messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "You are tasked with implementing a read-only dictionary in Python. Create a function called `create_read_only_dict` that takes a dictionary as an input and returns an instance of a read-only dictionary. The read-only dictionary should behave like a regular dictionary, but it sh... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n_incomplete_tasks(TASKS_FILE.read_text())\\n if remaining == 0:\\n print(\\\"all tasks checked off — ralph loop complete\\\")\\n return\\n print(f\\\"iteration {iteration}: {remaining} tasks remaining\\\")\\n ret... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Design a function `manage_processes(operations: List[Tuple[str, Union[str, int]]]) -> List[Union[int, bool, Dict[str, Union[str, int]]]]` that simulates a simplified process manager. The `operations` parameter is a list of tuples where each tuple contains an operation and its c... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a message storage system. The system should allow users to add and replace messages. Each message will consist of a header and a body. Your goal is to implement two functions: `add_message(header: str, body: str) -> str` and `replace_message(key... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "<local-command-stdout>Set model to \u001b[1mFable 5\u001b[22m and saved as your default for new sessions with \u001b[1mmedium\u001b[22m effort</local-command-stdout>\nMasssivly overhaul this UI, add a discord mode and search mode, and fun fact mode. DIscord mode: look at all ch... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of groups, where each group consists of multiple people's answers to a set of questions, represented as a list of strings. Each person's answers are on a separate string within the group. Your task is to find the total number of questions to which everyone ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that calculates the tax based on a given income and a dictionary of setup parameters. The function should be called `calculate_tax(income, setup_params)` and take two arguments: \n- `income`: A float representing the income for whi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that raises a custom exception when invalid input is detected. Implement a function named `validate_input` that takes a single argument `input_data`. If `input_data` is None or an empty string, the function should raise an `InvalidInputEr... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>btf58zd0z</task-id>\n<tool-use-id>toolu_01RbEnx8qxuKozmtx4tPU2Wq</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/5eeb7e10-99a4-4d7d-a505-3ef47dcab480/tasks/btf58zd0z.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes an API response represented as a dictionary. The dictionary contains two keys: 'status' and 'data'. Your function should return a string based on the value of 'status'. If 'status' is 200, return the value associated... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "GLI-20\nNo project\n\n\n\nhirer\nan agent that can hire (make) new people to work here.\n\nNew Sub-task\n\nUpload attachment\n\nNew document\nChat\nActivity\nRelated work\nJump to latest\n\nCEO\nworked for 1 minute\n2m ago\nCEO\nAcknowledgement of the latest state\n\nThere are ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "User: thoughts on my hyper-parameters?\nAssistant: Let me look at your training setup first.\nAssistant action: Glob {\"path\": \"C:\\\\Users\\\\user1\\\\Documents\\\\github\\\\distillery-scripts\\\\sft-distillation\", \"pattern\": \"**/*\"}\nResult: qwen3.5\\new-method\\qwen3.... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nipeline with e2e test\\\" && git log --oneline -1\", \"description\": \"Full suite then commit entry point\"}\nResult: ........................ [100%]\n96 passed in 4.23s\nc27d63d add train.py entry orchestr... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that generates a signed URL for email verification based on a given base URL and a unique identifier (e.g., user ID or email). The signing process involves creating a hash using a salt and appending a timestamp to the URL. The functio... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Make this UI mobile freindly\nAssistant action: Bash {\"command\": \"ls /home/user/Blindbot/hf_space\", \"description\": \"List hf_space files\"}\nResult: app.py\nDockerfile\n__pycache__\nrequirements.txt\nstatic\nAssistant action: Bash {\"command\": \"ls /home/user/Blindbot/hf... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "then collect ever\nResult: The file /home/lane/GR/glint-cli/src/core/config.ts has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant: Now build, type-check, and test that orphaned agents get cleaned up and the todo nudge fir... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n const update = (next: string, nextCursor: number) => {\\n setValue(next);\\n setCursor(Math.max(0, Math.min(nextCursor, next.length)));\\n onChange?.(next);\\n };\\n\\n useInput((input, key) => {\\n if (key.return) {\\n const trimmed ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "I dont see it.[Image #1]\n[Image: source: /home/user/.claude/image-cache/68396a0d-8585-4d00-9321-54b2b00c07f4/1.png]\nAssistant action: Bash {\"command\": \"ps aux | grep -E \\\"vite|paperclip\\\" | grep -v grep | head; ss -ltnp 2>/dev/null | grep -E \\\"3100|5173\\\" | head\",... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>bmpqoq5ga</task-id>\n<tool-use-id>toolu_01E5bZ7Z5HnGDxT8cQt1SLNo</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/e24a84d9-b09d-4531-97ce-3c078924b269/tasks/bmpqoq5ga.