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 ↗440 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
Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes ↗
A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow. Manually verifying whether a proposed no-code fix resolves the reported bug takes considerable developer time. This study proposes an automated, execution-based pipeline for evaluating the capability of large language models (LLMs) to generate no-code fixes in a real browser environment. We evaluate 322 no-code fixes generated by the 12 configurations released with the benchmark of a previous study, covering bug reports catego…
- Hacker News · Posted on Hacker News · First archived
Sub-1-Bit LLM Compression via Latent Factorization ↗
Hacker News discussion.
- arXiv · Published · First archived
Market Impact Estimation via Causal Foundation Models ↗
When a trader executes a large order, the relevant question is not \emph{what will the price be?} but \emph{what would the price have been had I not traded?} Market impact is thus a causal quantity, yet classical models (Almgren--Chriss, propagators) regress price on flow, which is biased whenever informed flow moves prices through information as well as trading. We present a proof-of-concept \emph{Causal Market Simulator}: a continuous-time causal prior-data fitted network (PFN) trained on a synthetic market prior in which a hidden informational flow confounds the flow--price relation by cons…
- Hacker News · Posted on Hacker News · First archived
Show HN: Gauze fixes (some) open-weight LLM deficiencies ↗
If you have worked with open-weight/local LLMs, you've known both the highs and the lows. Lows there are many: malformed response tags, empty responses, stuck loops, overthinking, inference engine errors and much more. You don't notice those when using commercial models, because the vendors iron out those quirks in their gateways, but you're left standing when using free models. Gauze is a transparent openai compatible gateway which monitors and…
- Hacker News · Posted on Hacker News · First archived
Show HN: Bot Bowl Bench – Benchmarking LLMs with Blood Bowl ↗
I wanted a meaningful benchmark for Mistral 4, and as a fan of Blood Bowl, I'm faintly aware that it's a hugely challenging game to build AI for... Hence the regular Bot Bowl[1] tournament, and now Bot Bowl Bench! I've kept it to cheap-ish models for now, but if people find it fun, might add Opus + Astra and see how they get on! [1] https://njustesen.github.io/botbowl/
- Hacker News · Posted on Hacker News · First archived
Show HN: LLM Fuzz CI ↗
Hi HN! Most of the explanation is in the blog post, and the code lives there: https://github.com/tiime-software/llm-fuzz-ci/ Happy to receive feedback, and to know how other people use agents to improve code security!
- Hacker News · Posted on Hacker News · First archived
Dear LLM, or how I stopped getting generic advice ↗
Hacker News discussion.
- GitHub · Repository created · First archived
OceanOver/Tomechat ↗
RAG knowledge-base chat app built on LangChain — FAISS vector search, FastAPI backend, Next.js WebUI, OpenAI/Gemini compatible
- Hacker News · Posted on Hacker News · First archived
How noisy are LLM evals in CI? ↗
Hacker News discussion.
- Hugging Face · Model / dataset date · First archived
AtesiT/ru-llm-judge-dataset — dataset update ↗
# RU-LLM-Judge-Dataset Датасет собирается инкрементально в течение нескольких сессий бесплатного Google Colab. Текущий объём: **24,692** суждений (по состоянию на последний запуск). ### Прогресс к цели (5,000 суждений) `[████████████████████]` 100% (24,692 / 5,000) ### История сессий сбора | Сессия | Дата | Добавлено | Итого | |--------|------|-----------|-------| | 1 | 2026-08-05 08:42 | 617 | 617 | | 2 | 2026-08-06 14:40 | 583 | 1,200 | | 3 | 2026-08-07 19:20 | 486 | 1,686 | | 4 | 2026-08-08 22:34 | 868 | 2,554 | | 5 | 2026-08-13 17:04 | 2,262 | 4,816 | | 6 | 2026-08-14 21:23 | 453 | 5,269 |
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.