THE INTERNET IS THINKING
Earlier sources: Language models
Language models learn patterns in text and other representations to predict or generate sequences. Follow model releases, training methods, reasoning, evaluation, and deployment research; a benchmark result is specific to its test conditions.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗437 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- arXiv · Published · First archived
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory ↗
Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge storage from general-purpose computation, offering a promising route to updating factual knowledge while keeping the Transformer backbone fixed. Realizing this potential is challenging because different expressions of a fact may activate different n-gram embeddings, while updating shared embeddings c…
- arXiv · Published · First archived
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models ↗
Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem for decades. It judges survey responses without knowing the true value, through a framework of validity and related concepts: content, construct, and criterion validity, reliability, incentive compatibility, and consequentiality. We argue that this framework is a general method for evaluating language models, and we set out what each concept means for LLM evalu…
- arXiv · Published · First archived
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs ↗
Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled benchmark for behaviorally structured PHR across four domains and 18 large language models. PHRBench characterizes each reasoning trajectory independently of final-answer correctness throug…
- Hacker News · Posted on Hacker News · First archived
Show HN: I made a desktop pet that uses LLM for voice and Jev for poses ↗
This desktop pet uses Gemini Live and GPT realtime for realtime conversation, and jev for model pose control. Check the github for how to create a controllable model.
- arXiv · Published · First archived
Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures ↗
Context: Once defined a taxonomy of stages structuring Machine Learning (ML) pipelines (e.g. Data Preprocessing, Modeling...), extracting these stages from source code is key for better understanding ML practices. However, the diversity caused by the constant evolution of ML (e.g., algorithms, datasets) makes this task challenging. Existing approaches either rely on non-scalable manual labeling or on classifiers that do not properly support domain's diversity. These limitations call for more reliable solutions. Objective: We evaluate whether Small Language Models (SLMs) can leverage their code…
- GitHub · Repository created · First archived
Zoria-Lind/cc-token-optimizer ↗
Cut your Claude Code token bill: tool-output trimming, read dedup, model-tier discipline, and live cost + cache-hit stats.
- Hacker News · Posted on Hacker News · First archived
Flux – Compile an LLM to your hardware, then serve it ↗
Hacker News discussion.
- GitHub · Repository created · First archived
EvilFreelancer/tgfake ↗
Offline Telegram Bot API for testing bots, Mini Apps and LLM integrations.
- arXiv · Published · First archived
On the Reliability of LLM-Based Vulnerability Patching Benchmarks ↗
Large language models (LLMs) have shown strong potential for automated vulnerability patching, but current benchmarks can substantially distort reported performance. Drawing on extensive experience developing, running, and stress-testing such frameworks, we identify under-examined pitfalls across three dimensions: (1) agent-level factors, where prompting, tool availability, and detailed instructions can raise success rates without improving developer-aligned patch quality; (2) framework-level factors, where permission errors, infrastructure bugs, and timeout handling can silently suppress or i…
- Hacker News · Posted on Hacker News · First archived
Show HN: InBrief – open-source AI news aggregator with LLM filtering ↗
Hacker News discussion.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Language models
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.