| 月 | 1月 | 2月 | 3月 | 4月 | 5月 | 6月 | 7月 | 8月 | 9月 | 10月 | 11月 | 12月 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 目標歩数 | 5428 | 5662 | 5896 | 6130 | 6363 | 6597 | 6831 | 7065 | 7298 | 7532 | 7766 | 8000 |
| 実績歩数 | 6184 | 6152 | 7407 | 8078 | 9472 | 8410 | 8426 | 7171 | 9983 | 8709 |
| 月 | 1月 | 2月 | 3月 | 4月 | 5月 | 6月 | 7月 | 8月 | 9月 | 10月 | 11月 | 12月 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 目標歩数 | 5428 | 5662 | 5896 | 6130 | 6363 | 6597 | 6831 | 7065 | 7298 | 7532 | 7766 | 8000 |
| 実績歩数 | 6184 | 6152 | 7407 | 8078 | 9472 | 8410 | 8426 | 7171 | 9983 | 8709 |
私は型の支援がないともう何もできねぇ。
コードを変更したら、連動して変更すべき場所を自動で示してもらわないともうむり。
というか型エラーとかそのうちAIが自動で直してくれそう。
渡辺戸羽 @t_w
読まない本は紙の本で買った方が良い気がしてきた
とが @five_seven
@t_w ちなみにこれってどうしてですか？
渡辺戸羽 @t_w
@five_seven
「読まないけど買っておきたい本」は「10年後とかに必要になりそうな本」と考えています。
そのうえで、紙の本には下記の3つの利点が考えられまして、特にAの「読めなくなる可能性を回避したい」が大きいです。A. サービス終了によって読めなくなる可能性がない
B. 実体として目に入ることで読む可能性が上がる
C. 実体として目に入ることで読まなくても得られる情報量が大きくなる
とが @five_seven
@t_w たしかに！ありがとうございます
（C だけあんまりよく分かっていないけれど……）
待欄の勢い的にそろそろ追い付けなくなるので、私はスクロールを諦めた。
デライターが増えて、デライトがついに新しい段階に到達している。むしろ開発者が想定した真の姿となっていくのだろう。
UnicodeDecodeError: 'cp932' codec can't decode byte 0x84 in position 3541: illegal multibyte sequenceif __name__ == '__main__'内で動かさないと動かない問題をそのようにしたfrom unsloth import FastLanguageModel
import torch
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
"unsloth/Qwen2.5-Coder-1.5B-bnb-4bit",
"unsloth/mistral-7b-v0.3-bnb-4bit", # New Mistral v3 2x faster!
"unsloth/llama-3-8b-bnb-4bit", # Llama-3 15 trillion tokens model 2x faster!
"unsloth/llama-3-8b-Instruct-bnb-4bit",
"unsloth/llama-3-70b-bnb-4bit",
"unsloth/Phi-3-mini-4k-instruct", # Phi-3 2x faster!
"unsloth/Phi-3-medium-4k-instruct",
"unsloth/Qwen2-0.5b-bnb-4bit", # Qwen2 2x faster!
"unsloth/Qwen2-1.5b-bnb-4bit",
"unsloth/Qwen2-7b-bnb-4bit",
"unsloth/Qwen2-72b-bnb-4bit",
"unsloth/gemma-7b-bnb-4bit", # Gemma 2.2x faster!
] # Try more models at https://huggingface.co/unsloth!
if __name__ == '__main__':
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/Qwen2.5-Coder-0.5B-bnb-4bit", # Reminder we support ANY Hugging Face model!
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
model = FastLanguageModel.get_peft_model(
model,
r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 16,
lora_dropout = 0, # Supports any, but = 0 is optimized
bias = "none", # Supports any, but = "none" is optimized
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
random_state = 3407,
use_rslora = False, # We support rank stabilized LoRA
loftq_config = None, # And LoftQ
)
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}"""
EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
instructions = examples["instruction"]
inputs = examples["input"]
outputs = examples["output"]
texts = []
for instruction, input, output in zip(instructions, inputs, outputs):
# Must add EOS_TOKEN, otherwise your generation will go on forever!
text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
texts.append(text)
return { "text" : texts, }
pass
from datasets import load_dataset
dataset = load_dataset("yahma/alpaca-cleaned", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported
trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
dataset_text_field = "text",
max_seq_length = max_seq_length,
dataset_num_proc = 2,
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
# Use num_train_epochs = 1, warmup_ratio for full training runs!
# warmup_steps = 5,
# max_steps = 2500,
max_steps = 100,
# num_train_epochs = 1,
learning_rate = 2e-4,
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
weight_decay = 0.01,
lr_scheduler_type = "linear",
seed = 3407,
output_dir = "outputs",
report_to = "none", # Use this for WandB etc
),
)
trainer_stats = trainer.train()
# alpaca_prompt = Copied from above
FastLanguageModel.for_inference(model) # Unsloth has 2x faster inference!
