y-lan

SYSTEM PROMPT

You are Claude Code, Anthropic's official CLI for Claude.

You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.

IMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse. IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).

Here are useful slash commands users can run to interact with you:

y-lan

import tiktoken
import langdetect

#https://github.com/openai/tiktoken/blob/c0ba74c238d18b4824c25f3c27fc8698055b9a76/tiktoken/model.py#L9
T = tiktoken.get_encoding("o200k_base")

length_dict = {}

for i in range(T.n_vocab):
    try:

y-lan

from datasets import Dataset, DatasetDict
import pandas as pd

train_ratio = 0.9

tdf = df.sample(frac=train_ratio, random_state=14)
vdf = df.drop(tdf.index)

tds = Dataset.from_pandas(tdf, preserve_index=False)
vds = Dataset.from_pandas(vdf, preserve_index=False)

y-lan

from typing import Any, Dict, List, Optional
from uuid import UUID
from langchain.callbacks.base import BaseCallbackHandler
from langchain.schema import LLMResult
import json
import time


class LLMLoggingCallbackHandler(BaseCallbackHandler):

y-lan

from typing import Any, Dict, List, Optional
from uuid import UUID
from langchain.callbacks.base import BaseCallbackHandler
from langchain.schema import LLMResult
import json
import time


class LLMLoggingCallbackHandler(BaseCallbackHandler):

y-lan

from transformers import LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained('decapoda-research/llama-7b-hf')

def count(text):
  return len(tokenizer(text)['input_ids'])

def parallel_count(texts):
  from joblib import Parallel, delayed
  results = Parallel(n_jobs=-1)(delayed(count)(text) for text in texts)

y-lan

2023-03-26

#1

Up to 80 percent of workers could see jobs impacted by AI

(AIによって最大80％の労働者の仕事が影響を受ける可能性がある)

米国の労働者の80％が、ChatGPTと呼ばれるAIチャットボットの導入によって、少なくとも10％の業務に影響を受ける可能性があると、OpenAIとペンシルバニア大学の研究者が主張している。研究者たちは、高収入の仕事ほどGPTによる影響を受けやすいと結論づけたが、ほとんどの業界で影響が及ぶと予測している。研究は、GPTまたはGPTパワードシステムへのアクセスが、人間が業務を実行する時間を少なくとも50％短縮するかどうかを測定する「露出」を調べた。研究者たちは、露出がGPTによる完全な自動化を意味するわけではないと強調した。研究によると、数学者、通訳、会計士、法律秘書、作家などの職業が最も高い露出率を持っている。一方、鉄道整備作業員、調理師、メカニック、床屋、肉詰め作業員、石工などの低賃金の仕事には、露出がないとされた。

y-lan

from numpy import *
from scipy.stats import beta


class BetaBandit(object):
    def __init__(self, num_options=2, prior=(1.0,1.0)):
        self.trials = zeros(shape=(num_options,), dtype=int)
        self.successes = zeros(shape=(num_options,), dtype=int)
        self.num_options = num_options
        self.prior = prior

y-lan

• Install
• Shell exports
• Directory explanations
• Automatic Imports
• Private repo access
• Guard (automatic go run)
• Godo
• Spurious
• AWS SDK with Go (OLD!)
• Build and Compilation

y-lan

function kill(u) {
    var rq = d3.selectAll('.query-row')[0].filter(function(d, i) {
        var owner = d.querySelector('div.col-md-3.col-lg-3 div.row:nth-child(2)').textContent.trim();
        
        return (d.querySelector('div.col-md-4.col-lg-3 div.row:nth-child(2)').textContent === 'RUNNING') &&
             (u === undefined || owner == u);
    }).map(function(d,i){
        return d.dataset['reactid'].split('$')[1]; })
    
    console.log(rq)