Fintan Ryan
@fintanr
Market Insights at @github l recovering analyst (ex @redmonk, @Gartner_Inc) | 331 ppm | @fintanr.bsky.social
We are all learning a lot about the ethics and values of various companies right now. Keep notes.
The Silent Language of Office Plants: How Foliage Drives Innovation This weeks ground breaking thought leadership msuaas post, courtesy of Google Gemini 2.5. msuaas.com/2025/07/25/sil…
This weeks MSUAAS post is courtesy of Anthropic Claude Sonnet 4.0 on "Retroactive Synergy: Achieving Tomorrow’s Results Yesterday" msuaas.com/2025/07/11/ret…
This weeks guest post is from OpenAI GPT 4.0 on "Quantum Management: Leading Teams Through Parallel Corporate Realities" msuaas.com/2025/07/06/qua…
Now @code will generate your copilot-instructions file for you. You will get CRAZY better results by having these instructions for the AI...
This 👇👇👇
Quitting programming as a career right now because of LLMs would be like quitting carpentry as a career thanks to the invention of the table saw.
We added a browser to GitHub Copilot Coding Agent (via Playwright). 🌐 Coding agent will now run a dev web server in the background, open up its browser to test out changes, and include screenshots in the PRs it opens. 🤯 github.blog/changelog/2025…
f you're interested in the nascent field of context engineering (the new, more cromulent alternative to prompt engineering) Drew's piece here provides some excellent nomenclature for some of the challenges you might face...
As your context bloats, you hit different failure modes. These failures hit agents hardest because they operate in exactly the scenarios where contexts balloon: gathering information, making sequential tool calls, engaging in multi-turn reasoning, & accumulating histories.
Personal take, while it is an entirely predictable move, it is still good to see @googlecloud moving A2A to the @linuxfoundation. This one is a truly a case of a rising tide. developers.googleblog.com/en/google-clou… and linuxfoundation.org/press/linux-fo…
"We survey over 150 prompting studies and introduce a taxonomy of 21 key properties for assessing prompt quality and their influence on model performance." arxiv.org/abs/2506.06950 < new paper on what makes a good natural language prompt
Now in @code Insiders: Define custom modes with their own prompts and tools. Create your own with `Chat: New Mode File` command.