Artem KK (@KazKozDev) header
Artem KK (@KazKozDev) profile picture

Making LLMs do what they're told

Barcelona
Joined June 2024
Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)Photo by Artem KK (@KazKozDev)
footnote-mcp v0.2.3 is out. MCP Registry, PyPI, GHCR, Glama. Zero-key search: SearXNG, Wikipedia, Crossr
1
14
Full CRUD for issues/projects/cycles, labels, workflows, dependency tracking, team queries. Safety-aware: reads unrestricted, writes require confirmation. MIT license. pip install abscissa-mcp
3
LLMFlow Search — local deep research where every claim is traced to its source. Five agents: planner → 3 parallel researchers → fact checker → writer → citation validator. SQLite evidence store. No API keys. github.com/KazKozDev/llmflow…
1
4
The writer is architecturally blocked from citing a source that didn't pass through the evidence store. Every citation resolves to a verified, stored page. Built on ollama (ornith:9b) + self-hosted SearXNG. Produces Markdown + letterhead PDF. MIT license.
26
Tested a customer support system prompt against 300+ adversarial attacks. 50% of authority bypasses worked. Base64 beat content filters. A simple roleplay prompt overrode every safety rule. Open-sourced my benchmark: github.com/KazKozDev/system-… #LLMSecurity #PromptInjection
41
Artem KK retweeted
7,200
13,265
866
156,610
21,490,360
Most agents don't fail because the model is dumb. They fail because the loop has no boundaries, memory is a mess, and nobody defined "done." Wrote about where agent architecture actually breaks. medium.com/@kazkozdev/agent-… #AIAgents #LLM #AIEngineering
197
New approach to train LLM agents using interactive ML tasks with online reinforcement learning, featuring exploration-enhanced fine-tuning, step-by-step RL, and an agent-specific reward module. arxiv.org/abs/2505.23723 #LLMTraining #ReinforcementLearning #AgentML
74
AlphaEvolve from Google DeepMind's automatically makes computer programs better by evolving them like species in nature. It doesn't just write code from scratch—it takes existing programs and evolves them into better versions. arxiv.org/pdf/2506.13131 #GoogleDeepnd #AlphaEvolve
59
Reducing AI hallucinations: "TruthPrInt" proposes a latent truthful-guided pre-intervention approach to mitigate object hallucination in Large Vision-Language Models. Building on insights from LLMs where internal states encode truthfulness, this method addresses a major challenge in multimodal AI trustworthiness. buff.ly/gYhzBOr #AITrust #MultimodalAI #HallucinationPrevention
60
Memory efficiency innovation: "KV-Distill" introduces a nearly lossless learnable context compression framework for LLMs. During generation, KV cache accounts for significant GPU memory usage. This solution distills representations to dramatically reduce memory requirements while maintaining performance on long contexts. buff.ly/dA6W6u7 #AIEfficiency #ModelCompression #LLMOptimization
45
Cognitive science meets AI: "LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns" investigates how LLMs handle Decisions from Experience tasks. While showing similar biases to humans (underweighting rare events), LLMs demonstrate fundamentally different learning trajectories, revealing insights about their decision processes. buff.ly/f8OlBkb #CognitiveAI #DecisionMaking #AIBehavior
39
"Copyright Law vs. AI: A Conceptual Conflict". Professor Craig identifies a fundamental contradiction between generative AI and copyright legislation. The research demonstrates that applying the concept of "authorship" to AI is erroneous, as authorship is inseparable from human intentionality. The author warns of reciprocal risks: AI may undermine copyright foundations, while strict regulation could impede AI development. This work advocates for creating a new legal paradigm to govern AI-generated content. buff.ly/ouusTmU #AILaw #Copyright #GenerativeAI
45
Mixtral LLMs Deliver Human-Comparable Evaluation for Question Answering Systems. Research reveals that Mixtral language models can effectively evaluate reading comprehension tasks through zero-shot prompting, outperforming traditional metrics and closely matching human judgment across multiple datasets. This approach requires minimal training data while providing accurate assessment for both Likert scale scoring and binary correctness evaluation, potentially eliminating costly human annotation processes in NLP development pipelines. buff.ly/ALaJgzV #LLMEvaluation #ReadingComprehension #NLPResearch
28
Healthcare AI research: "LLMs in Disease Diagnosis" compares DeepSeek-R1 and O3 Mini across chronic health conditions. The study evaluates predictive accuracy at both disease and category levels, showing how these models are revolutionizing medical diagnostics through enhanced classification and clinical decision support. buff.ly/iX5vIDm #MedicalAI #HealthTech #LLMDiagnostics
48
Advancing multilingual evaluation: "MMLU-ProX" introduces a comprehensive benchmark covering 13 typologically diverse languages with ~11,829 questions per language. Building on MMLU-Pro's reasoning-focused design, this framework addresses the gap in evaluating sophisticated language models across culturally diverse contexts. buff.ly/Tpn64u5 #NLP #MultililingualAI #AIBenchmarks
57