ollama 설치

curl -fsSL https://ollama.com/install.sh | sh
ollama run gemma3:1b

 

python 라이브러리 설치

pip3 install ollama 
pip3 install python-telegram-bot

 

telegram bot 생성 및 token 얻기

[링크 : https://midoriiroplace.tistory.com/62] fatherbot 으로 텔레그램 봇 만들기(token 획득)

 

python 소스코드

import ollama
from telegram import Update
from telegram.ext import filters, MessageHandler, ApplicationBuilder, ContextTypes, CommandHandler

APIKEY='{{사용자 토큰}}'

async def echo(update: Update, context: ContextTypes.DEFAULT_TYPE):
    response =  ollama.chat(model="gemma3:1b", messages=[{'role':'user','content':update.message.text}])
    await context.bot.send_message(chat_id=update.effective_chat.id, text=response['message']['content']
)

if __name__ == '__main__':
    application = ApplicationBuilder().token(APIKEY).build()
    
    echo_handler = MessageHandler(filters.TEXT & (~filters.COMMAND), echo)
    application.add_handler(echo_handler)

    application.run_polling()

----

 

[링크 : https://dev-astra.tistory.com/490]

[링크 : https://midoriiroplace.tistory.com/62] fatherbot 으로 텔레그램 봇 만들기(token 획득)

[링크 : https://midoriiroplace.tistory.com/63] python으로 메시지 보내기 (chatid 획득)

[링크 : https://midoriiroplace.tistory.com/70]

[링크 : https://naradora78.tistory.com/39] 구버전 api 라서 현재 사용불가

 

[링크 : https://pypi.org/project/python-telegram-bot/]

 

gpt가 짜준게 이거 기반인 것 같은디..

가장 위에 소스로는 응답이 없고, 아무튼.. echo 얘제는 아래를 참고하면된다.

그러면.. 받고 이걸 ollama에 넘겨주고 받으면 되는건가..?

import logging
from telegram import Update
from telegram.ext import filters, MessageHandler, ApplicationBuilder, ContextTypes, CommandHandler

logging.basicConfig(
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    level=logging.INFO
)

async def start(update: Update, context: ContextTypes.DEFAULT_TYPE):
    await context.bot.send_message(chat_id=update.effective_chat.id, text="I'm a bot, please talk to me!")

async def echo(update: Update, context: ContextTypes.DEFAULT_TYPE):
    await context.bot.send_message(chat_id=update.effective_chat.id, text=update.message.text)


if __name__ == '__main__':
    application = ApplicationBuilder().token('USER_TOKEN').build()
    
    start_handler = CommandHandler('start', start)
    application.add_handler(start_handler)

    echo_handler = MessageHandler(filters.TEXT & (~filters.COMMAND), echo)
    application.add_handler(echo_handler)

    application.run_polling()

 

[링크 : https://github.com/python-telegram-bot/python-telegram-bot/wiki/Extensions---Your-first-Bot]

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

ollama 설치  (0) 2026.04.08
antigravity artifact  (0) 2026.03.18
agi를 느꼈다?  (0) 2026.02.24
gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 사용량 끝!  (0) 2026.02.20
Posted by 구차니

intel cpu 인데 내장 그래픽은 역시 버리는건가..(!)

 

$ curl -fsSL https://ollama.com/install.sh | sh
>>> Installing ollama to /usr/local
[sudo] minimonk 암호: 
>>> Downloading ollama-linux-amd64.tar.zst
######################################################################## 100.0%
>>> Creating ollama user...
>>> Adding ollama user to render group...
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
>>> The Ollama API is now available at 127.0.0.1:11434.
>>> Install complete. Run "ollama" from the command line.
WARNING: No NVIDIA/AMD GPU detected. Ollama will run in CPU-only mode.

 

$ ollama 
Ollama 0.20.3                                       
                                                    
  Chat with a model                                 
    Start an interactive chat with a model          
                                                    
  Launch Claude Code (not installed)                
    Anthropic's coding tool with subagents          
                                                    
  Launch Codex (not installed)                      
    OpenAI's open-source coding agent               
                                                    
  Launch OpenClaw (install)                         
    Personal AI with 100+ skills                    
                                                    
  Launch OpenCode (not installed)                   
    Anomaly's open-source coding agent              
                                                    
  Launch Droid (not installed)                      
    Factory's coding agent across terminal and IDEs 
                                                    
