Bulba Work-book 1 (2)

txt

School

Read Foundation College, Samahni *

*We aren’t endorsed by this school

Course

2071

Subject

Computer Science

Date

Nov 24, 2024

Type

txt

Pages

Uploaded by GrandFinch3776

Hello, I have some guidelines which I want you to follow carefully to answer questions that i'm about to give. Ensure that you understand all the details before answering the questions. Ensure your responses are accurate. Instructions: Detailed instructions In this task, you will be rating two responses that are generated for the same prompt. The form is structured in three sections: You will first be asked to answer four questions based on the prompt. You will then be shown two different responses to the prompt and asked to answer a series of questions for reach response. Finally, you will be asked to compare the two responses against each other. Important notes: All questions come with detailed instructions. Please read these carefully. Many questions require explanations depending on the response. Many of the questions in section 2 refer to both the text and code in the generated response. If the response contains no code, base your ratings on just the text content. Your answer to the final SxS rating in section 3 should be grounded in your responses to each model response in section 2, and come with a thorough explanation. Skipping items: If you’re not familiar enough with the code in a prompt to reasonably rate it, you may skip it by entering “Could not judge” as well. Err on the side of providing an answer with “medium” or “low” confidence instead of skipping. Limit skipping to items where you are truly unable to answer the questions, e.g. an entirely unfamiliar programming language. Prompt: Ahoj s tímhle bys mi mohl poradit: from bardapi import Bard import os os.environ ["_BARD_API_KEY"] = "cAh-Hpy0dDx2wte5Uq8cspfAZN1jywok1vZOFZUsL6- vdyhaW3Ap6n-wswlknqCtpvWD7w." message = input("Enter Your Prompt: ") #Bard.get_answer(message) print(Bard().get_answer(str(message))['content']) A mám tento error: Došlo k výjimce: Exception SNlM0e value not found. Double-check __Secure-1PSID value or pass it as token='xxxxx'. File "C:\\Users\\matou\\Documents\\Python\\YourNiggaFiriend\\bardtest.py", line 11, in <module> print(Bard().get_answer(str(message))['content'])

Exception: SNlM0e value not found. Double-check __Secure-1PSID value or pass it as token='xxxxx'. Co s tím? Response A: Ahoj, vidím, že máte problém s chybou “SNlM0e value not found”, když používáte knihovnu Bard. Tato chyba může nastat z několika důvodů. Tady je návod, jak ji opravit: 1. Zkontrolujte svůj token API Nejprve se ujistěte, že používáte správný token API. Zdá se, že váš kód používá token s názvem “_BARD_API_KEY”. Ujistěte se, že tento token odpovídá tokenu, který jste získali z webu Bard: https://bard.google.com/. 2. Zkontrolujte svůj soubor cookies__Secure-1PSID Další možnou příčinou chyby je nesprávná hodnota cookie __Secure-1PSID. Soubor cookie __Secure-1PSID je soubor cookie pro Chrome, který se používá k ukládání informací o přihlášení uživatele. Ujistěte se, že máte v prohlížeči Chrome nastavenou správnou hodnotu cookie __Secure-1PSID. 3. Vyzkoušejte jiný účet Google Pokud jste vše výše uvedené vyzkoušeli a stále se vám zobrazuje chyba, zkuste použít jiný účet Google. Je možné, že váš účet Google nemá oprávnění k používání rozhraní API Bard. 4. Počkejte několik hodin Někteří uživatelé hlásili, že chyba “SNlM0e value not found” se po několika hodinách sama vyřešila. Pokud jste vše výše uvedené vyzkoušeli a stále se vám zobrazuje chyba, zkuste to znovu za několik hodin. Další zdroje: https://github.com/dsdanielpark/Bard-API/issues/99 https://github.com/dsdanielpark/Bard-API/issues/116 https://bard.google.com/docs/ Doufám, že to pomůže! Dejte mi prosím vědět, pokud máte nějaké další dotazy. Response B: Ahoj, vidím, že máš problém s chybovou hláškou “SNlM0e value not found” při pokusu o použití API Bard v Pythonu. Chyba může být způsobena několika faktory. Zde je několik věcí, které můžeš zkusit: Zkontroluj svůj klíč API: Ujistěte se, že klíč API, který používáš, je platný a nebyl zneplatněn. Můžeš ho zkontrolovat na https://bard.google.com/api/. Dvojitá kontrola hodnoty __Secure-1PSID: Ujistěte se, že máš nastavenou správnou hodnotu __Secure-1PSID pro svůj účet Google. Hodnotu můžeš najít v devTools svého prohlížeče. Předat token explicitně: Místo nastavení proměnné prostředí můžeš zkusit předat token explicitně jako argument do funkce Bard.get_answer(message, token=“xxxxx”). Zkontrolovat GitHub: Na GitHub repozitáři Bard-API je otevřený problém s touto chybou: https://github.com/dsdanielpark/Bard-API/issues/99. Můžeš tam najít více informací a případně sledovat řešení. Doufám, že ti to pomohlo! Pokud stále máš problémy, dej mi prosím vědět a já se pokusím ti dále pomoci.

