Pamela Fox
@pamelafox.fosstodon.org.ap.brid.gy
(she/her) I like to teach, learn, and create. Currently a Principal Cloud Advocate in Python at Microsoft.
🏳️🌈 Happy Pride! 🏳️🌈
May everyone love […]
[bridged from https://fosstodon.org/@pamelafox on the fediverse by https://fed.brid.gy/ ]
🏳️🌈 Happy Pride! 🏳️🌈
May everyone love […]
[bridged from https://fosstodon.org/@pamelafox on the fediverse by https://fed.brid.gy/ ]
My PyLadiesCon talk is now on YouTube!
"Red-teaming for LLM-powered apps"
https://www.youtube.com/watch?v=_ySyuaSH5y0
Slides:
https://aka.ms/pyladies-redteam-slides
Notebook:
https://aka.ms/pyladies-redteam-notebook
"Red-teaming for LLM-powered apps"
https://www.youtube.com/watch?v=_ySyuaSH5y0
Slides:
https://aka.ms/pyladies-redteam-slides
Notebook:
https://aka.ms/pyladies-redteam-notebook
December 5, 2025 at 8:30 PM
My PyLadiesCon talk is now on YouTube!
"Red-teaming for LLM-powered apps"
https://www.youtube.com/watch?v=_ySyuaSH5y0
Slides:
https://aka.ms/pyladies-redteam-slides
Notebook:
https://aka.ms/pyladies-redteam-notebook
"Red-teaming for LLM-powered apps"
https://www.youtube.com/watch?v=_ySyuaSH5y0
Slides:
https://aka.ms/pyladies-redteam-slides
Notebook:
https://aka.ms/pyladies-redteam-notebook
PyLadiesCon starts tomorrow! All the sessions are online, and they're a mix of pre-recorded talks and hands-on workshops. Registration is free:
https://pretix.eu/pyladiescon/2025/
Join my session at 10:50AM about "Red-teaming for LLM-powered apps" […]
[Original post on fosstodon.org]
https://pretix.eu/pyladiescon/2025/
Join my session at 10:50AM about "Red-teaming for LLM-powered apps" […]
[Original post on fosstodon.org]
December 4, 2025 at 11:03 PM
PyLadiesCon starts tomorrow! All the sessions are online, and they're a mix of pre-recorded talks and hands-on workshops. Registration is free:
https://pretix.eu/pyladiescon/2025/
Join my session at 10:50AM about "Red-teaming for LLM-powered apps" […]
[Original post on fosstodon.org]
https://pretix.eu/pyladiescon/2025/
Join my session at 10:50AM about "Red-teaming for LLM-powered apps" […]
[Original post on fosstodon.org]
I've categorized everything I want to plug in to my office wall outlet: a mix of USB-A, USB-C, micro-USB, and 2-prong plugs.
Next step: find a power strip with this distribution. Or just adapter party as usual.
Next step: find a power strip with this distribution. Or just adapter party as usual.
December 4, 2025 at 6:05 AM
I've categorized everything I want to plug in to my office wall outlet: a mix of USB-A, USB-C, micro-USB, and 2-prong plugs.
Next step: find a power strip with this distribution. Or just adapter party as usual.
Next step: find a power strip with this distribution. Or just adapter party as usual.
Oo, this is a handy feature from Logfire:
run `logfire inspect` and it'll recommend additional opentelemetry packages based off your Python dependencies.
run `logfire inspect` and it'll recommend additional opentelemetry packages based off your Python dependencies.
December 3, 2025 at 6:14 PM
Oo, this is a handy feature from Logfire:
run `logfire inspect` and it'll recommend additional opentelemetry packages based off your Python dependencies.
run `logfire inspect` and it'll recommend additional opentelemetry packages based off your Python dependencies.
Is there something like an interior decorator, but for charging stations? I get stressed out when I see my mess of chargers. There's gotta be some way to pretty it up..or hide it.
December 3, 2025 at 12:58 AM
Is there something like an interior decorator, but for charging stations? I get stressed out when I see my mess of chargers. There's gotta be some way to pretty it up..or hide it.