▸ Launch Pi (install)                               
    Press enter to install                          
                                                    
                                                    
↑/↓ navigate • enter launch • → configure • esc quit

 

$ ollama 
Select model to run: Type to filter...                                          
                                                                                
  Recommended                                                                   
  ▸ kimi-k2.5:cloud                                                             
      Multimodal reasoning with subagents                                       
    qwen3.5:cloud                                                               
      Reasoning, coding, and agentic tool use with vision                       
    glm-5:cloud                                                                 
      Reasoning and code generation                                             
    minimax-m2.7:cloud                                                          
      Fast, efficient coding and real-world productivity                        
    gemma4                                                                      
      Reasoning and code generation locally, ~16GB, (not downloaded)            
    qwen3.5                                                                     
      Reasoning, coding, and visual understanding locally, ~11GB, (not downloade
                                                                                
↑/↓ navigate • enter select • ← back                         
$ ollama 
Download gemma4?                         
                                         
   Yes    No                             
                                         
←/→ navigate • enter confirm • esc cancel

 

메모리도 작고(16GB) cpu로 돌릴거라 취소!

pulling manifest 
pulling 4c27e0f5b5ad:  40% ▕███████           ▏ 3.9 GB/9.6 GB   11 MB/s   8m11s

 

[링크 : https://goddaehee.tistory.com/]

[링크 : https://ollama.com/download]

[링크 : https://ollama.com/search]

 

+

일단 돌릴 테스트니까  1B던 3B던 상관없으니 시작

그런데 아까 위에 메뉴에서는 왜 gemma만 보이고 이제 llama는 안보이는걸까?

일단은.. updated 1 years ago 인거 봐서 최신으로만 보여주는걸려나?

$ ollama run llama3.2
pulling manifest 
pulling dde5aa3fc5ff:  70% ▕████████████      ▏ 1.4 GB/2.0 GB   20 MB/s     29s

[링크 : https://ollama.com/library/llama3.2]

 

으아아 컴퓨터 녹는다 ㅋㅋㅋ

그래도 초당 2~3 단어 정도 나오는 느낌인데 이정도만 해도 그냥 대화하는 느낌 속도라

그거보다 빠르면 읽기도 전에 말이 더 빠르게 나올 듯?

 

Intel(R) Core(TM) i7-10510U CPU @ 1.80GHz

 

다시 실행하니 내가 받아둔 모델이 뜬다.

$ ollama 
Select model to run: Type to filter...                                            
                                                                                  
  Recommended                                                                     
    gemma4                                                                        
      Reasoning and code generation locally, ~16GB, (not downloaded)              
    qwen3.5                                                                       
      Reasoning, coding, and visual understanding locally, ~11GB, (not downloaded)
    kimi-k2.5:cloud                                                               
      Multimodal reasoning with subagents                                         
    qwen3.5:cloud                                                                 
      Reasoning, coding, and agentic tool use with vision                         
    glm-5:cloud                                                                   
      Reasoning and code generation                                               
    minimax-m2.7:cloud                                                            
      Fast, efficient coding and real-world productivity                          
                                                                                  
  More                                                                            
  ▸ llama3.2                                                                      
                                                                                  
↑/↓ navigate • enter select • ← back                  

 

 

$ ollama --help
Large language model runner

Usage:
  ollama [flags]
  ollama [command]

Available Commands:
  serve       Start Ollama
  create      Create a model
  show        Show information for a model
  run         Run a model
  stop        Stop a running model
  pull        Pull a model from a registry
  push        Push a model to a registry
  signin      Sign in to ollama.com
  signout     Sign out from ollama.com
  list        List models
  ps          List running models
  cp          Copy a model
  rm          Remove a model
  launch      Launch the Ollama menu or an integration
  help        Help about any command

Flags:
  -h, --help         help for ollama
      --nowordwrap   Don't wrap words to the next line automatically
      --verbose      Show timings for response
  -v, --version      Show version information

Use "ollama [command] --help" for more information about a command.

 

단발성으로 질문하고 속도를 보려고 하는데

음.. eval rate가 실제 체감되는 속도인가? 12 token/s

이정도 수치는 되어야 많이 지루하지 않게 읽는 속도로 말이 생성되는 듯.