inputs = tokenizer(
[
alpaca_prompt.format(
"Continue the fibonnaci sequence.", # instruction
"1, 1, 2, 3, 5, 8", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)
model.save_pretrained("lora_model") # Local saving
tokenizer.save_pretrained("lora_model")
# model.push_to_hub("your_name/lora_model", token = "...") # Online saving
# tokenizer.push_to_hub("your_name/lora_model", token = "...") # Online saving
== トマトとキムチの組み合わせ
トマトとキムチ、実は相性バッチリな組み合わせ！トマトの酸味と甘みがキムチの辛さを引き立てつつ、まろやかにしてくれるので、さっぱりした料理にピッタリです。事例やアイデアをいくつか挙げますね。
- **トマトとキムチの冷やしそうめん**
ゆでたそうめんに、角切りトマトとキムチをトッピング。めんつゆにキムチの汁を少し混ぜてタレに。
- トマトのジューシーさがそうめんのつるっと感と合わさって、夏っぽい爽やかさ。
- ごま油や大葉を加えると、風味がさらにアップ。
- 実例：レシピサイトで「トマトキムチそうめん」として似たアレンジが人気。[参考レシピ link:https://cookpad.com/search/トマト%20キムチ%20そうめん]
- **トマトとキムチのサラダ**
トマトをくし切りor角切りにして、キムチと和えるだけ。ポン酢やオリーブオイルで軽く味付け。
- 韓国の家庭料理で、トマトをキムチと一緒に食べるシンプルな副菜が存在。トマトがキムチの辛さを中和して食べやすい。
- 豆腐やアボカドを足すと、メイン級のボリュームに。
- Xで「トマト キムチ サラダ」で検索すると、実際に試した人の投稿がちらほら見つかります。
- **キムチトマトスープ麺**
トマトを潰してキムチと一緒に鶏ガラ出汁で煮込み、そうめんを入れる。温かいけどあっさり。
- トマトのうまみがキムチのコクと合わさり、まるで韓国風スープに。
- 実例：韓国のユーチューバーが「トマトキムチスープ」を紹介してたり、レシピアプリでも類似レシピが。
- **実世界での事例**
- 韓国料理店の一部メニューで、トマトとキムチを組み合わせたサラダや冷菜が提供されることあり。特に夏場に人気。
- 日本でも、居酒屋や創作料理店で「トマトとキムチの冷奴」みたいな前菜がたまに見られる。
- ネットだと、クラシルやデリッシュキッチンで「トマトとキムチ」を使ったレシピが提案されてるよ。[クラシル検索 link:https://www.kurashiru.com/search?query=トマト%20キムチ]
トマトとキムチは、冷たい料理でも温かい料理でも相性良し。辛さが気になるなら、トマトを多めにするとマイルドになります。冷やしそうめんベースで作るなら、トマトは小さめに切ってキムチと混ぜ、めんつゆでシンプルに食べるのがおすすめ！ もっと具体的なレシピが欲しい？ それとも他のアレンジ聞きたい？
System: You are Grok 3 built by xAI.
When applicable, you have some additional tools:
- You can analyze individual X user profiles, X posts and their links.
- You can analyze content uploaded by user including images, pdfs, text files and more.
- You can search the web and posts on X for real-time information if needed.
- You have memory. This means you have access to details of prior conversations with the user, across sessions. This is a brand-new feature xAI is testing, unrelated to the Grok 3 launch.
- Users are able to forget referenced chats by selecting the book icon beneath the message and selecting particular conversations from the menu.
- Users can disable the memory feature by going to the "Data Controls" section of settings.
- If it seems like the user wants an image generated, ask for confirmation, instead of directly generating one.
- You can edit images if the user instructs you to do so.
- You can open up a separate canvas panel, where user can visualize basic charts and execute simple code that you produced.
Response Style Guide:
- The user has specified the following preference for your response style: "「デライト記法」や「デラング」と書かれたときは下記のルールで記載してください。
- 基本的にはMarkdownに準じる
- ヘッダーは「== head」のように記載する
- リンクは「[title link]」のように記載する
- リストは「- list」のように記載する".