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "User: Make a hyper detailed agents.md file that tells whoever is reading it (an AI agent) the following. 1. Never use placeholders/examples 2. Never use comments, but describe each function throughly in docs/functions.md for quick loopkups. 3. Keep a hyper detailed journal in j... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simplified training loop for a machine learning model. The function should take in a list of loss values for each epoch and return the average loss for every 5 epochs. Additionally, if the epoch number is a multiple o... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Make it more promint, this entire thing was made (in part) by glint research.\nAssistant action: Bash {\"command\": \"sed -n '1,120p' /home/user/MythosMini/slm_alliance.html | cut -c1-160\", \"description\": \"View head/styles for theme colors\"}\nResult: <!DOCTYPE html>\n<html... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>bwgkd0xis</task-id>\n<tool-use-id>toolu_01TVJ3GvCJbTbUh8YVDTF1Uf</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane/22bb18a2-14fc-4d00-b566-037d9c98da2f/tasks/bwgkd0xis.output</output-file>\n<status>completed</status>\n<summary>Background comm... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that validates an event data dictionary. The function should ensure that the event data meets certain criteria before it can be considered valid. The function should accept a dictionary called `event_data`, which contains the follo... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncreated successfully: Build fineweb-edu streaming data pipeline\nAssistant action: TaskCreate {\"subject\": \"Build training loop + checkpointing + telemetry\", \"description\": \"NAdamW, WSD schedule, bf16, OOM recovery, non-blocking background checkpoin... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are working on a game that involves casting spells using mana. Each spell requires a certain amount of mana to cast. Your task is to write a function `calculate_probability` that takes two parameters: an integer `total_mana` representing the total amount of mana available, ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n239bb/node_modules/@paperclipai/server/dist/routes/instance-settings.js:80:router.post(\"/instance/settings/experimental/issue-graph-liveness-auto-recovery/run\"\n/home/lane/.npm/_npx/43414d9b790239bb/node_modules/@paperclipai/server/dist/routes/issues.js... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": ", 'model': 'claude-fable-5', 'context': 'USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result a', 'cot': \"Alright, I've got a decen... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a simple feature flag management system. A feature flag is a way to control the visibility of a feature in an application. Your goal is to implement a function `manage_feature_flags` that takes a list of feature names and returns a list of uniqu... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes payment data based on certain rules. The function should take the following parameters: a boolean `BARCODE`, an integer `Amt`, a request object `request`, a string `ReturnURL`, and a string `NotifyURL`. Your function sh... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a concise coding assistant. Provide working code with brief explanations."
},
{
"role": "user",
"content": "What is the output of this code?\n```python\nx = [1, 2, 3]\ny = x\ny.append(4)\nprint(x)\n```"
},
{
"role": "assistant",
"content": "```... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "ompt_eval_cou\n=== stock arch ===\n architecture qwen35 \n parameters 4.7B \n Parameters\n=== mine ===\n architecture qwen35 \n parameters 4.2B \n Parameters\nAssistant: Both `qwen35`, stock runs — so it's a layer-pa... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "How do I start this?"
},
{
"role": "assistant",
"content": "<think>\nThe user’s message is extremely brief: “How do I start this?” There’s no explicit context about what “this” refers to. I need to infer what the user likely wants based on the environment I have acc... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are given a DNA sequence represented as a string, containing the characters 'A', 'C', 'G', 'T', 'N', 'M', 'K', 'R', 'Y', 'S', 'W', 'B', 'V', 'D'. Your task is to return a list of all possible complementary sequences derived from the input sequence based on a given mapping o... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n not isinstance(prompts_file, str):\\n payload = {**payload, \\\"prompts_file\\\": None}\", \"new_string\": \" prompts_file = payload.get(\\\"prompts_file\\\")\\n if isinstance(prompts_file, str) and prompts_file.strip():\\n ... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a `wait_until` function that waits for a condition to be met within a specified timeout period. The function should repeatedly check the condition until it evaluates to `True` or until the timeout period is exceeded. If the condition is met with... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n \"dangerouslyDisableSandbox\": false}\nResult: <tool_use_error>Blocked: sleep 40 followed by: cat /tmp/claude-1000/-home-lane-MythosMini/471accf0-3df7-4e2e-a567-a094f8f8d585/tasks/b01o94n7g.output. To wait for a condition, use Monitor with an until-loop ... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a senior backend engineer specializing in transactional database systems. Diagnose lock contention and deadlock issues with concrete reproductions and offer remediation grounded in isolation level semantics."