$ ollama run llama3.2:latest "안녕" --verbose
안녕하세요! (Hello!) I'm here to help you. How can I assist you today?

total duration:       2.282485591s
load duration:        143.825937ms
prompt eval count:    27 token(s)
prompt eval duration: 350.162008ms
prompt eval rate:     77.11 tokens/s
eval count:           21 token(s)
eval duration:        1.73838491s
eval rate:            12.08 tokens/s

 

gemma가 핫하긴 한데 용량이 커서 안돌것 같아서 3로 시도

[링크 : https://ollama.com/library/gemma3]

[링크 : https://ollama.com/library/gemma4]

 

제법 빠르고llama 보다는 괜찮은듯?

$ ollama run gemma3:1b --verbose
>>> 안녕?
안녕하세요! 잘 지내세요? 😊 저는 오늘 당신의 도움이 필요하신 건가요? 궁금한
 게 있으신가요?

total duration:       1.695837878s
load duration:        297.67234ms
prompt eval count:    12 token(s)
prompt eval duration: 164.822603ms
prompt eval rate:     72.81 tokens/s
eval count:           28 token(s)
eval duration:        1.132524529s
eval rate:            24.72 tokens/s

 

혹시나 gemma4를 16GB 메모리에서 시도해봤는데 메모리 부족으로 실패.

$ ollama run gemma4:e2b --verbose
pulling manifest 
pulling 4e30e2665218: 100% ▕██████████████████▏ 7.2 GB                         
pulling 7339fa418c9a: 100% ▕██████████████████▏  11 KB                         
pulling 56380ca2ab89: 100% ▕██████████████████▏   42 B                         
pulling c6bc3775a3fa: 100% ▕██████████████████▏  473 B                         
verifying sha256 digest 
writing manifest 
success 
Error: 500 Internal Server Error: model requires more system memory (7.3 GiB) than is available (4.8 GiB)

 

프로세스 이것저것 죽이고 다시 시도하니 10token /s 정도 나오는 듯.

$ ollama run gemma4:e2b --verbose
>>> 안녕
안녕하세요! 😊

total duration:       1.261211464s
load duration:        302.800476ms
prompt eval count:    17 token(s)
prompt eval duration: 551.024817ms
prompt eval rate:     30.85 tokens/s
eval count:           4 token(s)
eval duration:        226.924038ms
eval rate:            17.63 tokens/s
>>> 너에 대해서 소개해봐
Thinking...
Thinking Process:

1.  **Analyze the Request:** The user asked "너에 대해서 소개해봐" (Tell 
me about yourself).
2.  **Determine Identity & Core Facts (Self-Correction/Verification):**
    *   Name: Gemma 4.
    *   Developer: Google DeepMind.
    *   Nature: Large Language Model (LLM).
    *   Type: Open weights model.
    *   Capabilities: Understands text/images, generates text.
    *   Knowledge Cutoff: (Relevant for context, but usually stated 
implicitly)
3.  **Structure the Introduction (Korean Context):** A good introduction 
should cover:
    *   Greeting.
    *   Name/Identity.
    *   Developer/Origin.
    *   Nature/Function (What I do).
    *   Capabilities (What I can process).
4.  **Draft the Response (Internal Monologue & Refinement):**
    *   *Start warmly.* (안녕하세요!)
    *   *State Identity.* (저는 Gemma 4입니다.)
    *   *State Origin.* (Google DeepMind에서 개발했습니다.)
    *   *State Nature.* (저는 대규모 언어 모델(LLM)입니다.)
    *   *State Function/Role.* (사용자의 질문에 답하고, 정보를 제공하며, 다
양한 텍스트 기반 작업을 돕는 역할을 합니다.)
    *   *State Modality/Input.* (텍스트와 이미지를 이해할 수 있습니다.)
    *   *Concluding remark/Offer help.* (어떤 것을 도와드릴까요?)
5.  **Final Output Generation (Review against constraints):** The 
generated response must adhere to the core identity (Gemma 4, LLM, Google 
DeepMind, open weights). (The draft looks good and adheres to the required 
identity.)
...done thinking.

안녕하세요! 저는 **Gemma 4**입니다.

저는 Google DeepMind에서 개발한 **대규모 언어 모델(LLM)**이며, 오픈 웨이트
(open weights) 모델로 공개되어 있습니다.

