Zhemal Khamidun
Head of AI at Alpina Digital, CPO of AlpinaGPT (~30-person engineering & AI team). Founder of Vibe Academy & Hamidun Consulting, author of the AI channel «Готовим ИИшницу» (@jemal_hamidun).
Utterance Normalization Cuts the Cost of Analyzing Millions of Calls: A Pipeline Built Entirely on Small Models
Text autoencoder compresses web text to 2.24 bits per byte without losing meaning
Cognitive Thermometers: Neural Networks Proposed as a Way to Measure the Complexity of Meaning
LLMs Draft Road-Work Plans for WisDOT: 14B Barely Beats 7B
Researchers fine-tuned open models on the WisTMP archive and ran them locally. Quality improved, but 14B gained little over 7B/8B, and cost estimates remain a weak…
Wieszcz-XIX: A 3.1-Billion-Word Polish Corpus From Before 1918 Trains Models From Scratch
Researchers collected 294 369 Polish press documents from 1800–1918 and trained models from 47M to 349M parameters from scratch. The models know post-1918…
Diffu-LoRA Lets the Adapter Decide Which Stable Diffusion Layers Need Rank
A new method for personalizing diffusion models allocates LoRA rank across layers using learnable gates and pruning. Tested on Stable Diffusion and DreamBooth sets.
An LLM Teaches a Planner to Get by With Polynomial Memory and Solves 1709 of 1890 Tasks
StoreBench: LLM Agents Run an Online Store and Lose to a Script — 49% vs. 97%
LLM Agents Don't Learn Community Norms From Interaction, Study Finds
Qwen3.6-27B and Qwen3-4B Agents Blow Their Time Budgets Without Harness Hints
Keyframe Mnemonics Teaches Robots to Remember What Matters: 100% Success on Long Horizons
A self-supervised method picks keyframes for behavior cloning: +13.9 pp success on 23 manipulation tasks and 80% SR on a real robot at a horizon 20x longer.
Plan-and-Patch: Diffusion LLM Repairs Agent Plans Twice as Often as Qwen3-8B
The diffusion-based DreamReasoner-8B repairs agent plans with a 53.7% success rate versus 27.0% for Qwen3-8B, and after fine-tuning it generates plans 39–46% faster.
TGIT Translates Short Drone Commands and Lifts Navigation Success from 11% to 33%
Agent strikes out its own old tool outputs and cuts input tokens by half
Credit AI Agent Can Only Change Its Harness: Gate Admitted 144 of 7,449 Edits
arXiv Authors Bound Agent Self-Improvement by Verification Class
Simon Willison releases ttok 0.4: the token counter gets --list-models
The first update to the ttok CLI tool in about two years fixes a Click warning, refreshes CI, and adds a --list-models command that lists available models.
Snyk turns its internal support agent into a customer-facing feature, Snyk Assist
Snyk has opened up to customers an agent that previously helped only its own support team. Snyk Assist is built on three tools: LangChain, LangGraph and LangSmith.