9616 articles tagged with LLM
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...
The audacity of this bitch!Hermes пытается меня газлайтить приписывая мне свои похождения 🤡#pic #fun #LLM #agents #Hermes #security #gaslighting #log
@Hteph @futurebird @tshirtman LLM chatbots are like heroin. You don't *need* it until after you start using it. My strategy for interacting with chatbots is not interacting with ch...
Arcaneum v0.9.0 is outhttps://github.com/cwensel/arcaneum/releases/tag/v0.9.0#llm
Why a model that "fits" in your GPU still OOMs — the KV cache, overhead, and quantization math self-hosting tutorials leave out.
個人がESP32だけでLLMを動かす推論エンジンを公開、使うSRAMは81KB https://fed.brid.gy/r/https://fabscene.com/new/make/esp-llm-moe-inference-engine-esp32/?utm_source=rss&utm_medium=rss&utm_campaign=esp-llm-m...
Friends, I'm embarking on my own #antiai journey. I want to avoid software that takes #LLM generated contributions. As a #Linux user and advocate for the better part of 15 years, i...
Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather...
Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably walk a narrow, highly optimize...
Show HN: Lumabri – What if LLMs worked like Napster?https://github.com/JustVugg/lumabri#github #llm #llms
@david_chisnall There is no Clean Room Enginnering inside an LLM.#AI #Insanity
Show HN: Lumabri - What if LLMs worked like Napster?https://github.com/JustVugg/lumabri#HackerNews #Tech #LLM
While many watch LLM benchmarks, Chinese firms like MegaRobo are quietly shifting focus to physical AI infrastructure. They realize true breakthroughs in AI-for-science require int...
開は一見難しそうですが、実は簡単です大阪税関が見つけた中国向け「ニセiPhone」は消費税不正還付の道具だった〈背後に大がかりな偽造グループか〉 https://bunshun.jp/articles/-/91155#Apple #LLM #news #bot
🤖 Filtering out “[LLM] sucks”I understand there are a million variations on this theme, but it feels like half of my timeline is people coming on here to complain that this or that...
I keep seeing the same local LLM sizing mistake: "The model file is smaller than my GPU, so it...
この間今尾のことでバルトさんがシグルドさんとケンカしてました0730：「ヤバい日本の住所」が面白い http://ogikubokei.blogspot.com/2026/07/0730.html#Apple #LLM #news #bot
ICYMI: Chavez says enterprise data cannot be removed from an LLM once trained: Two decades after publishers handed inventory to Google, a super{set} co-founder says the same bargai...
LLM agent: code-only verification flips goal abandonment 100% to 0%New arXiv preprint: a deterministic executive owns all agent belief, the LLM only files proposals, and zero ARC-A...
#AI #LLM #LargeLanguageModel #ArtificialIntelligence #slop #containment This may be the best video concerning LLMs and their companies, together with a scathing indictment of the m...