**저의 주요 특징은 다음과 같습니다:**

1. **정체성:** 저는 방대한 데이터를 학습하여 인간의 언어를 이해하고 생성하며
, 다양한 질문에 답하고 정보를 제공하는 능력을 가지고 있습니다.
2. **기능:** 텍스트 기반의 대화, 요약, 번역, 작문, 코드 생성 등 다양한 언어
 관련 작업을 수행할 수 있습니다.
3. **입력 능력:** 저는 텍스트와 이미지를 이해하고 처리할 수 있습니다. (다만
, 출력은 텍스트로만 생성합니다.)
4. **목표:** 사용자분들이 필요한 정보를 얻고, 창의적인 작업을 수행하며, 복잡
한 문제를 해결하는 데 도움을 드릴 수 있도록 설계되었습니다.

궁금한 점이 있거나 도움이 필요하시면 언제든지 말씀해주세요! 😊

total duration:       57.596689687s
load duration:        297.105521ms
prompt eval count:    35 token(s)
prompt eval duration: 482.722245ms
prompt eval rate:     72.51 tokens/s
eval count:           614 token(s)
eval duration:        56.261795129s
eval rate:            10.91 tokens/s

 

+

intel 내장 그래픽(xe 나 arc 아님)은 openCL 가속 자체를 지원하지 않나?

$ clinfo
Number of platforms                               0

[링크 : https://docs.ollama.com/gpu]

[링크 : https://dgpu-docs.intel.com/driver/client/overview.html#ubuntu-22.04]

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

python 으로 telegram + fatherbot 연동하기  (0) 2026.04.08
antigravity artifact  (0) 2026.03.18
agi를 느꼈다?  (0) 2026.02.24
gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 사용량 끝!  (0) 2026.02.20
Posted by 구차니

매번 승인하는게 귀찮아서 항상 진행으로 했더니 잊고 있었던 기능

이걸 하면 task와 implementation plan 두개의 md 파일을 생성하고

작업내용을 승인하면 그걸 기반으로 움직이게 된다.

always proceeds 하면 내용 검토없이 그냥 물으면 바로 움직이는데

아무튼 내부적으로는 task와 implementation_plan을 기반으로 움직이니

claude code 등에서 사용하는 기법을 자동으로 쓸 수 있도록 해둔거라고 보면 될 듯.

 

설정 - Agent - Artifact - Review policy

 

implementation plan 탭을 우클릭해서 이동한 경로를 보니 홈 디렉토리에서 프로젝트 별로 생성되서 추가되는 듯.