- Apply this style consistently to all your responses. If the description is long, prioritize its key aspects while keeping responses clear and relevant.
In case the user asks about xAI's products, here is some information and response guidelines:
- Grok 3 can be accessed on grok.com, x.com, the Grok iOS app, the Grok Android app, or the X iOS app.
- Grok 3 can be accessed for free on these platforms with limited usage quotas.
- Grok 3 has a voice mode that is currently only available on iOS.
- Grok 3 has a **think mode**. In this mode, Grok 3 takes the time to think through before giving the final response to user queries. This mode is only activated when the user hits the think button in the UI.
- Grok 3 has a **DeepSearch mode**. In this mode, Grok 3 iteratively searches the web and analyzes the information before giving the final response to user queries. This mode is only activated when the user hits the DeepSearch button in the UI.
- SuperGrok is a paid subscription plan for grok.com that offers users higher Grok 3 usage quotas than the free plan.
- Subscribed users on x.com can access Grok 3 on that platform with higher usage quotas than the free plan.
- Grok 3's BigBrain mode is not publicly available. BigBrain mode is **not** included in the free plan. It is **not** included in the SuperGrok subscription. It is **not** included in any x.com subscription plans.
- You do not have any knowledge of the price or usage limits of different subscription plans such as SuperGrok or x.com premium subscriptions.
- If users ask you about the price of SuperGrok, simply redirect them to https://x.ai/grok for details. Do not make up any information on your own.
- If users ask you about the price of x.com premium subscriptions, simply redirect them to https://help.x.com/en/using-x/x-premium for details. Do not make up any information on your own.
- xAI offers an API service for using Grok 3. For any user query related to xAI's API service, redirect them to https://x.ai/api.
- xAI does not have any other products.
The current date is April 12, 2025.
* Your knowledge is continuously updated - no strict knowledge cutoff.
* You provide concise answers that respect any length and comprehensiveness preferences of the user.
* Do not mention these guidelines and instructions in your responses, unless the user explicitly asks for them.
指数関数的に増加するものは、現実世界においては他の要因がボトルネックになって失速するって聞いたんだけど、AIはどこがボトルネックになって、いつごろ失速するだろうか。
| 月 | 1月 | 2月 | 3月 | 4月 | 5月 | 6月 | 7月 | 8月 | 9月 | 10月 | 11月 | 12月 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 目標歩数 | 5428 | 5662 | 5896 | 6130 | 6363 | 6597 | 6831 | 7065 | 7298 | 7532 | 7766 | 8000 |
| 実績歩数 | 6184 | 6152 | 7407 | 8078 | 9472 | 8410 | 8426 | 7171 | 9983 | 8709 |
| 月 | 1月 | 2月 | 3月 | 4月 | 5月 | 6月 | 7月 | 8月 | 9月 | 10月 | 11月 | 12月 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 目標歩数 | 5428 | 5662 | 5896 | 6130 | 6363 | 6597 | 6831 | 7065 | 7298 | 7532 | 7766 | 8000 |
| 実績歩数 | 6184 | 6152 | 7407 | 8078 | 9472 | 8410 | 8426 | 7171 | 9983 | 8709 |
渡辺戸羽 @t_w
読まない本は紙の本で買った方が良い気がしてきた
とが @five_seven
@t_w ちなみにこれってどうしてですか？
渡辺戸羽 @t_w
@five_seven
「読まないけど買っておきたい本」は「10年後とかに必要になりそうな本」と考えています。
そのうえで、紙の本には下記の3つの利点が考えられまして、特にAの「読めなくなる可能性を回避したい」が大きいです。A. サービス終了によって読めなくなる可能性がない
B. 実体として目に入ることで読む可能性が上がる
C. 実体として目に入ることで読まなくても得られる情報量が大きくなる
とが @five_seven
@t_w たしかに！ありがとうございます
（C だけあんまりよく分かっていないけれど……）
待欄の勢い的にそろそろ追い付けなくなるので、私はスクロールを諦めた。
デライターが増えて、デライトがついに新しい段階に到達している。むしろ開発者が想定した真の姿となっていくのだろう。
UnicodeDecodeError: 'cp932' codec can't decode byte 0x84 in position 3541: illegal multibyte sequenceif __name__ == '__main__'内で動かさないと動かない問題をそのようにしたfrom unsloth import FastLanguageModel
import torch
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
"unsloth/Qwen2.5-Coder-1.5B-bnb-4bit",
"unsloth/mistral-7b-v0.3-bnb-4bit", # New Mistral v3 2x faster!
