John Smith's picture
In a Training Loop 🔄

John Smith PRO

John6666

AI & ML interests

None yet

Recent Activity

reacted to unmodeled-tyler's post with 👍 about 4 hours ago
NEW MODEL: https://huggingface.co/vanta-research/mox-tiny-1 Excited to share the first model from the new Mox-1 model family from VANTA Research! Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction. Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically. Domains include but not limited to: - Direct opinions (clear stances on various topics) - Constructive disagreement (Pushing back on flawed premises) - Epistemic confidence (calibrated certainty and uncertainty) - Warmth & presence (Empathetic, human responses) - Wonder & puzzlement (Intellectual curiosity) Interaction Examples: Direct opinions: ```python User: What's the best programming language? Mox: That question doesn't have a context-free answer, and anyone who gives you one is either selling something or hasn't worked on enough different problems. But I'll give you my actual take across contexts: Python for rapid prototyping and data work, Rust for systems programming where correctness matters, TypeScript for web development... ``` Warmth & Humor: ```python User: I've been debugging this issue for six hours. Mox: At hour six, you've entered the part of debugging where the bug isn't in your code anymore - it's in your understanding of reality itself. The semicolon starts looking suspicious. Show me what you're dealing with. Fresh eyes help, and mine haven't been staring at it since lunch. ``` Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!
reacted to kanaria007's post with ❤️ about 4 hours ago
✅ New Article: *Observations, Under-Observation, and Repair Loops* (v0.1) Title: 👁️ Observations, Under-Observation, and Repair Loops: The OBS Cookbook for SI-Core 🔗 https://huggingface.co/blog/kanaria007/observations-under-observation --- Summary: SI-Core’s rule is simple: *No effectful Jump without PARSED observations.* This article turns that slogan into an operational design: define *observation units* (sem_type/scope/status/confidence/backing_refs), detect *under-observation* (missing / degraded / biased), and run *repair loops* instead of “jumping in the dark.” Key clarification: under-observed conditions may still run *read / eval_pre / jump-sandbox*, but must not commit or publish (sandbox: `publish_result=false`, `memory_writes=disabled`). --- Why It Matters: • Prevents “we had logs, so we had context” failures: *logs ≠ observations* unless typed + contract-checked • Makes safety real: even PARSED observations should be gated by *coverage/confidence minima* (declared thresholds) • Turns OBS into something measurable: *SCover_obs + SInt* become “OBS health” and safe-mode triggers • Links semantic compression to reality: distinguish *missing raw* vs *compression loss*, and fix the right thing --- What’s Inside: • A practical observation-status taxonomy: `PARSED / DEGRADED / STUB / ESTIMATED / MISSING / REDACTED / INVALID` (+ mapping to core status) • Per-jump *observation contracts* (required sem_types, allowed statuses, age/confidence limits) + explicit fallback actions • Fallback patterns: *safe-mode / conservative default / sandbox-only / human-in-loop* • Repair loops as first-class: ledgered `obs.repair_request`, PLB proposals, governance review for contract changes • Testing OBS itself: property tests, chaos drills, golden-diff for observation streams --- 📖 Structured Intelligence Engineering Series this is the *“how to operate OBS”* layer—so the system can *know when it doesn’t know* and repair over time.
View all activity

Organizations

Glide's profile picture open/ acc's profile picture Solving Real World Problems's profile picture FashionStash Group meeting's profile picture No More Copyright's profile picture XORTRON - Criminal Computing's profile picture