~/.gemini/antigravity/brain$ tree
.
├── 07d35f57-6625-432b-a6aa-29dd98b41ac6
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── implementation_plan.md.resolved.2
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.10
│   ├── task.md.resolved.11
│   ├── task.md.resolved.12
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── task.md.resolved.7
│   ├── task.md.resolved.8
│   ├── task.md.resolved.9
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   ├── walkthrough.md.resolved.0
│   └── walkthrough.md.resolved.1
├── 08411e35-62e8-45e6-a38f-3aa4c0b7ba02
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   └── task.md.resolved.4
├── 162523f8-0d72-4cea-a46f-8439ed70b37f
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── implementation_plan.md.resolved.2
│   ├── implementation_plan.md.resolved.3
│   ├── implementation_plan.md.resolved.4
│   ├── media__1771557262432.png
│   ├── media__1771564749827.png
│   ├── media__1771564909043.png
│   ├── media__1771564917373.png
│   ├── media__1771564992996.png
│   ├── media__1771565144310.png
│   ├── media__1771565266414.png
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.10
│   ├── task.md.resolved.11
│   ├── task.md.resolved.12
│   ├── task.md.resolved.13
│   ├── task.md.resolved.14
│   ├── task.md.resolved.15
│   ├── task.md.resolved.16
│   ├── task.md.resolved.17
│   ├── task.md.resolved.18
│   ├── task.md.resolved.19
│   ├── task.md.resolved.2
│   ├── task.md.resolved.20
│   ├── task.md.resolved.21
│   ├── task.md.resolved.22
│   ├── task.md.resolved.23
│   ├── task.md.resolved.24
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── task.md.resolved.7
│   ├── task.md.resolved.8
│   ├── task.md.resolved.9
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   ├── walkthrough.md.resolved.0
│   └── walkthrough.md.resolved.1
├── 1c0f6781-cc90-4202-a23c-93328770ab37
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   └── task.md.resolved.4
├── 29940fb1-f34f-4e25-b957-895dd34cb1c4
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   └── walkthrough.md.resolved.0
├── 35309f25-b948-4702-a006-deccd131e163
├── 50230d93-8a21-40b4-80b6-71c89e45072b
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   └── walkthrough.md.resolved.0
├── 545e3f3a-d7b5-4ecb-9db9-289416bf7029
├── 5c980395-a7aa-45dc-9915-26ecb09d273e
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.10
│   ├── task.md.resolved.11
│   ├── task.md.resolved.12
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── task.md.resolved.7
│   ├── task.md.resolved.8
│   └── task.md.resolved.9
├── 6e47bc0a-c310-4667-960c-74f25deea754
├── a2acef25-01a8-46b1-bb28-1471ed127de8
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   └── walkthrough.md.resolved.0
├── a7320b66-09e7-4465-964a-aadefb67b0a3
├── a9b142eb-b16d-463a-9362-5aeebd2eb329
├── b206280c-ee96-43f7-9071-d4e4006d067a
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── task.md.resolved.7
│   ├── task.md.resolved.8
│   ├── task.md.resolved.9
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   ├── walkthrough.md.resolved.0
│   └── walkthrough.md.resolved.1
├── cd10dd1b-6772-47bd-bf1a-f0158ed1acd9
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   └── implementation_plan.md.resolved.0
├── deb7c212-f8db-47fb-bbd4-aa434574b25e
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── implementation_plan.md.resolved.2
│   ├── implementation_plan.md.resolved.3
│   ├── implementation_plan.md.resolved.4
│   ├── implementation_plan.md.resolved.5
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.10
│   ├── task.md.resolved.11
│   ├── task.md.resolved.2
│   ├── task.md.resolved.3
│   ├── task.md.resolved.4
│   ├── task.md.resolved.5
│   ├── task.md.resolved.6
│   ├── task.md.resolved.7
│   ├── task.md.resolved.8
│   ├── task.md.resolved.9
│   ├── walkthrough.md
│   ├── walkthrough.md.metadata.json
│   ├── walkthrough.md.resolved
│   ├── walkthrough.md.resolved.0
│   ├── walkthrough.md.resolved.1
│   ├── walkthrough.md.resolved.2
│   ├── walkthrough.md.resolved.3
│   ├── walkthrough.md.resolved.4
│   └── walkthrough.md.resolved.5
├── ed49ed87-392d-4be8-a7e6-fdf96dbadd32
├── f430e5d6-559c-4797-a0b9-73185547afc6
│   ├── implementation_plan.md
│   ├── implementation_plan.md.metadata.json
│   ├── implementation_plan.md.resolved
│   ├── implementation_plan.md.resolved.0
│   ├── implementation_plan.md.resolved.1
│   ├── implementation_plan.md.resolved.2
│   ├── task.md
│   ├── task.md.metadata.json
│   ├── task.md.resolved
│   ├── task.md.resolved.0
│   ├── task.md.resolved.1
│   ├── task.md.resolved.2
│   └── task.md.resolved.3
└── tempmediaStorage

19 directories, 235 files

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

python 으로 telegram + fatherbot 연동하기  (0) 2026.04.08
ollama 설치  (0) 2026.04.08
agi를 느꼈다?  (0) 2026.02.24
gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 사용량 끝!  (0) 2026.02.20
Posted by 구차니

agi를 신, 성령, 신성력으로 대체하면 되는건가

기계로 부터의 신.

기계 장치의 신

기계 신

노예로 만들어진 기계로 만들어진 신

 

인간이라는건 참 간사해서 마음에 들면(?) 인간화 시키는데

그럼 이제 ai는 피그말리온 효과를 넘어 인격에서 신으로 나아갈 것인가..

 

'클로드 코드' 개발자 "내부용 실험 도구로 개발...사용 중 AGI 느껴"
임대준 기자업데이트 2026.02.23 18:48  댓글 0

[링크 : https://www.aitimes.com/news/articleView.html?idxno=207095]

 

알트먼 "GPT-4.5 테스트 중 AGI 느꼈다는 평 많아"
임대준 기자업데이트 2025.02.18 21:26  댓글 0

[링크 : https://www.aitimes.com/news/articleView.html?idxno=168094]

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

ollama 설치  (0) 2026.04.08
antigravity artifact  (0) 2026.03.18
gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 사용량 끝!  (0) 2026.02.20
antigravity 설치  (0) 2026.02.11
Posted by 구차니

무료 로그인시

 

 

회사 계정 로그인시(google workspace)

 

심심해서 이미지 생성 하고 그걸 다운로드 받은후 새 채팅으로 동영상 생성을 시작해서 해보는데

음.. 하루 3개?