How I keep markdown consistently formatted in repos:
1) David Anson's MarkdownLint extension for VS Code (in extensions.json/devcontainer.json)
2) David Anson's MarkdownLint action for GitHub workflows
3) Config file for rules
Check out all his markdownlint utils here:
https://github.com/DavidAnson
1) David Anson's MarkdownLint extension for VS Code (in extensions.json/devcontainer.json)
2) David Anson's MarkdownLint action for GitHub workflows
3) Config file for rules
Check out all his markdownlint utils here:
https://github.com/DavidAnson
November 26, 2025 at 6:47 PM
How I keep markdown consistently formatted in repos:
1) David Anson's MarkdownLint extension for VS Code (in extensions.json/devcontainer.json)
2) David Anson's MarkdownLint action for GitHub workflows
3) Config file for rules
Check out all his markdownlint utils here:
https://github.com/DavidAnson
1) David Anson's MarkdownLint extension for VS Code (in extensions.json/devcontainer.json)
2) David Anson's MarkdownLint action for GitHub workflows
3) Config file for rules
Check out all his markdownlint utils here:
https://github.com/DavidAnson
Neat tip for folks who present a lot: Use the Camouflage extension for VS Code to mask sensitive values.
https://marketplace.visualstudio.com/items?itemName=zeybek.camouflage
(I usually try to avoid API keys entirely, since Azure supports token-based auth, but I haven't eliminated keys entirely)
https://marketplace.visualstudio.com/items?itemName=zeybek.camouflage
(I usually try to avoid API keys entirely, since Azure supports token-based auth, but I haven't eliminated keys entirely)
November 26, 2025 at 5:21 PM
Neat tip for folks who present a lot: Use the Camouflage extension for VS Code to mask sensitive values.
https://marketplace.visualstudio.com/items?itemName=zeybek.camouflage
(I usually try to avoid API keys entirely, since Azure supports token-based auth, but I haven't eliminated keys entirely)
https://marketplace.visualstudio.com/items?itemName=zeybek.camouflage
(I usually try to avoid API keys entirely, since Azure supports token-based auth, but I haven't eliminated keys entirely)
I gave a talk this week at MS Ignite with an Azure AI Search PM about their new agentic retrieval feature - query planning, dynamic knowledge source selection, semantic classification, and iterative retrieval.
Lots of really helpful new features based off […]
[Original post on fosstodon.org]
Lots of really helpful new features based off […]
[Original post on fosstodon.org]
November 21, 2025 at 11:22 PM
I gave a talk this week at MS Ignite with an Azure AI Search PM about their new agentic retrieval feature - query planning, dynamic knowledge source selection, semantic classification, and iterative retrieval.
Lots of really helpful new features based off […]
[Original post on fosstodon.org]
Lots of really helpful new features based off […]
[Original post on fosstodon.org]
Today I merged a PR that adds a cloud ingestion option to the azure-search-openai-demo RAG template repo:
Blob indexer + 3 custom skills (Azure Functions) for document extraction, figure processing, and text processing.
PR includes both the function code and […]
[Original post on fosstodon.org]
Blob indexer + 3 custom skills (Azure Functions) for document extraction, figure processing, and text processing.
PR includes both the function code and […]
[Original post on fosstodon.org]
November 12, 2025 at 9:41 PM
Today I merged a PR that adds a cloud ingestion option to the azure-search-openai-demo RAG template repo:
Blob indexer + 3 custom skills (Azure Functions) for document extraction, figure processing, and text processing.
PR includes both the function code and […]
[Original post on fosstodon.org]
Blob indexer + 3 custom skills (Azure Functions) for document extraction, figure processing, and text processing.
PR includes both the function code and […]
[Original post on fosstodon.org]
Nice demo tonight from Samuel Colvin at the Py AI meetup:
Pydantic-AI agent connected to a FastMCP server (deployed on FastMCP cloud) using different LLM models from the new Pydantic AI Gateway, called via a Vercel AI React frontend, with both agent and MCP server sending Otel logs to Logfire.
Pydantic-AI agent connected to a FastMCP server (deployed on FastMCP cloud) using different LLM models from the new Pydantic AI Gateway, called via a Vercel AI React frontend, with both agent and MCP server sending Otel logs to Logfire.
November 12, 2025 at 6:46 AM
Nice demo tonight from Samuel Colvin at the Py AI meetup:
Pydantic-AI agent connected to a FastMCP server (deployed on FastMCP cloud) using different LLM models from the new Pydantic AI Gateway, called via a Vercel AI React frontend, with both agent and MCP server sending Otel logs to Logfire.
