{ "schema": "vqv.terminal.topic_page.v1", "generated_at": "2026-08-02T05:23:38.004649+00:00", "topic": { "slug": "open-source-llms", "name": "Open Source LLMs", "category": "open-source", "description": "Open weights, local models, model releases, and community inference stacks.", "url": "/t/open-source-llms/", "api_url": "/terminal/topics/open-source-llms/index.json", "total": 2, "counts": { "total": 2, "today": 0, "last_24h": 0, "last_7d": 2, "source_backed": 2, "watch": 0, "low_signal": 0, "latest_activity": "2026-07-29T14:45:05+00:00" }, "latest_activity": "2026-07-29T14:45:05+00:00", "page_count": 1, "page_size": 50, "connected_entity_counts": { "companies": 0, "models": 0, "products": 0 }, "public_event_count": 0 }, "pagination": { "page": 1, "page_size": 50, "page_count": 1, "signal_count": 2, "has_previous": false, "has_next": false, "previous_path": "", "next_path": "", "canonical_path": "/t/open-source-llms/" }, "signals": [ { "title": "Study on Developer Experience with Code Tours Generated by Open-Weight LLMs", "summary": "This study examines how developers interact with code tours\u2014interactive onboarding tools\u2014automatically generated and evaluated by open-weight large language models (LLMs) when debugging unfamiliar codebases. It focuses on developer experience and trust calibration, areas not previously explored in...", "why_it_matters": "Understanding how developers use and trust LLM-generated code tours can improve onboarding and debugging efficiency in unfamiliar codebases. Insights from this study can guide the design of better developer tools leveraging open-source LLMs.", "why_this_is_here": "Why this is here: This signal is recent, source-backed, and connected to activity readers are already following in Open Source LLMs.", "label": "SOURCE-BACKED", "signal_strength": 95, "score": 64.12, "public_interest": { "score": 22, "editorial_category": "OPEN SOURCE", "version": "v1", "reasons": [ "editorial category: OPEN SOURCE", "passes high signal-strength gate" ], "components": { "recognizable_entity_score": 0, "practical_impact_score": 28, "novelty_interest_score": 48, "consequence_score": 18, "curiosity_score": 0, "shareability_score": 42 } }, "what_this_means_for_you": "", "reader_depth": "TECHNICAL", "editorial_freshness": { "band": "archive-level", "age_hours": 86.64 }, "topic": { "name": "Open Source LLMs", "slug": "open-source-llms", "url": "/t/open-source-llms/" }, "source": { "name": "arXiv", "type": "arxiv", "domain": "arxiv.org", "url": "http://arxiv.org/abs/2607.26987v1", "source_page": "/source/arxiv/" }, "urls": { "signal_page": "/s/dtH1k/", "topic_anchor": "/t/open-source-llms/#signal-f2c9f39101", "short_url": "https://vqv.me/dtH1k" }, "share_text": "New research explores how developers experience and trust code tours generated by open-weight LLMs when debugging unfamiliar codebases.", "reposts": 0, "published_at": "2026-07-29T14:45:05+00:00", "fetched_at": "2026-08-02T05:20:18+00:00", "ai_assisted_summary": true, "id": "f2c9f39101", "url_hash": "81e6585c7ff4c393f57d485ef8c70abcba8706d8dbd31da543a5a12257aa9f96", "short_code": "dtH1k", "source_title": "How Developers Experience Debugging Unfamiliar Codebases with Code Tours Generated and Evaluated by Local LLMs", "source_snippet": "Code tours are interactive, onboarding documentation to guide developers through a codebase. Large Language Models (LLMs) can automatically synthesize code tours. Prior work on code tour generation has not studied developer experience or trust calibration when debugging unfamiliar codebases with code tours...", "seen_at": "2026-07-29T14:45:05+00:00", "prominence_tier": "primary", "buckets": { "companies": [], "models": [], "products": [], "topic": "open-source-llms", "reader_depth": "TECHNICAL", "editorial_category": "OPEN SOURCE" }, "display_seen_at": "2026-07-29 14:45 UTC", "is_early": false, "primary_action_url": "/s/dtH1k/", "primary_action_label": "Open signal", "source_action_label": "Original source", "copy_url": "https://vqv.me/dtH1k", "category": "OPEN SOURCE", "label_class": "source-backed" }, { "title": "Study on Prompt Scope and Demonstration Selection in LLM Machine Translation", "summary": "This paper examines how large language models perform machine translation when prompted with varying scopes, such as translating into multiple related languages or using example-based conditioning. It highlights the impact of prompt design and demonstration similarity on translation outcomes.", "why_it_matters": "Understanding how different prompt scopes and example selections affect LLM translation can improve their practical use as versatile translation tools. This insight helps optimize LLM prompts for more accurate and context-aware multilingual translations.", "why_this_is_here": "Why this is here: This signal is recent, source-backed, and connected to activity readers are already following in Open Source LLMs.", "label": "SOURCE-BACKED", "signal_strength": 95, "score": 66.08, "public_interest": { "score": 21, "editorial_category": "OPEN SOURCE", "version": "v1", "reasons": [ "editorial category: OPEN SOURCE", "passes high signal-strength gate" ], "components": { "recognizable_entity_score": 0, "practical_impact_score": 8, "novelty_interest_score": 48, "consequence_score": 18, "curiosity_score": 36, "shareability_score": 38 } }, "what_this_means_for_you": "", "reader_depth": "TECHNICAL", "editorial_freshness": { "band": "archive-level", "age_hours": 103.95 }, "topic": { "name": "Open Source LLMs", "slug": "open-source-llms", "url": "/t/open-source-llms/" }, "source": { "name": "arXiv", "type": "arxiv", "domain": "arxiv.org", "url": "http://arxiv.org/abs/2607.26286v1", "source_page": "/source/arxiv/" }, "urls": { "signal_page": "/s/tIgFu/", "topic_anchor": "/t/open-source-llms/#signal-0fe2943c22", "short_url": "https://vqv.me/tIgFu" }, "share_text": "New research explores how prompt scope and example selection influence large language models' machine translation performance across multiple languages.", "reposts": 0, "published_at": "2026-07-28T21:26:36+00:00", "fetched_at": "2026-08-02T05:20:18+00:00", "ai_assisted_summary": true, "id": "0fe2943c22", "url_hash": "abc1a7fa21011bfdc2bd01696221772ce7a7e02c89bd5d78c3e6e72cef582359", "short_code": "tIgFu", "source_title": "Evaluating Prompt Scope and Demonstration Similarity in Local LLM Machine Translation", "source_snippet": "Large language models (LLMs) are increasingly used as general-purpose translation systems, but their behavior is usually evaluated under a single prompt shape: translate one source sentence into one target language. In practice, users may ask for one target language, for several related languages at once, or for...", "seen_at": "2026-07-28T21:26:36+00:00", "prominence_tier": "primary", "buckets": { "companies": [], "models": [], "products": [], "topic": "open-source-llms", "reader_depth": "TECHNICAL", "editorial_category": "OPEN SOURCE" }, "display_seen_at": "2026-07-28 21:26 UTC", "is_early": false, "primary_action_url": "/s/tIgFu/", "primary_action_label": "Open signal", "source_action_label": "Original source", "copy_url": "https://vqv.me/tIgFu", "category": "OPEN SOURCE", "label_class": "source-backed" } ] }