Topics /
LLM RSS Feeds
2 feeds from 2 sites tagged “LLM”. Follow one here, or copy its address into any RSS reader.
- 1Towards Data SciencePublish AI, ML & data-science insights to a global community of data professionals.Last post 8 Nov
- 2AIToolStack releasesDated public releases for tools on the AIToolStack list, linked to the official announcement.Last post 4 Nov
Follow the whole topic
The newest LLM posts from across the directory as one feed, for any reader:
Latest LLM posts
LLM Rate Limits: Your Retry Loop Is the Easy Part
The first time an LLM feature hits real traffic, the logs fill with 429s and somebody writes a retry loop. It usually looks like the one from the last REST API they integrated: catch the error, sleep, try again, maybe double the sleep. It ships, the errors drop, and everyone moves on. Then the bill…
I dumped semantic i18n keys. Now the source text itself is the key — and LLMs do the rest.
The thing everyone does (and why we stopped) If you've ever built a non-trivial UI in a second language, you've written code like this: t ( ' features.localeFiles.title ' ) t ( ' features.localeFiles.description ' ) Semantic keys. Dot-separated, namespaced, "proper". It's the pattern every i18n…
Change One Monty Hall Rule and Five LLMs Still Say Switch
Even with step-by-step reasoning, the models landed near 33% accuracy, and one quoted the host's rule correctly before ignoring it. The post Change One Monty Hall Rule and Five LLMs Still Say Switch appeared first on Towards Data Science .
Meta、MuseとMeta AI向け特化モデルを展開。記憶の選別と作業継続を強化
Metaは「Muse Wonder」で訓練した特化モデルをMuseとMeta AIに展開し始めた。過去の会話から有効な条件を見分け、想定外の問題が起きても別の方法で作業を続けるよう訓練した。途中の指示変更への対応も強化している。
My local LLM turns my voice notes into to-do items automatically, and nothing falls through the cracks
No more losing my half-formed ideas
Inkling 2 Small、5940億パラメータMoEで来週のApache 2.0公開を計画
OpenAI元CTOミラ・ムラティ氏率いるThinking Machines Labが第2世代AI「Inkling 2 Small」を発表。5940億パラメータのMoEで前世代より性能を上げ、来週のApache 2.0公開を計画している。
Why a Tiny GPT Can Know Two Facts and Still Not Connect Them
A tiny GPT memorized every fact I gave it, then couldn’t answer a single question that needed two of them. I tested the one-line fix from a recent paper, and it only half worked. The post Why a Tiny GPT Can Know Two Facts and Still Not Connect Them appeared first on Towards Data Science .
datasette-llm 0.1a10
Release: datasette-llm 0.1a10 Fixes a bug that affected my agent.datasette.io demo site, where the set of available LLM models was not correctly restricted to just those in the configuration. Tags: datasette , llm
Tencent Hy4
Tencent announced Hy4, an open-source model with visual understanding and computer use. The announcement says the API is approximately $0.90 per million input tokens and $2.70 per million output tokens, and that weights and system cards are planned in the coming days. Performance comparisons on…
I let AI build. I don’t let AI decide.
A long workbench split down the middle, finished tools stacked on one side and a single open notebook on the other. My list of tasks I give models without a second thought and what I review until the tools evolve. I’ve used generative models for almost four years and designed machine learning…
llm 0.37.1
Release: llm 0.37.1 A bugfix release for LLM , with contributions from Steven Huang , Tao An , Arjan Mossel , and XQ . Tags: llm
The best speech recognition you can run at home is absolutely tiny, and it runs on a ten-year-old laptop
Parakeet is a tiny speech recognition model that transcribes on a ten-year-old laptop with no subscription
Berhenti Menghitung Token, Mulai Menghitung Kode yang Ter-deploy: Mengubah Ekonomi AI Coding
Biaya token AI coding melonjak 10-50x dibanding chat biasa. Artikel ini membahas mengapa metrik cost per merged PR lebih baik dari cost per token, dan bagaimana model hybrid (frontier API + kapasitas sendiri) mengubah ekonomi pengembangan perangkat lunak.
Era Web Agentic Telah Tiba: AI Otonom Mengambil Alih Navigasi Internet
Visi Tim Berners-Lee tentang web semantik terwujud lewat agen AI berbasis LLM yang bisa browsing, booking, dan bertindak atas nama pengguna — mengubah struktur internet fundamental.
Meituan LongCat-2.5
Meituan released LongCat-2.5, a native multimodal model for long-horizon agent tasks, with 1.6 trillion total parameters. The company says people can try it at longcat.ai and developers can call it through an API. Vendor source: https://www.meituan.com/news/NN261102280001343
DIY WiFi Analyzer Sniffs Out Congestion and Coverage Issues, Suggests Fixes
[Roni Bandini]’s JEV WiFi Analyzer is an interesting experiment that glues together a single-board Linux computer, a USB WiFi adapter, and a specialized AI model to create a new kind …read more
An AI Chatbot for the Apocalypse
You don’t have to be a full-on “prepper” to at least occasionally wonder what would happen if civilization collapsed. One thing you probably couldn’t do is go on the Internet …read more
AI helped me automate some of my wealth advisor job. Here's why I'm not worried about it stealing my edge.
Rick Nott has used AI to save hundreds of tedious hours uploading documents for his clients. Here's why he's not worried about Claude taking over.
What Is Model Distillation? A Guide for Developers
Over time, knowledge has been passed down in various forms. Before writing was invented in ancient Mesopotamia (modern-day Iraq), laws, history, myths, songs, and other information were all transferre
AI Moral Decision-Making
LLM-based AI models are being increasingly used by physicians to assist clinical decision-making. What might their effect on medical moral reasoning be? The post AI Moral Decision-Making first appeared on Science-Based Medicine .