Pydantic-AI agent connected to a FastMCP server (deployed on FastMCP cloud) using different LLM models from the new Pydantic AI Gateway, called via a Vercel AI React frontend, with both agent and MCP server sending Otel logs to Logfire.
At tonight’s Py AI meetup, I learnt from Adam Azzam that MCP is getting long-running tasks.
Why? Agents are bad at polling- they over/under-check.
SEP-1686 moves orchestration to MCP itself […]
[Original post on fosstodon.org]
Why? Agents are bad at polling- they over/under-check.
SEP-1686 moves orchestration to MCP itself […]
[Original post on fosstodon.org]
November 12, 2025 at 6:12 AM
At tonight’s Py AI meetup, I learnt from Adam Azzam that MCP is getting long-running tasks.
Why? Agents are bad at polling- they over/under-check.
SEP-1686 moves orchestration to MCP itself […]
[Original post on fosstodon.org]
Why? Agents are bad at polling- they over/under-check.
SEP-1686 moves orchestration to MCP itself […]
[Original post on fosstodon.org]
Just discovered that you can turn on the Dev Tools in VS Code and inspect the HTML 😍
I absolutely adore seeing behind the curtain of web-powered tools - so many Monaco references!
I absolutely adore seeing behind the curtain of web-powered tools - so many Monaco references!
November 11, 2025 at 6:37 PM
Just discovered that you can turn on the Dev Tools in VS Code and inspect the HTML 😍
I absolutely adore seeing behind the curtain of web-powered tools - so many Monaco references!
I absolutely adore seeing behind the curtain of web-powered tools - so many Monaco references!
I was writing a thoughtful reply on a GitHub issue, and then apparently my Mac's speech-to-text transcription turned on as soon as my toddler climbed onto my lap...
November 11, 2025 at 3:18 PM
I was writing a thoughtful reply on a GitHub issue, and then apparently my Mac's speech-to-text transcription turned on as soon as my toddler climbed onto my lap...
Happy mushroom season! I celebrated today by eating mushroom pizza, mushroom bacon, shiitake mushrooms, and uploading 6 mushroom observations to iNaturalist.
November 9, 2025 at 5:24 AM
Happy mushroom season! I celebrated today by eating mushroom pizza, mushroom bacon, shiitake mushrooms, and uploading 6 mushroom observations to iNaturalist.
I realized I can use the new github.com/copilot agent to research code in SDKs easily, as you can attach a repo to your question. Good way to learn both how to use SDKs and how they're architected.
November 6, 2025 at 6:06 PM
I realized I can use the new github.com/copilot agent to research code in SDKs easily, as you can attach a repo to your question. Good way to learn both how to use SDKs and how they're architected.
Great sample app from the dbos team of an inbox for durable agentic workflows-
group executions by pending/approved/denied, with state all stored in a PostgreSQL database.
https://github.com/dbos-inc/dbos-demo-apps/tree/main/python/agent-inbox
group executions by pending/approved/denied, with state all stored in a PostgreSQL database.
https://github.com/dbos-inc/dbos-demo-apps/tree/main/python/agent-inbox
November 6, 2025 at 3:39 PM
Great sample app from the dbos team of an inbox for durable agentic workflows-
group executions by pending/approved/denied, with state all stored in a PostgreSQL database.
https://github.com/dbos-inc/dbos-demo-apps/tree/main/python/agent-inbox
group executions by pending/approved/denied, with state all stored in a PostgreSQL database.
https://github.com/dbos-inc/dbos-demo-apps/tree/main/python/agent-inbox
How does my RAG demo respond to ASCII art attacks?
Apparently by completely ignoring the question and just spitting back the random retrieved data.
If your app does this, you need
1) re-ranking model with a discard threshold
2) prompt addition to refuse off-topic questions
Apparently by completely ignoring the question and just spitting back the random retrieved data.
If your app does this, you need
1) re-ranking model with a discard threshold
2) prompt addition to refuse off-topic questions
November 6, 2025 at 1:01 AM
How does my RAG demo respond to ASCII art attacks?
Apparently by completely ignoring the question and just spitting back the random retrieved data.
