gelisam

@haskell_cat

AI Safety ∩ Programming Language Theory. Part-time technical alignment researcher, full-time Haskell software engineer at http://well.co, opinions are my own.

Montreal

haskellcat.com

於六月 2016 加入

2K貼文 1K位跟隨者 311個跟隨中

你可能會喜歡

@bgamari

@tweagio

@welltyped

@kosmikus

@mattoflambda

@nomeata

@NikitaYVolkov

@snoyberg

@int_index

@tikhonjelvis

@vrom911

@csaba_hruska

@Iceland_jack

@owickstrom

置頂

gelisam

@haskell_cat

年10月9日

I am doing technical alignment research in my free time. Here is a project in which I use static analysis to verify whether a neural network satisfies its safety property under _all_ inputs or if it needs more training. gelisam.com/ai-safety-via-…

haskell_cat's tweet card. Proving that the neural network learned its safety property.

Parity Bot

來源: gelisam.com

gelisam

@haskell_cat

年12月8日

Tell your model _why_ ask! "Would you like me to explain how to downgrade your compiler, port the code to a newer version... or, since you want to use this code as a starting point, would you like me to generate some starting code which works with your version of the compiler?"

gelisam 已轉發

Joe

@alpha_convert

年11月25日

I know I'm a little late to the unwrap discourse, but: The value proposition of Rust is not "your program will not crash." It's "your program will not have memory unsafe behavior" The widespread conflation of the latter with the former is due to Haskell being too successful :)

gelisam

@haskell_cat

年11月6日

We should not develop superintelligence until we know how to do it safely. Sign the statement today! #KeepTheFutureHuman superintelligence-statement.org

haskell_cat's tweet card. “We call for a prohibition on the development of superintelligence, not lifted before there is (1) broad scientific consensus that it will be done safely and controllably, and (2) strong public...

Statement on Superintelligence

來源: superintelligence-statement.org

gelisam 已轉發

ControlAI

@ai_ctrl

年10月22日

🚨BREAKING: A tremendous coalition of leaders just called for a ban on the development of superintelligence. The two most-cited living scientists, Nobel laureates, faith leaders, politicians, founders, artists, a former head of state, and over 1000 others have joined. Thread 🧵

ai_ctrl's tweet image. 🚨BREAKING: A tremendous coalition of leaders just called for a ban on the development of superintelligence.

The two most-cited living scientists, Nobel laureates, faith leaders, politicians, founders, artists, a former head of state, and over 1000 others have joined.

Thread 🧵

gelisam

@haskell_cat

年9月26日

Somebody on my timeline recommends a book and it is _not_ If Anyone Builds It Everyone Dies??

Santiago

@svpino

年9月25日

This is a really good book. I like it because it covers both ends of the spectrum: 1. How LLMs work 2. How to build using LLMs It's a really nice one-two punch: start with the theory and use that right away to implement something useful. The second half of the book is what I…

svpino's tweet image. This is a really good book.

I like it because it covers both ends of the spectrum:

1. How LLMs work
2. How to build using LLMs

It's a really nice one-two punch: start with the theory and use that right away to implement something useful.

The second half of the book is what I…

gelisam 已轉發

Jeffrey Ladish

@JeffLadish

年9月24日

Post: lesswrong.com/posts/6ZnznCaT…

gelisam

@haskell_cat

年9月4日

> my prediction is that auto-regressive LLMs are doomed Yan LeCun, notorious AI Doomer 🤣

Karl Mehta

@karlmehta

年9月3日

1. "Nobody in their right mind will use autoregressive LLMs a few years from now." The technology powering ChatGPT and GPT-4? Dead within years. The problem isn't fixable with more data or compute. It's architectural. Here's where it gets interesting...

gelisam 已轉發

Crémieux

@cremieuxrecueil

年8月16日

One concept I wish more people were aware of is the Tocqueville Effect. Named for Alexis de Tocqueville, this concept describes the curious phenomenon by which people become more frustrated as problems are resolved: As life gets better, people think it's getting worse!🧵

cremieuxrecueil's tweet image. One concept I wish more people were aware of is the Tocqueville Effect.

Named for Alexis de Tocqueville, this concept describes the curious phenomenon by which people become more frustrated as problems are resolved:

As life gets better, people think it's getting worse!🧵

gelisam 已轉發

Rob Miles

@robertskmiles

年8月22日

Technology is generally really good. Why should AI be any different? A new video: (youtube link in the reply)

gelisam

@haskell_cat

年6月26日

When I was a teen, my government held a public consultation about switching from 1st-past-the-post to a proportional system. I did my research, went, presented approval voting, and was laughed off the stage. I never did politics again. Today, we're still using 1st-past-the-post.

Nauseam

@ChadNauseam

年6月25日

If you liked this, follow @ElectionScience for more information on a better way! It's called "approval voting", and it's so simple: you can vote for multiple candidates, and the candidate with the most votes wins. While not perfect, I think it's better than ranked-choice

gelisam

@haskell_cat

年6月20日

I like to learn about neural networks by working on tiny problems for which there exists a 100% correct solution. Here is an interactive experiment showing how in practice, backprop doesn't find this solution: gelisam.com/local-minima/

gelisam.com

Tensorflow — Neural Network Playground

Tinker with a real neural network right here in your browser.

來源: gelisam.com

gelisam

@haskell_cat

年5月30日

My first MCP server, which allows the agent to pick from a selection of shell commands. GitHub Copilot can natively run shell commands, but VS Code asks you to confirm each command. With mcp-cli, you only have to authorize the use of the tool once! github.com/gelisam/mcp-cli

github.com