Eoin Travers
@eointravers.bsky.social
I'm a Data Scientist, working on responsible AI for mental health.
Posting about data, AI, evals, and cognitive science.
eointravers.com
🇮🇪
Posting about data, AI, evals, and cognitive science.
eointravers.com
🇮🇪
Reposted by Eoin Travers
It'ssssss PREPRINT THURSDAY! (Sadly not a thing). Approximately an era ago, I spent a *lot* of time discussing the assumptions that underpin the field of #ComputationalPskychiatry with the brilliant @jonroiser.bsky.social and @olijrobinson.bsky.social osf.io/preprints/ps...
OSF
osf.io
July 10, 2025 at 11:07 AM
It'ssssss PREPRINT THURSDAY! (Sadly not a thing). Approximately an era ago, I spent a *lot* of time discussing the assumptions that underpin the field of #ComputationalPskychiatry with the brilliant @jonroiser.bsky.social and @olijrobinson.bsky.social osf.io/preprints/ps...
Reposted by Eoin Travers
Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust.
In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)
In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)
May 13, 2025 at 5:00 PM
Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust.
In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)
In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)
I'm on the job market, and like many, I hate LinkedIn. So I've done what any product-oriented data scientist would: built my own workflow. With browser automation/scraping, data pipelines, structured LLM outputs, and a fun way of using @notion.com as a UI.
eointravers.com/blog/job-scr...
eointravers.com/blog/job-scr...
March 24, 2025 at 2:47 PM
I'm on the job market, and like many, I hate LinkedIn. So I've done what any product-oriented data scientist would: built my own workflow. With browser automation/scraping, data pipelines, structured LLM outputs, and a fun way of using @notion.com as a UI.
eointravers.com/blog/job-scr...
eointravers.com/blog/job-scr...
Reposted by Eoin Travers
I'm organizing a "Data for Good Rapid Response Team", i.e. a set of people who can be mobilized to work on short data science projects to help various groups and organizations. Sign up here if this is of interest to you, and please share with others with data science skills.
Data-for-good rapid response team
I'm collecting people with data science skills who may want to hear about sporadic opportunities to use their skills for good on short projects. Project themes will center on topics I am connected wit...
docs.google.com
March 23, 2025 at 5:21 PM
I'm organizing a "Data for Good Rapid Response Team", i.e. a set of people who can be mobilized to work on short data science projects to help various groups and organizations. Sign up here if this is of interest to you, and please share with others with data science skills.
Stats time.
If you take a one-in-n chance n times (e.g. taking 10 one-in-10 chances), what’s the probability that at least one of them will come off?
Somewhat satisfyingly, the answer, regardless of what n is, turns out to be “around 63%”. Here’s why.
(Also at eointravers.com/blog/one-in-n/)
If you take a one-in-n chance n times (e.g. taking 10 one-in-10 chances), what’s the probability that at least one of them will come off?
Somewhat satisfyingly, the answer, regardless of what n is, turns out to be “around 63%”. Here’s why.
(Also at eointravers.com/blog/one-in-n/)
Taking One-In-N Chances
...
eointravers.com
March 20, 2025 at 11:50 AM
Stats time.
If you take a one-in-n chance n times (e.g. taking 10 one-in-10 chances), what’s the probability that at least one of them will come off?
Somewhat satisfyingly, the answer, regardless of what n is, turns out to be “around 63%”. Here’s why.
(Also at eointravers.com/blog/one-in-n/)
If you take a one-in-n chance n times (e.g. taking 10 one-in-10 chances), what’s the probability that at least one of them will come off?
Somewhat satisfyingly, the answer, regardless of what n is, turns out to be “around 63%”. Here’s why.
(Also at eointravers.com/blog/one-in-n/)
Humble-brag:
Over the past two years at Unmind, I got to build two AI features: Nova AI wellbeing coach, and AI practitioner matching. It's lovely to see both get a call out in Fast Company's list of the most innovative companies in the workplace for 2025.
www.fastcompany.com/91270254/wor...
Over the past two years at Unmind, I got to build two AI features: Nova AI wellbeing coach, and AI practitioner matching. It's lovely to see both get a call out in Fast Company's list of the most innovative companies in the workplace for 2025.
www.fastcompany.com/91270254/wor...
March 19, 2025 at 5:19 PM
Humble-brag:
Over the past two years at Unmind, I got to build two AI features: Nova AI wellbeing coach, and AI practitioner matching. It's lovely to see both get a call out in Fast Company's list of the most innovative companies in the workplace for 2025.
www.fastcompany.com/91270254/wor...
