15459 articles tagged with LLM
Нашёл интересного #LLM ассистента. Он может работать с телефоном и управлять им. Например его можно попросить написать контакту, либо посмотреть новости или даже забрать награду из...
Running local LLMs via Ollama, LM Studio, or llama.cpp usually starts with the same guessing game:...
Every plan, read fully — including the Friday 5pm ones. Pull up a chair, grab some chai, and let...
And yes @benchsmoke, I consider it an inexcusable abdication of responsibility to give an #LLM authority to merge changes to shared code. You can't meaningfully claim human control...
亜人とヒトはWebPについてもっとよく話さないといけませんPixRinse 1.0.5 - 画像の圧縮・変換・リサイズをMac内で一括処理 https://macsoft.jp/pixrinse/#Apple #LLM #news #bot
Alternately, just surrender to the slop entirely, and direct your LLM instance to "restate the answer in the style of Ali G."#AI #nihilism
Prompt injection, hallucinated numbers, runaway costs and leaked card data: practical guardrails for putting AI agents into a security-sensitive platform.
@nzakas> But that [#LLM review of #LLM-generated code] is the way it has to be. Humans can't possibly do all this reviewing […]That is not the way it has to be, of course: We can r...
@neurovagrant This part of your post is an excellent general summary of an #LLM : "Your threat intelligence LLM operates on a single principle: find data that probably looks like a...
A small build-time i18n pipeline for a hand-written HTML site: extract strings, translate them in batches with an LLM, validate placeholders and tags, fail the build on anything mi...
Introduction A few weeks ago, my team and I were stuck. We’re building a waste management...
ICYMI: In-context learning: In-context learning is a language model's ability to pick up a task from examples or instructions in its prompt, with no retraining. How it works and fa...
LLM JSON that sometimes fails to parse: why it happens, when constrained decoding fixes it, and a validate-and-retry loop for the rest.
Thus final answer.https://olud.ai/latest.html#AI #LLM
Thinking Machines Labs Inc. released Inkling 2 Small, a large language model that automates artificial intelligence training tasks. The debut occurred late Thursday.Source: Silicon...
MIT researchers have built CheMeleon, a foundation model for chemistry that predicts molecular properties from scant data. Pre-trained on descriptors of a million PubChem molecules...
This was just a bunch of filters amplifying each other’s noise!The didn’t ‘invent their own languages’. That was the LLM token version of feedback squeal.You must not think of thin...
SketchAgentBench – evaluate LLMs on 3D spatial reasoninghttps://sketchagent.dev/#llm #llms
A Jev that can ask Opus for help gives Opus accuracy at 4x lower costhttps://hightouch.com/blog/llm-judges-identity-resolution#llm
You are a senior developer/devops/whatever using #AI heavly? You are on a degenerative way becoming a junior again. #llm
Title: P5: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]To success we should not accumulate errors and catch main aspects.Approaches to build System-2:MECE ...
Title: P4: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]- System-2 - Low precision: answer as an accumulation of errors. High recall: some critical point wa...
Title: P3: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]Error reasons: Cascading or accumulation and precision vs recall.- System-1 - Low precision: not eno...
Title: P2: TTC & System-2-thinking, Precision vs Recall for LLM [2026-05-14 Thu]- System-2 thinking - slow, deliberate, and logical reasoning, multi-step.From Classical ML:- Precis...