Search
1000 results for “context”
-
Beyond Context Graphs : Agentic Memory , Causual Graphs , Promise Graphs and decision traces by Volodymyr Pavlyshyn is the featured bundle of ebooks 📚 on Leanpub!
How to make agents adopted to enterprice grade tasks
Link: https://leanpub.com/b/beyondcontextgraphs-agenticai
#ai #deep_learning #data_science #software_architecture #databases #data_structures #software_engineering
-
Beyond Context Graphs : Agentic Memory , Causual Graphs , Promise Graphs and decision traces by Volodymyr Pavlyshyn is the featured bundle of ebooks 📚 on Leanpub!
How to make agents adopted to enterprice grade tasks
Link: https://leanpub.com/b/beyondcontextgraphs-agenticai
#ai #deep_learning #data_science #software_architecture #databases #data_structures #software_engineering
-
Beyond Context Graphs : Agentic Memory , Causual Graphs , Promise Graphs and decision traces by Volodymyr Pavlyshyn is the featured bundle of ebooks 📚 on Leanpub!
How to make agents adopted to enterprice grade tasks
Link: https://leanpub.com/b/beyondcontextgraphs-agenticai
#ai #deep_learning #data_science #software_architecture #databases #data_structures #software_engineering
-
Beyond Context Graphs : Agentic Memory , Causual Graphs , Promise Graphs and decision traces by Volodymyr Pavlyshyn is the featured bundle of ebooks 📚 on Leanpub!
How to make agents adopted to enterprice grade tasks
Link: https://leanpub.com/b/beyondcontextgraphs-agenticai
#ai #deep_learning #data_science #software_architecture #databases #data_structures #software_engineering
-
Fenêtre contextuelle ou nouvelle page : comment choisir ?
@vitalyf vous aide à choisir selon le contexte et la complexité de la tâche que l’utilisatrice doit réaliser grâce à un arbre de décision UX :
https://a42.fr/ux-decision-tree (en anglais)
-
Fenêtre contextuelle ou nouvelle page : comment choisir ?
@vitalyf vous aide à choisir selon le contexte et la complexité de la tâche que l’utilisatrice doit réaliser grâce à un arbre de décision UX :
https://a42.fr/ux-decision-tree (en anglais)
-
Fenêtre contextuelle ou nouvelle page : comment choisir ?
@vitalyf vous aide à choisir selon le contexte et la complexité de la tâche que l’utilisatrice doit réaliser grâce à un arbre de décision UX :
https://a42.fr/ux-decision-tree (en anglais)
-
Fenêtre contextuelle ou nouvelle page : comment choisir ?
@vitalyf vous aide à choisir selon le contexte et la complexité de la tâche que l’utilisatrice doit réaliser grâce à un arbre de décision UX :
https://a42.fr/ux-decision-tree (en anglais)
-
Fenêtre contextuelle ou nouvelle page : comment choisir ?
@vitalyf vous aide à choisir selon le contexte et la complexité de la tâche que l’utilisatrice doit réaliser grâce à un arbre de décision UX :
https://a42.fr/ux-decision-tree (en anglais)
-
Bounded Contexts prevent large fintech models from becoming inconsistent. Without explicit boundaries, the same term used differently by payments, risk, and compliance teams creates integration errors across distributed services.
-
Bounded Contexts prevent large fintech models from becoming inconsistent. Without explicit boundaries, the same term used differently by payments, risk, and compliance teams creates integration errors across distributed services.
-
Bounded Contexts prevent large fintech models from becoming inconsistent. Without explicit boundaries, the same term used differently by payments, risk, and compliance teams creates integration errors across distributed services.
-
Bounded Contexts prevent large fintech models from becoming inconsistent. Without explicit boundaries, the same term used differently by payments, risk, and compliance teams creates integration errors across distributed services.
-
Bounded Contexts prevent large fintech models from becoming inconsistent. Without explicit boundaries, the same term used differently by payments, risk, and compliance teams creates integration errors across distributed services.
-
Finding context in an endless loop. Sunday Morning Reading. with writing from @[email protected] @[email protected] @[email protected] and more. #SundayMorningReading warnercrocker.com/2026/05/03/s...
Sunday Morning Reading -
Finding context in an endless loop.
Sunday Morning Reading
With writing from @dtm
@Daojoan
@HilliTech
And more.#SundayMorningReading #Tech #AI #Chicago #Culture
https://warnercrocker.com/2026/05/03/sunday-morning-reading-153/ -
Finding context in an endless loop.
Sunday Morning Reading
With writing from @dtm
@Daojoan
@HilliTech
And more.#SundayMorningReading #Tech #AI #Chicago #Culture
https://warnercrocker.com/2026/05/03/sunday-morning-reading-153/ -
Finding context in an endless loop.
Sunday Morning Reading
With writing from @dtm
@Daojoan
@HilliTech
And more.#SundayMorningReading #Tech #AI #Chicago #Culture
https://warnercrocker.com/2026/05/03/sunday-morning-reading-153/ -
Finding context in an endless loop.
Sunday Morning Reading
With writing from @dtm
@Daojoan
@HilliTech
And more.#SundayMorningReading #Tech #AI #Chicago #Culture
https://warnercrocker.com/2026/05/03/sunday-morning-reading-153/ -
Finding context in an endless loop.
Sunday Morning Reading
With writing from @dtm
@Daojoan
@HilliTech
And more.#SundayMorningReading #Tech #AI #Chicago #Culture
https://warnercrocker.com/2026/05/03/sunday-morning-reading-153/ -
that context I came to see the offensive parts very differently. I think he's one of the greatest. #Frightclub #theskinilivein
-
5/ Context for the story - The climate is changing rapidly. The impacts of those changes are already upon us. How we adapt to those impacts will be a major theme for the rest of our lives and beyond. #books #booksky #novel #fiction #climatefiction #indie #indieauthor #climatefiction
-
Model Context Protocol (MCP): как ИИ-агенты «разговаривают» с внешним миром
Если вы читали или смотрели видео про MCP, то наверняка сталкивались с таким комментарием: «Спасибо, ещё одна статья, из которой я ничего не понял». Аналогии и пояснения вроде «MCP — это как USB Type-C» или «MCP — это Tools, Resources и Prompts» лично мне не добавляли понимания. Поэтому я решил подробно изучить данную технологию и написать статью, где будет понятно, достоверно и применимо . Без магии. Попутно я прошёл обучение у Anthropic (ссылки дам, сертификаты выдают, курсы бесплатные, cправда на английском). Я ставил себе цель ответить на вопросы: Что такое MCP и как он связан с ИИ? Как чат GPT (большая языковая модель, LLM) может вызвать какой-то инструмент (tool)? Модель же языковая , т.е. она умеет говорить, рассуждать, отвечать, но никак не делать . Как LLM может читать файлы, вызывать программы, открывать интернет сайты, вызывать внешние API? Для программистов, кто в теме и уже использовал MCP-сервера, т.е. знает серверные примитивы: tools, resources и prompts , возможно будут интересны клиентские примитивы: sampling, roots, elicitation . Они звучат загадочно и трудно переводимы. И чтобы вас заинтриговать: MCP-сервер благодаря sampling может «сжигать» ваши LLM-токены для выполнения своих серверных задач. А благодаря roots получать доступ к файлам на вашем компьютере. Итак, поехали.
-
The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.
This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.
So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.
I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.
But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?
Yes, Virginia, it can.
P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.
-
The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.
This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.
So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.
I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.
But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?
Yes, Virginia, it can.
P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.
-
The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.
This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.
So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.
I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.
But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?
Yes, Virginia, it can.
P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.
