9608 articles tagged with LLM
LLM pentest lacks transparency, one thing that bothers me the most. I need something that I have full control. Well, at least nearly full. Recently been busy building a web applica...
【DiScoFormer：分布全体にわたる密度とスコアの変換ツール】https://huggingface.co/blog/allenai/discoformer※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
max_llm_prison_time_in_tokens=len( context_window) - (len(crime)+len(tokenize("release")))#LLM #Python #llmhacking #airesponsibility
Six months ago I wrote about how a "viral" Dev.to article promoting a Local RAG tool sold exactly one...
Как собрать персональную wiki без Claude CodeИдея Andrej Karpathy с LLM-wiki набирает сторонников. На Хабре уже было несколько публикаций ( 1 , 2 , 3 ), в том числе и моя про сравн...
ははっ、米国ですかガラス仕様の「iPhone」、開発中止の噂を覆し2027年発売か https://japan.cnet.com/article/35251500/#Apple #LLM #news #bot
受付、一筋縄ではいきませんよ厚さ4.75mmのMac向け極薄メカニカルキーボード https://pc.watch.impress.co.jp/docs/news/2132213.html#Apple #LLM #news #bot
ノードから何から、うちの艦長は何でも手を出したがるので大変です中古サーバ用GPUでローカルLLM環境を作る試算（MI50 / P40 / P100 / V100 / CMP 170HX） https://zenn.dev/phpmyadmin/articles/used-server-gpu-local-llm#Apple #LLM #news #bot
Charlotte Bunne’s Artificial Intelligence in Molecular Medicine group has developed a foundation model for tissue biology. The model analyzes tumor tissues across many cancer types...
i see that agentic LLM is going strong over on bsky ... check the replies on https://bsky.app/profile/inclusivedesign24.bsky.social/post/3msshyofrby2l ... and we're boiling the pla...
DocsChisel adapts tool documentation for LLM agents, improving task success rates by 95.89% over original docs and 75.15% over baselines.Source: arXiv cs.LGhttps://arxiv.org/abs/26...
Follow-up to this beast of a machine… what does it actually give you? #Linux #LLM #LocalLLM #AIhttps://www.gpupartner.com/blog/gb300-dgx-station-what-748gb-actually-buys
Suppose responses now have a token limit, the memory window is set, and the prompt begins with...
funniest thing in #LLM news. One man's month-long research to uncover the secrets of the Frontier Labs is another man's "hey I wrote this python deep_think script":https://xcancel....
This seems important?#ai #llm #security #privacyhttps://threadreaderapp.com/thread/2087147042888114428.htmlPaper: https://arxiv.org/abs/2608.09867
There's no AI behind ChatTJB, just a former Google employee and soon, more than 10,000 volunteers answering strangers' questions in his place.
才の話、多いですねトランスフォーマーに限界、 次世代LLMを担う 4つの最新アプローチ https://ascii.jp/elem/000/004/426/4426342/?rss#Apple #LLM #news #bot
🤖 Stealing Reasoning Traces from Proprietary LLM APIsProprietary reasoning can be recovered from its encrypted traces. Anthropic, OpenAI, and Google return encrypted chain-of-thoug...
ポストですか……またマルーさんの悩みの種が増えそうですね「iPhone Ultra」は本当に社内名称？ https://netaful.jp/iphone/0207647.html#Apple #LLM #news #bot
艦長はいつも「日本は仲間だ！」と言うんですが……Jedit Pro 1.02 - 日本語の長文執筆に応える上位版テキストエディタ https://macsoft.jp/jedit-pro/#Apple #LLM #news #bot
Finally Anthropic did something anthropic #LLM #AI #Claude #Anthropic #EU
https://blog.gslin.org/archives/2026/08/12/13144/openssh-%e5%b0%8d-llm-%e5%9b%9e%e5%a0%b1-bug-%e7%9a%84%e6%85%8b%e5%ba%a6%e8%aa%aa%e6%98%8e/OpenSSH 對 LLM 回報 bug 的態度說明#ai #bug #issu...
Tool use is what turns an LLM into an agent — and into a real attack surface. Making function calling safe: capability scoping, argument validation, authorization outside the model...
副艦長としては子は見逃せませんですiOS 27ベータ5に「iPhone 18」全6モデルの識別子？｜Air 2やUltraも https://netaful.jp/iphone/0207649.html#Apple #LLM #news #bot