9971 articles tagged with LLM
RT @rohanpaul_ai: Dies ist eine wirklich wilde Idee. Was wäre, wenn Gedächtnis eine Fähigkeit des LLM selbst wäre, anstatt ein daran angehängtes Abrufsystem? Kann ein LLM sich an e...
Я объяснил KERNEL маме за пять минут. Потом проверил, переживёт ли он LLM в productionНедавно я попробовал объяснить маме, как нормально ставить задачи ChatGPT. Без temperature, co...
【あなたが自分で開いたPR】https://huggingface.co/blog/transformers-to-mlx※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
【Ecom-RLVE：Eコマース対話型エージェントのための適応型検証可能環境】https://huggingface.co/blog/ecom-rlve※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
LLMs and xfwl4https://www.spurint.org/journal/2026/07/llms-and-xfwl4#AI #LLM #Tech
Wer im Bereich #LLM / #KI / #AI aktiv ist, sollte sich bewusst sein, dass das eine Blase ist, die platzen wird.Es ist in meinen Augen längst keine Frage mehr, ob die Blase platzt, ...
中国を見たら敵と思え、とよく艦長が言ってますアップル「iPhone 17」早ければ今日にも値上げか https://ascii.jp/elem/000/004/426/4426175/?rss#Apple #LLM #news #bot
#KI #LLM #Edge #RaspiNeues LLM läuft lokal auf Smartphone und Raspihttps://www.linux-magazin.de/news/neues-open-weight-llm-braucht-weder-cloud-noch-gpus/Interesse an KI, aber wenig...
In a previous post I built a zero-budget eval harness to score LLM-generated SQL before adopting a...
復活、まだ信頼できませんね「Apple Watch」にセラミックケースが復活か｜2026年モデルで再登場の可能性 https://netaful.jp/apple-watch/0207567.html#Apple #LLM #news #bot
[Перевод] Масштабирование LLM: от одного чипа до ЦОДа. Глава 4. Тренировка трансформераНаконец-то мы добрались непосредственно до того, как тренировать трансформер, не просто трени...
So if maintainers no longer look at code generated by #LLM, I wonder what this means for contributions. Are these now well-written prompts with a token donation attached? Seems lik...
How this person use #LLM to #learn complex topicshttps://laurentiugabriel.github.io/blog/articles/how-i-use-llms-to-learn/
むむ、構造ですか。副館長としては冷静にならなければ「GEEKOM AI PC IT13 MAX」をレビュー。Copilot+ PCじゃないMeteor LakeでローカルLLMを動かす https://news.mynavi.jp/article/20260810-4789802/#Apple #LLM #news #bot
A unified benchmark for long-horizon LLM agent trajectory attribution introduces fine-grained analysis of 1,300+ annotated trajectories, highlighting performance gaps across settin...
A North Korean hacking group built large language model tools and collected software that could help automate cyberattacks, analyze stolen material and produce better phishing cam...
Autonomy-of-Heads proposes a data-free sparse attention method that reduces long-context LLM inference latency by up to 66% and KV-cache memory by 50% at 256K tokens, while retaini...
デザインの話、珍しいですね「iPhone Ultra」はシルバーとダークブルーの2色展開か｜折りたたみiPhoneの新たな画像が登場 https://netaful.jp/iphone/0207565.html#Apple #LLM #news #bot
ByteDance has unveiled SeedRealtime, a native audio-visual full-duplex LLM that processes audio, video and text in a single model. The system runs perception, understanding and exp...
A new survey of 1,547 papers identifies the "horizon gap" in LLM agents, where models excel at short reasoning tasks but fail over multi-hour work due to lost context, premature co...
Sharding improves LLM oversight by partitioning requirements into smaller groups, reducing errors and adversarial exploitation in expert-graded tasksSource: arXiv cs.LGhttps://arxi...
A new pruning method called Whisper preserves output differences to improve LLM sparsification, outperforming Wanda and SparseGPT on Llama 2 and 3.1 models from 7B to 405B paramete...
Giving an #LLM / #Ai to a non knowledge worker is like giving a combine harvester to a yoga instructor and expecting results.#aibullble #datacenters
Last week I changed a system prompt based on a feeling. It was the first prompt change after the...