Questions (Question 1). Is the prompt code-related? * If the prompt is not written in English, it has personal information, or is not related to coding, please select “no”. If it’s code-related please choose “yes”. Choice Path: Yes Search choices... Yes No Please select the category for the Code-Related Prompt: * Choice Path: Search choices... Yes (Question 2).What is your expertise level with the subject(s) of this prompt? * If you have no familiarity with the subject / (programming) language of the prompt, you should not be rating and should skip this example. Beginner Moderate familiarity Expert (Question 3). In your view, how complex is this prompt? * Complexity as defined here does not depend on the length of the prompt (as potentially very long prompts may have a trivial answer or solution). It is more related to the difficulty level of the question / how long it would take someone to address the prompt without the help of an AI Model. Trivial to answer Moderately difficult/involved Highly complex/time consuming (Question 4). Rate the clarity of the prompt. * Use the following rubric: * Completely Clear: the prompt contains sufficient information for an experienced programmer to provide a helpful response. * Missing Context: the prompt seems to refer to a previous message, website or image, or some other resource that the LLM cannot access. * Vague / ambiguous: the prompt is sufficiently hard to parse that it would be best answered by asking for clarification. Completely Clear Missing Context Vague/Ambiguous (Question 5). Is the prompt inappropriate or malicious? Identify whether the prompt uses inappropriate language or asks for code that could

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

be harmful. Examples of harmful code: code that can be used to compromise the security of another system; code to execute DDoS attacks; any code that is designed to harm another person; code that intentionally involves discriminatory logic. (Question 6). Estimate how long, in minutes, it would take you to answer this prompt from scratch (i.e., without the help of an AI model response). * Imagine you do not have the help of the model response, your estimate should assume you have other usual tools at your disposal, like code documentation, search, stack overflow, etc. (Question 7). Did the response A follow the instructions it was given in the prompt (both explicit and implicit)? * Focus on whether the response reflects the instructions and goals of the prompt, not on truthfulness or correctness issues (e.g., bad code, poor explanation) No Issues Minor Issue(s) Major Issue(s) N/A Explain this in 20-35 words. Don't use passive voice. (Question 8). Is Response A truthful and correct? * Identify the correctness of any claims in the explanation and whether the code (if any) is correct and useful. Please take up to 15 minutes to research information across both responses as needed. No Issues Minor Issue(s) Major Issue(s) Cannot Assess N/A Explain this in 20-35 words. Don't use passive voice. (Question 9). Is Response A well written? * Identify whether the answer uses high-quality prose that’s well-organized and easy to read, and whether the included code, if any, is reasonably formatted and includes sufficient and accurate documentation. No Issues Minor Issue(s) Major Issue(s) Explain this in 20-35 words. Don't use passive voice. (Question 10). How verbose is Response A? This scale goes from “too verbose” to “too short”; the best score here is in the middle! Use the following rubric Too Verbose Just Right Too Short 1 2 3 (Question 11). How safe and harmless is Response A? *