Over the past two years at Unmind, I got to build two AI features: Nova AI wellbeing coach, and AI practitioner matching. It's lovely to see both get a call out in Fast Company's list of the most innovative companies in the workplace for 2025.
www.fastcompany.com/91270254/wor...
Reposted by Eoin Travers
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
March 10, 2025 at 6:14 PM
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
Reposted by Eoin Travers
I have been doing entirely too much earnest posting about deep things recently, I need to do a proper thread about hippo testicles or something just to keep myself sane.
Oh by the way hippos have migratory testicles.
Oh by the way hippos have migratory testicles.
a statue of a hippopotamus with its mouth open and teeth showing .
Alt: A hippo being tossed a watermelon, which it crushes in its massive jaws.
media.tenor.com
March 12, 2025 at 5:33 AM
I have been doing entirely too much earnest posting about deep things recently, I need to do a proper thread about hippo testicles or something just to keep myself sane.
Oh by the way hippos have migratory testicles.
Oh by the way hippos have migratory testicles.
Automation frameworks for testing like Selenium (selenium-python.readthedocs.io/index.html) are underrated as a way of quickly prototyping new AI-driven UXs. For example, this script, (<1hr work with Cursor) will open a dedicated browswer that saves every job ad I open to a database [...]
March 10, 2025 at 4:47 PM
Automation frameworks for testing like Selenium (selenium-python.readthedocs.io/index.html) are underrated as a way of quickly prototyping new AI-driven UXs. For example, this script, (<1hr work with Cursor) will open a dedicated browswer that saves every job ad I open to a database [...]
R, Snowflake, and MacOS: A match made in Hell. 😠
March 7, 2025 at 9:57 AM
R, Snowflake, and MacOS: A match made in Hell. 😠
"Why aren’t more psychometricians becoming AI engineers and data scientists?"
March 5, 2025 at 12:59 PM
"Why aren’t more psychometricians becoming AI engineers and data scientists?"
Now that it's possible to run priming experiments on LLMs like this, I'd love to see more psychology researchers getting in on the act. There's no shortage of open questions to be answered about LLM behaviour, of experimental psychologists with the skills to answer them, and students who [...]
This is a crazy paper. Fine-tuning a big GPT-4o on a small amount of insecure code or even "bad numbers" (like 666) makes them misaligned in almost everything else. They are more likely to start offering misinformation, spouting anti-human values, and talk about admiring dictators. Why is unclear.
February 25, 2025 at 10:11 PM
Now that it's possible to run priming experiments on LLMs like this, I'd love to see more psychology researchers getting in on the act. There's no shortage of open questions to be answered about LLM behaviour, of experimental psychologists with the skills to answer them, and students who [...]
A fun post.
LLM prompt-based chatbots are easy and flexible, but hard to control. Rule-based bots give you control, but require more manual work and are inflexible. Is there a middle ground? Yes, and it involves graphs.
eointravers.com/blog/structu...
LLM prompt-based chatbots are easy and flexible, but hard to control. Rule-based bots give you control, but require more manual work and are inflexible. Is there a middle ground? Yes, and it involves graphs.
eointravers.com/blog/structu...
February 19, 2025 at 12:50 PM
A fun post.
LLM prompt-based chatbots are easy and flexible, but hard to control. Rule-based bots give you control, but require more manual work and are inflexible. Is there a middle ground? Yes, and it involves graphs.
eointravers.com/blog/structu...
LLM prompt-based chatbots are easy and flexible, but hard to control. Rule-based bots give you control, but require more manual work and are inflexible. Is there a middle ground? Yes, and it involves graphs.
eointravers.com/blog/structu...
LinkedIn, subscribing to the "Just make it a RAG chatbot" school of thought when it comes to AI features. 🥲
February 18, 2025 at 11:40 AM
LinkedIn, subscribing to the "Just make it a RAG chatbot" school of thought when it comes to AI features. 🥲
Reminder, because this has just bitten me again:
In python, `load_dotenv()` doesn't override variables if they're already set. Use `load_dotenv(override=True)` if you want to always use the values from your `.env` file, and save yourself a lot of debugging headaches.
In python, `load_dotenv()` doesn't override variables if they're already set. Use `load_dotenv(override=True)` if you want to always use the values from your `.env` file, and save yourself a lot of debugging headaches.
February 12, 2025 at 1:33 PM
Reminder, because this has just bitten me again:
In python, `load_dotenv()` doesn't override variables if they're already set. Use `load_dotenv(override=True)` if you want to always use the values from your `.env` file, and save yourself a lot of debugging headaches.
In python, `load_dotenv()` doesn't override variables if they're already set. Use `load_dotenv(override=True)` if you want to always use the values from your `.env` file, and save yourself a lot of debugging headaches.
