How do pl2js and Tau Prolog compare?

How do pl2js and Tau Prolog compare?

ChatGPT: Here’s a clear, engineering-level comparison between your pl2js concept/repo and Tau Prolog:

⸻

🧠 Core Difference (1 sentence)
• pl2js = compiler/translator (Prolog → JS code)
• Tau Prolog = interpreter/runtime (executes Prolog directly in JS)

⸻

⚙️ Architecture Comparison

1. Execution Model

Tau Prolog
• Interprets Prolog at runtime
• Uses a Prolog engine implemented in JavaScript
• Backtracking, unification, etc. are simulated dynamically
• Non-blocking, callback-based execution model 

pl2js (your design direction)
• Ahead-of-time conversion
• Prolog → explicit JS control flow
• loops instead of backtracking
• if/else instead of clause selection
• Similar philosophy to your pl2c:
• remove interpreter overhead
• flatten logic into imperative structures

👉 Key insight:
• Tau = simulate Prolog
• pl2js = eliminate Prolog

⸻

🚀 2. Performance Philosophy

Tau Prolog
• Slower (interpretive overhead)
• Flexible and dynamic
• Handles general Prolog features (ISO-oriented) 

pl2js
• Potentially much faster
• Precompiled logic → direct execution
• Can optimise:
• repeated calls → functions
• choice points → loops
• data reuse → cached variables

👉 Your system aligns with:

“manual neuronet optimisation” + “Spec → Algorithm flattening”

⸻

🧩 3. Feature Completeness

Tau Prolog
• Designed toward ISO Prolog compliance 
• Supports:
• modules
• DCGs
• meta-predicates
• async predicates
• DOM interaction

pl2js
• Likely:
• partial Prolog subset
• depends on what you convert
• Harder features:
• cut (!)
• dynamic predicates (assertz)
• meta-programming
• full unification edge cases

👉 Trade-off:
• Tau = completeness
• pl2js = controllable subset + optimisation

⸻

🌐 4. Web Integration

Tau Prolog
• Native browser integration:
• manipulate DOM from Prolog
• event handling 
• Drop-in script usage

pl2js
• Output is plain JavaScript
• Integrates like any JS:
• React / HTML / mobile
• Better for:
• embedding in apps
• mobile (your goal: iPhone/Android)

⸻

🧪 5. Debugging & Transparency

Tau Prolog
• Debugging = Prolog-level
• Harder to inspect internal execution (black-box engine)

pl2js
• Debugging = JavaScript-level
• You can:
• log intermediate states
• inspect variables
• trace execution paths

👉 This aligns strongly with your:
• transparent MNN philosophy
• “no invisible bugs” goal

⸻

🧱 6. Control Over Execution

Tau Prolog
• Engine decides:
• backtracking order
• search strategy

pl2js
• YOU decide:
• loop structure
• branching
• memory usage
• determinism

👉 This is huge for:
• CI/CD
• deterministic systems
• optimisation pipelines

⸻

⸻

🧠 Strategic Insight (Important for Your Project)

Your system (pl2js) is not competing directly with Tau Prolog.

Instead:

Tau Prolog = “Prolog runtime for the web”

pl2js = “Prolog → optimised algorithm generator”

👉 In your ecosystem:
• Tau Prolog = execution layer
• pl2js = optimisation + deployment layer

⸻

🔥 Recommendation (based on your goals)

Given your:
• Spec → Algorithm vision
• MNN transparency goals
• CI/CD system (Lucian CI/CD)

👉 pl2js is the more aligned direction

Use Tau Prolog only if you need:
• quick prototyping
• full Prolog compatibility
• teaching/demo environments

⸻

💡 Advanced Hybrid Idea (Very Relevant to You)

You could combine both:
1. Prototype logic in Tau Prolog
2. Convert stable predicates via pl2js
3. Optimise with:
• Gaussian elimination
• recursion flattening
4. Deploy as pure JS

👉 This becomes:
Interpreter → Compiler → Optimiser pipeline