosystem documentation.

* * *

*Fractional AI · Applied AI Digest*