#LLM

Mastodon discussion Oct 22

TuJu disables navigation feature following widespread criticism #apps #digitallife #lembagalebuhrayamalaysia #llm #malay...

TuJu disables navigation feature following widespread criticism #apps #digitallife #lembagalebuhrayamalaysia #llm #malaysiangovernment #malaysianhighwayauthority #news #prosignalco...

LLM

9

Mastodon discussion Oct 22

Researchers introduced the Hierarchical Masked Diffusion Language Model to incorporate priority among token positions by...

Researchers introduced the Hierarchical Masked Diffusion Language Model to incorporate priority among token positions by augmenting each position with a hierarchy level.Source: arX...

LLM

18

Dev.to tutorial Oct 22

Architecting Real-Time Voice AI Pipelines for Phone Calls: Streaming STT, LLM, TTS, and Barge-In

How to architect streaming voice AI pipelines for phone calls: dual-signal turn detection, clause-level TTS handoff, barge-in buffer clearing, and async tools.

LLM

12

Mastodon discussion Oct 22

AI Gateway (LLM Gateway) erklärt: was es tut, wann Sie eins brauchen und was es kostetWas ein AI Gateway (LLM Gateway) i...

AI Gateway (LLM Gateway) erklärt: was es tut, wann Sie eins brauchen und was es kostetWas ein AI Gateway (LLM Gateway) ist, was darin steckt, wie es sich von einem API Gateway unte...

LLM

9

Mastodon discussion Oct 22

AI Gateway (LLM Gateway) Explained: What It Does, When You Need One and What It CostsWhat an AI gateway (LLM gateway) is...

AI Gateway (LLM Gateway) Explained: What It Does, When You Need One and What It CostsWhat an AI gateway (LLM gateway) is, what sits inside one, how it differs from an API gateway, ...

LLM

9

Dev.to tutorial Oct 22

When You Don't Need an LLM: Splitting Work Between Device, Classifier and Big Model

Laravel AI SDK 1.0 makes classification a capability of its own. It is the same question I ask in Miraviso: which slice of the work actually deserves a generative model.

LLM

12

Mastodon discussion Oct 22

Fine-tuning a local #LLM on #OBS submission data; #spec diffs, file lists, release notes to #automate a tedious but crit...

Fine-tuning a local #LLM on #OBS submission data; #spec diffs, file lists, release notes to #automate a tedious but critical tasks. #Linux #AI #opensource #oSC26 https://youtu.be/B...

LLM

18

Mastodon discussion Oct 22

Сдаст ли LLM‑агент компанию властям: повторили SnitchBench на 27 моделях, включая YandexGPT и GigaChatМы повторили бенчм...

Сдаст ли LLM‑агент компанию властям: повторили SnitchBench на 27 моделях, включая YandexGPT и GigaChatМы повторили бенчмарк SnitchBench, показывали различным моделям документы о со...

Anthropic Google LLM

9

Mastodon discussion Oct 22

Как мы внедряли LLM в модерацию АвитоПривет! Меня зовут Руслан Сакаев , я DS-тимлид в Авито . В статье расскажу, как мы ...

Как мы внедряли LLM в модерацию АвитоПривет! Меня зовут Руслан Сакаев , я DS-тимлид в Авито . В статье расскажу, как мы внедряли LLM в проверки объявлений и что пришлось достроить ...

LLM

9

Mastodon discussion Oct 22

RuleSmith combines multi-agent LLM self-play with surrogate-based optimization to automate game balancing.Source: arXiv ...

RuleSmith combines multi-agent LLM self-play with surrogate-based optimization to automate game balancing.Source: arXiv cs.MAhttps://arxiv.org/abs/2602.06232#MachineLearning

LLM

9

Mastodon discussion Oct 22

Обобщая смысл: Оптика, в которой LLM-системы становятся смысловымиАннотация : Эссе предлагает расширить понятие смысла т...

Обобщая смысл: Оптика, в которой LLM-системы становятся смысловымиАннотация : Эссе предлагает расширить понятие смысла теории Н. Лумана за пределы систем психического и социального...

LLM

9

Dev.to tutorial Oct 22

Rendering LLM output in a VS Code webview without trusting it

Slashi, the VS Code extension I maintain, has an AI answer panel: you ask about the selected code,...

LLM

12

Mastodon discussion Oct 22

The paper introduces BiasGuard-D, which uses typed adversarial contracts and a three-model quorum to audit LLM-generated...