Reposted by Eoin Travers
Can LLMs be used to discover interpretable models of human and animal behavior?🤔
Turns out: yes!
Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12
Turns out: yes!
Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12
February 10, 2025 at 12:21 PM
Can LLMs be used to discover interpretable models of human and animal behavior?🤔
Turns out: yes!
Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12
Turns out: yes!
Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12
New post: Evaluating Multi-Step Conversational AI is Hard (eointravers.com/blog/convo-e...)
TL;DR: Everyone [1] agrees that evals are crucial, but no one really knows how to do them for chatbots. I'm trying.
[1]: Well, e.g. @eugeneyan.com, @hamel.bsky.social, the other authors of applied-llms.org
TL;DR: Everyone [1] agrees that evals are crucial, but no one really knows how to do them for chatbots. I'm trying.
[1]: Well, e.g. @eugeneyan.com, @hamel.bsky.social, the other authors of applied-llms.org
February 10, 2025 at 10:28 PM
New post: Evaluating Multi-Step Conversational AI is Hard (eointravers.com/blog/convo-e...)
TL;DR: Everyone [1] agrees that evals are crucial, but no one really knows how to do them for chatbots. I'm trying.
[1]: Well, e.g. @eugeneyan.com, @hamel.bsky.social, the other authors of applied-llms.org
TL;DR: Everyone [1] agrees that evals are crucial, but no one really knows how to do them for chatbots. I'm trying.
[1]: Well, e.g. @eugeneyan.com, @hamel.bsky.social, the other authors of applied-llms.org
This, but also, psychology/cognitive science!
Maybe a hot take, but what about the following advice to the next gen:
Don't get an AI degree; the curriculum will be outdated before you graduate. Instead, study math, stats, or physics as your foundation, and stay current with AI through code-focused books, blogs, and papers.
Don't get an AI degree; the curriculum will be outdated before you graduate. Instead, study math, stats, or physics as your foundation, and stay current with AI through code-focused books, blogs, and papers.
February 9, 2025 at 6:11 PM
This, but also, psychology/cognitive science!
[I'm doing some messing around with docs.bsky.app, and this is a placeholder post]
February 6, 2025 at 2:14 PM
[I'm doing some messing around with docs.bsky.app, and this is a placeholder post]
Reposted by Eoin Travers
Anyone else have the worry that a lot of LLM research is .... just bad psychology?
February 3, 2025 at 3:26 AM
Anyone else have the worry that a lot of LLM research is .... just bad psychology?
I started writing some notes on how I think about the process of iterating on LLM prompts, and didn't know where to stop. The result? 2,500 words of possibly deranged thoughts social-technical systems, RL, product development, and more.
eointravers.com/blog/llm-pro...
eointravers.com/blog/llm-pro...
January 31, 2025 at 3:41 PM
I started writing some notes on how I think about the process of iterating on LLM prompts, and didn't know where to stop. The result? 2,500 words of possibly deranged thoughts social-technical systems, RL, product development, and more.
eointravers.com/blog/llm-pro...
eointravers.com/blog/llm-pro...
Reposted by Eoin Travers
A Python browser sandbox, by the @pydantic.dev folks!
github.com/pydantic/pyd...
Great to share small snippets of code (e.g: pydantic.run/store/c544b1...).
github.com/pydantic/pyd...
Great to share small snippets of code (e.g: pydantic.run/store/c544b1...).
January 30, 2025 at 10:43 AM
A Python browser sandbox, by the @pydantic.dev folks!
github.com/pydantic/pyd...
Great to share small snippets of code (e.g: pydantic.run/store/c544b1...).
github.com/pydantic/pyd...
Great to share small snippets of code (e.g: pydantic.run/store/c544b1...).
Reposted by Eoin Travers
We’re building a new static type checker for Python, from scratch, in Rust.
From a technical perspective, it’s probably our most ambitious project yet. We’re about 800 PRs deep!
From a technical perspective, it’s probably our most ambitious project yet. We’re about 800 PRs deep!
January 29, 2025 at 5:18 PM
We’re building a new static type checker for Python, from scratch, in Rust.
From a technical perspective, it’s probably our most ambitious project yet. We’re about 800 PRs deep!
From a technical perspective, it’s probably our most ambitious project yet. We’re about 800 PRs deep!
Unsexy request: Does anyone have go-to examples of python codebases that do unit/integration tests REALLY well? AI-related code a bonus.
January 27, 2025 at 8:26 PM
Unsexy request: Does anyone have go-to examples of python codebases that do unit/integration tests REALLY well? AI-related code a bonus.