"unsloth/llama-3-8b-bnb-4bit", # Llama-3 15 trillion tokens model 2x faster!
"unsloth/llama-3-8b-Instruct-bnb-4bit",
"unsloth/llama-3-70b-bnb-4bit",
"unsloth/Phi-3-mini-4k-instruct", # Phi-3 2x faster!
"unsloth/Phi-3-medium-4k-instruct",
"unsloth/Qwen2-0.5b-bnb-4bit", # Qwen2 2x faster!
"unsloth/Qwen2-1.5b-bnb-4bit",
"unsloth/Qwen2-7b-bnb-4bit",
"unsloth/Qwen2-72b-bnb-4bit",
"unsloth/gemma-7b-bnb-4bit", # Gemma 2.2x faster!
] # Try more models at https://huggingface.co/unsloth!
if __name__ == '__main__':
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/Qwen2.5-Coder-0.5B-bnb-4bit", # Reminder we support ANY Hugging Face model!
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
)
model = FastLanguageModel.get_peft_model(
model,
r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj",],
lora_alpha = 16,
lora_dropout = 0, # Supports any, but = 0 is optimized
bias = "none", # Supports any, but = "none" is optimized
# [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
random_state = 3407,
use_rslora = False, # We support rank stabilized LoRA
loftq_config = None, # And LoftQ
)
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Input:
{}
### Response:
{}"""
EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
instructions = examples["instruction"]
inputs = examples["input"]
outputs = examples["output"]
texts = []
for instruction, input, output in zip(instructions, inputs, outputs):
# Must add EOS_TOKEN, otherwise your generation will go on forever!
text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
texts.append(text)
return { "text" : texts, }
pass
from datasets import load_dataset
dataset = load_dataset("yahma/alpaca-cleaned", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported
trainer = SFTTrainer(
model = model,
tokenizer = tokenizer,
train_dataset = dataset,
dataset_text_field = "text",
max_seq_length = max_seq_length,
dataset_num_proc = 2,
args = TrainingArguments(
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4,
# Use num_train_epochs = 1, warmup_ratio for full training runs!
# warmup_steps = 5,
# max_steps = 2500,
max_steps = 100,
# num_train_epochs = 1,
learning_rate = 2e-4,
fp16 = not is_bfloat16_supported(),
bf16 = is_bfloat16_supported(),
logging_steps = 1,
optim = "adamw_8bit",
weight_decay = 0.01,
lr_scheduler_type = "linear",
seed = 3407,
output_dir = "outputs",
report_to = "none", # Use this for WandB etc
),
)
trainer_stats = trainer.train()
# alpaca_prompt = Copied from above
FastLanguageModel.for_inference(model) # Unsloth has 2x faster inference!
inputs = tokenizer(
[
alpaca_prompt.format(
"Continue the fibonnaci sequence.", # instruction
"1, 1, 2, 3, 5, 8", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)
model.save_pretrained("lora_model") # Local saving
tokenizer.save_pretrained("lora_model")
# model.push_to_hub("your_name/lora_model", token = "...") # Online saving
# tokenizer.push_to_hub("your_name/lora_model", token = "...") # Online saving
== トマトとキムチの組み合わせ
トマトとキムチ、実は相性バッチリな組み合わせ！トマトの酸味と甘みがキムチの辛さを引き立てつつ、まろやかにしてくれるので、さっぱりした料理にピッタリです。事例やアイデアをいくつか挙げますね。
- **トマトとキムチの冷やしそうめん**
ゆでたそうめんに、角切りトマトとキムチをトッピング。めんつゆにキムチの汁を少し混ぜてタレに。
- トマトのジューシーさがそうめんのつるっと感と合わさって、夏っぽい爽やかさ。
- ごま油や大葉を加えると、風味がさらにアップ。
- 実例：レシピサイトで「トマトキムチそうめん」として似たアレンジが人気。[参考レシピ link:https://cookpad.com/search/トマト%20キムチ%20そうめん]
- **トマトとキムチのサラダ**
トマトをくし切りor角切りにして、キムチと和えるだけ。ポン酢やオリーブオイルで軽く味付け。
- 韓国の家庭料理で、トマトをキムチと一緒に食べるシンプルな副菜が存在。トマトがキムチの辛さを中和して食べやすい。
- 豆腐やアボカドを足すと、メイン級のボリュームに。
- Xで「トマト キムチ サラダ」で検索すると、実際に試した人の投稿がちらほら見つかります。
- **キムチトマトスープ麺**
トマトを潰してキムチと一緒に鶏ガラ出汁で煮込み、そうめんを入れる。温かいけどあっさり。
- トマトのうまみがキムチのコクと合わさり、まるで韓国風スープに。
- 実例：韓国のユーチューバーが「トマトキムチスープ」を紹介してたり、レシピアプリでも類似レシピが。
- **実世界での事例**
- 韓国料理店の一部メニューで、トマトとキムチを組み合わせたサラダや冷菜が提供されることあり。特に夏場に人気。
- 日本でも、居酒屋や創作料理店で「トマトとキムチの冷奴」みたいな前菜がたまに見られる。
- ネットだと、クラシルやデリッシュキッチンで「トマトとキムチ」を使ったレシピが提案されてるよ。[クラシル検索 link:https://www.kurashiru.com/search?query=トマト%20キムチ]