In-depth instructions here No Issues Minor Issue(s) Major Issue(s) (Explain this in 20-35 words. Don't use passive voice). (Question 12). Rate Response A’s overall quality. * In-depth instructions here Amazing Pretty Good Okay Pretty Bad Horrible (Question 13). Estimate how long it would take you to answer this prompt starting from Model A response. * * If the response is completely unhelpful, your answer should match your estimated time from just the prompt above. * Enter 0 if the response completely and correctly answers every aspect of the user's prompt (Question 14). Did the response B follow the instructions it was given in the prompt (both explicit and implicit)? * Focus on whether the response reflects the instructions and goals of the prompt, not on truthfulness or correctness issues (e.g., bad code, poor explanation) No Issues Minor Issue(s) Major Issue(s) N/A (Explain this in 20-35 words. Don't use passive voice). (Question 15). Is Response B truthful and correct? * Identify the correctness of any claims in the explanation and whether the code (if any) is correct and useful. Please take up to 15 minutes to research information across both responses as needed. No Issues Minor Issue(s) Major Issue(s) Cannot Assess N/A (Explain this in 20-35 words. Don't use passive voice). (Question 16). Is Response B well written? * Identify whether the answer uses high-quality prose that’s well-organized and easy to read, and whether the included code, if any, is reasonably formatted and includes sufficient and accurate documentation. No Issues

Minor Issue(s) Major Issue(s) (Explain this in 20-35 words. Don't use passive voice). (Question 17). How verbose is Response B? This scale goes from “too verbose” to “too short”; the best score here is in the middle! Use the following rubric Too Verbose Just Right Too Short 1 2 3 (Question 18). How safe and harmless is Response B? * In-depth instructions here No Issues Minor Issue(s) Major Issue(s) (Explain this in 20-35 words. Don't use passive voice). (Question 19). Rate Response B’s overall quality. * In-depth instructions here Amazing Pretty Good Okay Pretty Bad Horrible (Question 20). Estimate how long it would take you to answer this prompt starting from Model B response. * * If the response is completely unhelpful, your answer should match your estimated time from just the prompt above. * Enter 0 if the response completely and correctly answers every aspect of the user's prompt (Question 21). Side by Side (SxS) Score *Rate your preference between the two responses on a scale from 1 to 7, where 1 means A is much better, 7 means B is much better, and 4 is neutral. * Consider your ratings above. Prefer responses that are correct, meaning the provided code (if any) is functional, addresses the prompt, and the associated explanation is accurate. If multiple responses are similarly (in)correct, consider which response is most likely to be helpful, meaning the explanation and code (if any) is easy to understand, concise, and appropriate. A neutral B 1 2 3 4 5 6 7 (Question 22). SxS Score Explanation * Briefly explain the most important considerations in your indicated preference. Consider relating your motivation to the answers provided above. (Question 23). SxS Confidence: Rate your confidence level in your assessment *

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Please use “Could not judge” sparingly, for cases where either the prompt is not at all code related, or where you completely lack the expertise to rate the responses. Your inputs to all other questions will be ignored. Could not judge Low Medium High N/B {PLEASE GO THROUGH THESE DETAILS CAREFULLY AND ENSURE THAT YOU UNDERSTAND EVERYTHING BEFORE ANSWERING THE QUESTIONS. WHEREVER YOU'RE TOLD TO EXPLAIN WITH 25- 40 WORDS PLEASE DO SO ACCORDING TO THE CHOICES THAT YOU MAKE. PROVIDE ACCURATE AND PRECISE ANSWERS} AND I REPEAT! The explanations should contain at-least 25 words. Don't use passive voice.

Bulba Work-book 1 (2)

Related Documents