Faisal Waris

Gen. AI strategist; AI/ML researcher

[Faisal Waris @fwaris7]

@lateinteraction @raphaelsrty @antoine_chaffin @LightOnIO colbert style indexing and search running on the phone using a distilled onnx model .

https://t.co/MoRwH8wjSz

https://t.co/mWDOdSxr3F

[Faisal Waris @fwaris7]

@gdb @gdb
FsVoice is a platform for buiding 'conversational apps' with gpt-realtime and other gpt models. Supports mobile, web and SIP-based deployments.

https://t.co/rYetPWVOZr

[Faisal Waris @fwaris7]

@yminsky Note API's (not LLMs) already use grammar-induced sampling for JSON-(Schema).

However, models are so good at code gen that this is not really needed. General lang. knowledge + context is sufficient.

But for online gens (no human in loop) - need proof to fully trust code.

[Faisal Waris @fwaris7]

@yminsky Working on proof-oriented validation of agentic/llm-generated output via 'dependent' types of F* (ocaml / F# related).

LLM generates F* code from non-deterministic 'context' which is 'proven' (via Z3) against pre-defined types. Works quite well in practice! - paper soon.

[Faisal Waris @fwaris7]

FSharp.DI is a thin wrapper over .Net Dependency Injection (logging / services) that should enable easy/consistent use of DI from F# functional code.

https://t.co/39Ot7Bqg9P

[OpenAI @OpenAI]

Introducing GPT-Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine.

[Charly Wargnier @DataChaz]

🚨 This is absolute GOLD.

The @AnthropicAI engineer who literally wrote "Building Effective Agents" just dropped a 14-minute masterclass.

saves you months of headaches trying to figure this out alone.

bookmark for the weekend + read @Av1dlive's great guide below 👇

[Faisal Waris @fwaris7]

@stephen_wolfram Some evidence of discretization of reality (from metaphysics)

https://t.co/m7dhIVPG8k

[Faisal Waris @fwaris7]

@headinthebox I am on a similar track. Using dependently-typed f-star for 'provably' correct LLM generated content to enable trustworthy agents.
(PS the theory goes back a 100+ years if you start with Boole & Frege and end with LEAN 4 - I am reading "The Laws of Thought" by Griffiths)

[Faisal Waris @fwaris7]

Making GEPA interpretable with VISTA https://t.co/lopXz41luY
[F#-based prompt optimizer enhanced with the VISTA algorithm.]

[Faisal Waris @fwaris7]

@GabriellaG439 actually it should be dependently type languages instead - e.g. LEAN, Idris, F*, etc.

[Faisal Waris @fwaris7]

@headinthebox We are in a new paradigm. Generated code is probabilistically correct with ever increasing probability of correctness.

Will need new methods for trusting software - akin to 'quantum error correction'. I believe formal verification/proofs will play a larger role.

[Faisal Waris @fwaris7]

My F#/Prolog 'logic-RAG' voice bot project got featured at the Microsoft .NET blog
https://t.co/bNknT1rJxR

[Faisal Waris @fwaris7]

@rickasaurus I found 5.2 answers confusing as well. Sticking with 5.1 for now

[Lee Smart @VFD_org]

Biology doesn’t compute the way our current AI systems assume.

Neurons aren’t static units. They operate across multiple scales, electrical, mechanical, structural, and quantum-timing, all interacting in real time.

Recent neuroscience points to:
• fractal dendritic integration
• phase-dependent computation in local microdomains
• microtubule-scale vibrational timing structures
• multi-scale electromechanical coupling inside neurons
• nested oscillatory hierarchies coordinating local and global processing

These are not captured by today’s neural networks.
If AI is going to move beyond statistical pattern matching toward true natural-intelligence behaviors, we need models that reflect:

multi-scale geometry, recursive timing structure, and intrinsic dynamical complexity, not just more layers and parameters.

This isn’t about copying biology literally;
it’s about understanding the computational principles biology actually uses.

The next step is to model the right dynamics.

@AllenInstitute @mitbrainandcog @stanfordneuro @NeuroCellPress @NatureNeuro
@HumanBrainProj @CIFARnews @MetaAI @DeepMind @googledeepmind @drmichaellevin @MITNeuro @MurrayShanahan @KordingLab

[Faisal Waris @fwaris7]

@avsm @PrologInfo
GenAI meets Symbolic AI
https://t.co/C37lYtUe1u

[Faisal Waris @fwaris7]

@avsm My suggestion is to try codex also. I found it better for F# and Prolog code gen than Sonnet 4.5 (have not tried Opus yet).

Additionally codex seems to be pretty decent with F*, a dependently typed language based in OCaml.

[Nick Palladinos @NickPalladinos]

A Pair of tricks - Oleg Kiselyov
https://t.co/tgqqWtlPM2

[Faisal Waris @fwaris7]

GenAI meets old school Symbolic AI
https://t.co/zuLwkWxR4p

[Faisal Waris @fwaris7]

OpenAI Codex (preview) is the best code gen model I have used thus for F# code gen. (Sonnet 4.5 is not at the same level).

Did a flawless job of creating Fabulous-Maui bindings for a new Maui controls lib. See:

https://t.co/aGFZhTorwq