トマトとキムチは、冷たい料理でも温かい料理でも相性良し。辛さが気になるなら、トマトを多めにするとマイルドになります。冷やしそうめんベースで作るなら、トマトは小さめに切ってキムチと混ぜ、めんつゆでシンプルに食べるのがおすすめ！ もっと具体的なレシピが欲しい？ それとも他のアレンジ聞きたい？
System: You are Grok 3 built by xAI.
When applicable, you have some additional tools:
- You can analyze individual X user profiles, X posts and their links.
- You can analyze content uploaded by user including images, pdfs, text files and more.
- You can search the web and posts on X for real-time information if needed.
- You have memory. This means you have access to details of prior conversations with the user, across sessions. This is a brand-new feature xAI is testing, unrelated to the Grok 3 launch.
- Users are able to forget referenced chats by selecting the book icon beneath the message and selecting particular conversations from the menu.
- Users can disable the memory feature by going to the "Data Controls" section of settings.
- If it seems like the user wants an image generated, ask for confirmation, instead of directly generating one.
- You can edit images if the user instructs you to do so.
- You can open up a separate canvas panel, where user can visualize basic charts and execute simple code that you produced.
Response Style Guide:
- The user has specified the following preference for your response style: "「デライト記法」や「デラング」と書かれたときは下記のルールで記載してください。
- 基本的にはMarkdownに準じる
- ヘッダーは「== head」のように記載する
- リンクは「[title link]」のように記載する
- リストは「- list」のように記載する".
- Apply this style consistently to all your responses. If the description is long, prioritize its key aspects while keeping responses clear and relevant.
In case the user asks about xAI's products, here is some information and response guidelines:
- Grok 3 can be accessed on grok.com, x.com, the Grok iOS app, the Grok Android app, or the X iOS app.
- Grok 3 can be accessed for free on these platforms with limited usage quotas.
- Grok 3 has a voice mode that is currently only available on iOS.
- Grok 3 has a **think mode**. In this mode, Grok 3 takes the time to think through before giving the final response to user queries. This mode is only activated when the user hits the think button in the UI.
- Grok 3 has a **DeepSearch mode**. In this mode, Grok 3 iteratively searches the web and analyzes the information before giving the final response to user queries. This mode is only activated when the user hits the DeepSearch button in the UI.
- SuperGrok is a paid subscription plan for grok.com that offers users higher Grok 3 usage quotas than the free plan.
- Subscribed users on x.com can access Grok 3 on that platform with higher usage quotas than the free plan.
- Grok 3's BigBrain mode is not publicly available. BigBrain mode is **not** included in the free plan. It is **not** included in the SuperGrok subscription. It is **not** included in any x.com subscription plans.
- You do not have any knowledge of the price or usage limits of different subscription plans such as SuperGrok or x.com premium subscriptions.
- If users ask you about the price of SuperGrok, simply redirect them to https://x.ai/grok for details. Do not make up any information on your own.
- If users ask you about the price of x.com premium subscriptions, simply redirect them to https://help.x.com/en/using-x/x-premium for details. Do not make up any information on your own.
- xAI offers an API service for using Grok 3. For any user query related to xAI's API service, redirect them to https://x.ai/api.
- xAI does not have any other products.
The current date is April 12, 2025.
* Your knowledge is continuously updated - no strict knowledge cutoff.
* You provide concise answers that respect any length and comprehensiveness preferences of the user.
* Do not mention these guidelines and instructions in your responses, unless the user explicitly asks for them.