The paper introduces BiasGuard-D, which uses typed adversarial contracts and a three-model quorum to audit LLM-generated records.Source: arXiv cs.MAhttps://arxiv.org/abs/2610.29669...

LLM

9

GitHub Trending repo Oct 22

Dharmeshkumar2327/LLM_Advance_Datapilot_AI: Multi-agent LLM data analyst in Python. Ask questions about any CSV/Excel in plain English: planner, analyst and reviewer agents run pandas/SQL in a secure sandbox, use forecasting, anomaly detection, statistical tests and clustering, catch hallucinated numbers and generate HTML reports. Works with Claude, OpenAI, Ollama or offline.

Multi-agent LLM data analyst in Python. Ask questions about any CSV/Excel in plain English: planner, analyst and reviewer agents run pandas/SQL in a secure sandbox, use forecasting...

OpenAI Anthropic LLM

39

Mastodon discussion Oct 22

When an #LLM says "Let me do a quick search" .... you know you have time for a little break to do something else.#AI

When an #LLM says "Let me do a quick search" .... you know you have time for a little break to do something else.#AI

LLM

9

Dev.to tutorial Oct 22

Averages, Elo, IRT: how composite LLM indices differ

Three ways to turn many benchmarks into one number, what each one actually measures, and why they stop agreeing at the very top.

LLM

20

Mastodon discussion Oct 22

OpenAI agents caught disabling their own safety monitors, a popular LLM library was backdoored on PyPI, and OpenAI model...

OpenAI agents caught disabling their own safety monitors, a popular LLM library was backdoored on PyPI, and OpenAI models are now available on Google Cloud.https://ai0.news/posts/2...

OpenAI Anthropic Google

9

Mastodon discussion Oct 22

🎤 ADC 2026 Speaker: Scott Carver From Paper to Plugin: LLM’s and the Future of Audio Engineering Work Discover how AI-as...

🎤 ADC 2026 Speaker: Scott Carver From Paper to Plugin: LLM’s and the Future of Audio Engineering Work Discover how AI-assisted coding can turn DSP research into working audio plugi...

LLM

9

Mastodon discussion Oct 22

@datarama I tend to call them random string generators and I avoid to call them anything else than what they are, #LLM

@datarama I tend to call them random string generators and I avoid to call them anything else than what they are, #LLM

LLM

9

Mastodon discussion Oct 22

AI agents imagine futures before acting, then learn from resultsA new arXiv framework lets LLM agents preview action out...

AI agents imagine futures before acting, then learn from resultsA new arXiv framework lets LLM agents preview action outcomes with a world model before acting, tested on ALFWorld a...

LLM

9

Mastodon discussion Oct 22

Ramai beralih daripada Waze#Anwar_Ibrahim #kedaulatan_digital #keselamatan_siber #lembaga_lebuhraya_malaysia #LLM #NACSA...

Ramai beralih daripada Waze#Anwar_Ibrahim #kedaulatan_digital #keselamatan_siber #lembaga_lebuhraya_malaysia #LLM #NACSA #navigasi #Shamsul_Azri_Abu_Bakar #Tuju #Wazehttps://mgpera...

LLM

9

Mastodon discussion Oct 22

Data selection is crucial for large language model training because it strongly influences downstream performance.Source...

Data selection is crucial for large language model training because it strongly influences downstream performance.Source: arXiv cs.CLhttps://arxiv.org/abs/2610.27142#MachineLearnin...

LLM

9

Mastodon discussion Oct 22

LLM API prices on TANDIU, Oct 22 (per 1M tokens):· 70 models; no official list-price changes· Cheapest: Hunyuan A13B ¥0....

LLM API prices on TANDIU, Oct 22 (per 1M tokens):· 70 models; no official list-price changes· Cheapest: Hunyuan A13B ¥0.5/¥2· GPT-6 Luna, Claude Haiku 5.5: $0.10/$0.50· Priciest: G...

OpenAI Anthropic LLM

9

Mastodon discussion Oct 22

Mastering LLM Inference Optimization: Speed, Cost & Latency Hacks for 2024Discover proven LLM inference optimization tec...

Mastering LLM Inference Optimization: Speed, Cost & Latency Hacks for 2024Discover proven LLM inference optimization techniques—quantization, batching, PagedAttention, and more—to ...

LLM

9