Faisal Waris @fwaris7

Gen. AI strategist; AI/ML researcher github.com/fwaris Joined June 2009

Tweets

1K
Followers

191
Following

159
Likes

1K

Yaron (Ron) Minsky @yminsky

4 months ago

I'm pleased to announce OxCaml! OxCaml is Jane Street's branch of OCaml. We've given it a new name and a snazzy logo, and done a bunch of work to make it easy for people to try.

57 231 2K 213K 671

Download Image

Faisal Waris @fwaris7

6 months ago

F# (windows) service and GUI client (Avalonia, FuncUI) for transcription and diarization. linkedin.com/posts/activity…

0 0 3 75 0

Pretty impressive performance by o3 #OpenAI12Days. Still, o3 can consume $1K+ worth of electricity on complex tasks (@ megawatts). Human brains are in @ 25 watts range, so machines have some way to go, yet. However, with Googles quantum leap, the gap may be closing fast.

0 0 0 78 1

Faisal Waris @fwaris7

10 months ago

Experimental 'chat with code evaluator' feature added to FsOpenAI to generate and evaluate F# code interactively. …zdthndaey.eastus-01.azurewebsites.net (need own OpenAI key) Evaluation sandbox utilizes typed AST to only allow types from set namespaces.

0 1 11 495 0

Download Image

Faisal Waris @fwaris7

11 months ago

OpenAI's o1 seems like a pretty capable F# code generator. See this post for more. linkedin.com/posts/activity…

0 2 8 411 2

Faisal Waris @fwaris7

a year ago

Revisiting Logic Puzzle with "o1" linkedin.com/pulse/revisiti… via @LinkedIn

0 0 0 49 0

Faisal Waris @fwaris7

a year ago

New look for F# FsOpenAI rag/chat app. Test link below (need to use own OpenAI key) fsopenaiserver1.azurewebsites.net Now with Radzen Blazor components Source: (github.com)

2 6 13 1K 3

Download Image

Faisal Waris @fwaris7

a year ago

Need of the hour: Parallel but self-throttled LLM API calls to stay below allowed capacity. #fsharp #asyncseq extensions github.com/fwaris/OnnxVis…

0 0 4 169 1

Download Image

Faisal Waris @fwaris7

a year ago

Check out my latest article: Phi-3 Vision is a Surprisingly Useful Gem linkedin.com/pulse/phi-3-vi… via @LinkedIn

0 0 0 53 0

Faisal Waris @fwaris7

a year ago

F# example to serve ONNX vision models (e.g. phi-3 vision) for online and batch modes. Supports multiple parallel request if GPU hardware allows. github.com/fwaris/OnnxVis…

0 11 23 2K 4

Jeremy Howard @jeremyphoward

a year ago

There's a new bill, SB-1047 "Safe and Secure Innovation for Frontier Artificial Intelligence Models Act". I think it could do a great deal of harm to startups, American innovation, open source, and safety. So I've written a response to the authors: 🧵 answer.ai/posts/2024-04-…

35 281 1K 303K 357

Faisal Waris @fwaris7

2 years ago

Check out my latest article: Constrained and Provable LLM Code Generation linkedin.com/pulse/constrai… via @LinkedIn

0 1 1 415 0

Faisal Waris @fwaris7

2 years ago

Management has green lighted more #fsharp based apps for Gen AI. To train additional resources in F# / GenAI, I have created a stack called the 'Contemporary' web stack. Description of Contemporary plus a minimal demo app is here: github.com/fwaris/CW1

1 8 23 2K 10

Faisal Waris @fwaris7

2 years ago

Have been using F# interactive in VS Code to work on a large Linux VM from my local desktop using "Remote SSH". Works great! One issue: A long line of code may not compile (not sure why exactly). Works if you split code over multiple lines. Beats using Terminal for sure.

0 0 1 248 0

Faisal Waris @fwaris7

2 years ago

Formulating and solving 'zebra' logic puzzles with F# and Z3: github.com/fwaris/LLMLogi…

0 3 14 2K 5

Faisal Waris @fwaris7

2 years ago

tussling with internal teams to acquire more compute capacity for my LLM apps. LLM compute capacity is the new scarce resource.

0 0 0 114 0

Faisal Waris @fwaris7

2 years ago

GitHub Co-Pilot is *very* responsive. Not sure exactly how it works - but knowing something about LLMs - I can surmise they (MS) are running it on pretty beefy infrastructure.