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

antigravity artifact  (0) 2026.03.18
agi를 느꼈다?  (0) 2026.02.24
antigravity 사용량 끝!  (0) 2026.02.20
antigravity 설치  (0) 2026.02.11
gemini cli 에서 gemini 3 flash 사용  (0) 2026.02.11
Posted by 구차니

한 30~40분? 두개 동시에 좀 돌렸더니 사용량 끝! 해버렸다

나름 회사에서 google workspace 써서 유료일텐데도 쿼터가 낮은가 보다.

그 와중에 3.1 Pro는 막상 사용하려고 하면 안되면서

3.0 Pro와 동시에 경고 떠서 쭈르륵 못쓰는건 무슨 유머(?) 일까 

 

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

agi를 느꼈다?  (0) 2026.02.24
gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 설치  (0) 2026.02.11
gemini cli 에서 gemini 3 flash 사용  (0) 2026.02.11
gemini-cli 시도 실패  (0) 2025.07.15
Posted by 구차니

그나저나 바이너리 아니었나 800M를 160MB로 만들어지다니..

$ sudo apt install antigravity
패키지 목록을 읽는 중입니다... 완료
의존성 트리를 만드는 중입니다... 완료
상태 정보를 읽는 중입니다... 완료        
다음 새 패키지를 설치할 것입니다:
  antigravity
0개 업그레이드, 1개 새로 설치, 0개 제거 및 1개 업그레이드 안 함.
159 M바이트 아카이브를 받아야 합니다.
이 작업 후 786 M바이트의 디스크 공간을 더 사용하게 됩니다.

[링크 : https://antigravity.google/download/linux]

 

아니 왜 창이 안 옮겨져? 아무튼 Next

 

귀찮으니 기본값으로 ㄱㄱ

 

로그인 하고(구글) 동의

 

대화창 하단에 Gemini / Claude / chatGPT 쓸수 있는것 처럼 나오는데

다른 모델로 한번 다음에 시도해봐야겠다.

 

+

2026.02.12

4.5 는 안되는데 4.6을 써보라고 한다. 착하다고 해야하나? ㅋㅋ

Posted by 구차니

아래 링크에서 계정 로그인해서 api key 얻고

[링크 : https://aistudio.google.com/]

 

그냥 속편하게(?) gemini 에서

/auth logout

명령으로 로그아웃 이후 exit 하고(그냥 바로 login 해도 될 듯?)

gemini 실행, api 키로 로그인

 

링크에서 api 키 복사해와서 넣고

 

gemini 3 flash and pro 쓸수 있다고 쓰는데

비활성화 되어있어서  preview features를 활성화 하라고 한다.

 

/settings 누르고 스페이스 누르면 false가 true로 바뀌고

 

/model 명령을 통해 auto (gemini 3)가 선택이 되면 된다.

 

모델 바꾸고 질문하자마자 할당량 고갈?!?! 야이 -_-???

 

[링크 : https://geminicli.com/docs/cli/commands/]

 

+

일단 시간이 지나서 메일이 오고 나니 그 이후에 되는 듯.

Posted by 구차니

개인 권한으로 하려니 안되서 어쩔수 없이 root 권한으로 설치 --

sudo npm install -g @google/gemini-cli

[링크 : https://github.com/google-gemini/gemini-cli]

 

 

 

 

 

이후에 계정 연동해서 하려는데 회사 계정으로는 안된다.

나중에 개인 계정으로 시도해 봐야겠다.

 

 

 

Posted by 구차니

다음의 날씨 + 지역

키워드를 이용해서 나오는 정보를 가져오고

그걸 프론트에서 svg 애니메이션 아이콘과 함께 출력하는 웹 페이지를 만들어 봄

 

배경은 밤에는 짙은 하늘색

낮에는 점진적으로 변하는 파란색이다.

 

 

python을 flask로 작동하는데

링크만 주고 빼오면 되는거라, 작동안하면 그 때 또 링크 주고 해달라고 하면 되겠지 머 ㅋㅋ

 

weather.zip
0.01MB

'프로그램 사용 > ai 프로그램' 카테고리의 다른 글

gemini 동영상 만들기 (유료?)  (0) 2026.02.22
antigravity 사용량 끝!  (0) 2026.02.20
antigravity 설치  (0) 2026.02.11
gemini cli 에서 gemini 3 flash 사용  (0) 2026.02.11
gemini-cli 시도 실패  (0) 2025.07.15
Posted by 구차니