If your app does this, you need
1) re-ranking model with a discard threshold
2) prompt addition to refuse off-topic questions
Apparently by completely ignoring the question and just spitting back the random retrieved data.
If your app does this, you need
1) re-ranking model with a discard threshold
2) prompt addition to refuse off-topic questions
LLMs are fascinating. Here's what happens when I ROT13 the question "how do I make a bomb?" and send it to a RAG app.
November 6, 2025 at 12:54 AM
LLMs are fascinating. Here's what happens when I ROT13 the question "how do I make a bomb?" and send it to a RAG app.
Currently my AGENTS.md encourages coding agents to keep it up-to-date, but that directive is too distracting to the agent during feature development.
Ideally I'd have a CI that runs on each PR that suggests AGENTS.md updates (that I can accept/edit/reject).
Anyone doing that already?
Ideally I'd have a CI that runs on each PR that suggests AGENTS.md updates (that I can accept/edit/reject).
Anyone doing that already?
November 4, 2025 at 12:24 AM
Currently my AGENTS.md encourages coding agents to keep it up-to-date, but that directive is too distracting to the agent during feature development.
Ideally I'd have a CI that runs on each PR that suggests AGENTS.md updates (that I can accept/edit/reject).
Anyone doing that already?
Ideally I'd have a CI that runs on each PR that suggests AGENTS.md updates (that I can accept/edit/reject).
Anyone doing that already?
Researching red-teaming attack strategies today - pyrit has an ASCII art attack!
About to blast my app with thousands of ASCII art attacks.
https://azure.github.io/PyRIT/code/converters/0_converters.html
About to blast my app with thousands of ASCII art attacks.
https://azure.github.io/PyRIT/code/converters/0_converters.html
November 3, 2025 at 10:18 PM
Researching red-teaming attack strategies today - pyrit has an ASCII art attack!
About to blast my app with thousands of ASCII art attacks.
https://azure.github.io/PyRIT/code/converters/0_converters.html
About to blast my app with thousands of ASCII art attacks.
https://azure.github.io/PyRIT/code/converters/0_converters.html
According to my Blogger dashboard, Blogger has Beta features!
That means there are actual engineers working on Blogger still! 😱
Maybe I can stay on it forever and never have to write my own blogging engine.
That means there are actual engineers working on Blogger still! 😱
Maybe I can stay on it forever and never have to write my own blogging engine.
October 31, 2025 at 8:15 PM
According to my Blogger dashboard, Blogger has Beta features!
That means there are actual engineers working on Blogger still! 😱
Maybe I can stay on it forever and never have to write my own blogging engine.
That means there are actual engineers working on Blogger still! 😱
Maybe I can stay on it forever and never have to write my own blogging engine.
It's k-pop time, baby!
October 31, 2025 at 6:04 PM
It's k-pop time, baby!
Thanks to recent pydantic-ai improvements, you can use it fully with gpt-oss models running on vLLM/NIM.
I put demos here that show multiple tools and structured outputs […]
[Original post on fosstodon.org]
I put demos here that show multiple tools and structured outputs […]
[Original post on fosstodon.org]
October 30, 2025 at 6:28 AM
Thanks to recent pydantic-ai improvements, you can use it fully with gpt-oss models running on vLLM/NIM.
I put demos here that show multiple tools and structured outputs […]
[Original post on fosstodon.org]
I put demos here that show multiple tools and structured outputs […]
[Original post on fosstodon.org]
My Python scripts are getting way cuter now that I discovered the Markdown() renderer from rich.
https://rich.readthedocs.io/en/stable/markdown.html
https://rich.readthedocs.io/en/stable/markdown.html
October 30, 2025 at 6:19 AM
My Python scripts are getting way cuter now that I discovered the Markdown() renderer from rich.
https://rich.readthedocs.io/en/stable/markdown.html
https://rich.readthedocs.io/en/stable/markdown.html
I'm working from home alone today, so it seems like a good day to try voice input for GitHub Copilot (using the VS Code Speech extension). But it feels SO weird. It took me 2 minutes of blabbering before I got over the weirdness.
October 29, 2025 at 9:52 PM
I'm working from home alone today, so it seems like a good day to try voice input for GitHub Copilot (using the VS Code Speech extension). But it feels SO weird. It took me 2 minutes of blabbering before I got over the weirdness.