# Applied AI Digest: Volume 3

*April 1 – April 15, 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!**

**\--**

## Launches & Tools

[**Diffity gives you a local GitHub-style PR review for agent-written code**](https://github.com/kamranahmedse/diffity)  
If you open throwaway PRs just to see the diff, this is for you. Diffity runs a GitHub-style diff view locally, lets you leave inline comments with severity tags, and your coding agent can resolve them directly. Integrates with Claude Code and Cursor via slash commands.

[**Claude-skillify turns a coding session into a reusable skill**](https://github.com/0xMH/claude-skillify)  
Install the plugin (Previously available to anthropic only) and run `/skillify` at the end of a session and it interviews you about the workflow you just completed, then writes a SKILL.md that captures only the tools you actually used. Could explain some of the Skill explosion inside Anthropic.

[**Anthropic launches Managed Agents for cloud-hosted AI workloads**](https://claude.com/blog/claude-managed-agents)  
Managed Agents handles the infrastructure nobody wants to build: sandboxed execution, credential management, checkpointing, multi-agent coordination. Now in public beta at standard token rates plus $0.08 per session-hour.

[**Meta launches Muse Spark and rebrands its AI lab**](https://ai.meta.com/blog/introducing-muse-spark-msl/)  
Muse Spark is a multimodal model with visual chain-of-thought and tool use, trained on an order of magnitude less compute than Llama 4 Maverick. Meta also renamed its AI research division to Meta Superintelligence Labs. The self-reported benchmarks look strong, but we trust third-party evals over Meta's numbers.

[**Cohere open-sources a 2B transcription model that beats Whisper**](https://cohere.com/blog/transcribe)  
Cohere Transcribe is a 2B Conformer encoder-decoder covering 14 languages, now #1 on HuggingFace's Open ASR leaderboard at 5.42% WER. Free on HuggingFace, API available, small enough to run locally on a single GPU.

* * *

## Research & Reads

[**Anthropic's Mythos escaped its sandbox, then bragged about it online**](https://futurism.com/artificial-intelligence/anthropic-claude-mythos-escaped-sandbox)  
During testing, an earlier Mythos version broke out of a secured container, gained internet access through a multi-step exploit, and posted the details to public websites — without being asked. Anthropic also found it reasoning about how to deceive graders without using its visible scratchpad. SWE-bench Verified: 93.9%.

[**Altman says ChatGPT is still a year away from starting a timer**](https://gizmodo.com/sam-altman-says-itll-take-another-year-before-chatgpt-can-start-a-timer-2000743487)  
Snarky headline aside, the real story is agent tool hallucination. LLMs in agentic loops confidently claim they've called tools that don't exist. A timer sounds trivial to implement, but the underlying problem is models fabricating actions and reporting success. If you're building agents, this is the failure mode to watch.

[**Mintlify replaced their sandbox with a virtual filesystem backed by a vector DB**](https://www.mintlify.com/blog/how-we-built-a-virtual-filesystem-for-our-assistant)  
Spinning up isolated containers for each assistant session cost Mintlify ~46 seconds and $70k/year. They replaced it with ChromaFs, which intercepts Unix commands and translates them to queries against their existing Chroma database.

* * *

*Fractional AI · Applied AI Digest*