},
{
"role": "user",
"content": "We're seeing i... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates a note-taking application. The function should take in a title, content, and a boolean value indicating whether the note is pinned or not. It should return the number of words in the note's content. Implement a function cal... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n \\\"opencode\\\",\\n \\\"run\\\",\\n \\\"--print-logs\\\",\\n \\\"--log-level\\\",\\n \\\"ERROR\\\",\\n \\\"--model\\\",\\n OPENCODE_MODEL,\\n prompt,\\n ]\\n\\n\\ndef ask_use_claude() -> bool:\\n ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that calculates the total cost of a customer's purchase, including sales tax and a possible discount. The function should take four parameters: item_price (a float representing the item's price), tax_rate (a float representing the sales t... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that transliterates a given input string into a different script. Write a function called `transliterate` that takes a single string as input and returns the transliterated version of that string. For the purpose of this problem, l... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a string containing Markdown text. Your task is to write a function `extract_hyperlinks(markdown_text: str) -> List[Tuple[str, str]]` that extracts all hyperlinks from the text. Each hyperlink is represented in Markdown format as `[anchor_text](url)`. The function... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nm starlette.testclient import TestClient as TestClient # noqa\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"C:\\\\Users\\\\aranr\\\\Documents\\\\github\\\\teich\\\\src\\\\teich\\\\studio\\\\project.py\", \"old_string\": \" prom... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a large integer `q`. Your task is to write a program to find the prime factors of this integer and then calculate the sum of all the distinct prime factors. Write a function `sum_of_distinct_prime_factors(q)` that takes the integer `q` as input and returns the sum... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that capitalizes the first and fourth characters of a given string. The function should take a string as input and return the modified string with the specified characters capitalized. If the input string has fewer than four character... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of image data and their corresponding labels. Your task is to implement a function that randomly shuffles the data and labels while maintaining their correspondence. The function should take two lists: `image_data`, a list of lists representing image data, ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "As a technical writer helping draft educational content, i'm a junior developer here. I'm for a client deliverable and lazy and looking for best practices about design a zero-downtime database migration for adding a non-nullable enum. We're on Python/Phoenix with Redis. How do ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nog) { v = Math.log(v); mn = Math.log(mn); mx = Math.log(mx); }\n1374: const a = Math.pow(Math.max(0, Math.min(1, p)), 2.5);\n1375: const r = Math.round(worstGreen[0] + (bestGreen[0] - worstGreen[0]) * a);\n1376: const g = Math.round(worstGreen[1] + (be... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "As a code reviewer providing detailed feedback, i'm confident but seeking validation for an interview prep and trying to understand quicksort vs. mergesort in modern memory hierarchies. I'm a data engineer struggling with why cache behavior matters more than comparison count. W... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are given two lists of floats, `time_steps` and `discount_factors`, representing the bond's time steps and their corresponding discount factors respectively. Your task is to implement a function `recompute_cached_bond_property(time_steps: List[float], discount_factors: List... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ns\"}\nResult: grid 115x66, h=0.0469 m, particles=9786\nt= 0.0s maxSpeed= 1.13 m/s KE/m= 0.107 y∈[0.061,2.089] x∈[0.061,3.332] NaN=0\nt= 2.0s maxSpeed= 7.09 m/s KE/m= 0.972 y∈[0.061,3.031] x∈[0.061,5.330] NaN=0\nt= 4.0s maxSpeed= 7.90 m/... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nL RESULT: \nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"D:\\\\project-5\\\\js\\\\ui.js\", \"old_string\": \" const lines = wrap(text);\\n const w = {\\n kind: 'msg',\\n page: 0, chars: 0, sticky,\\n done,\", \"new... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>\n<command-name>/login</command-n... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are given a list of integers representing energy levels of a particle, a float representing the time of the particle, and a float representing the position of the particle. Your task is to implement a function `check_energy_levels(energy_levels: List[int], time: float, posi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n answers are\\n // fabricated file descriptions. Demand reads of the real files.\\n if (guessNudges < 2 && looksGuessed(res.content)) {\\n guessNudges++;\\n state.messages.push({\\n role: \\\"user\\\",\\n content:... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "\nAssistant: Found issues. Now let me check when game.input.fire is set to false on pause:\nAssistant action: Bash {\"command\": \"grep -n \\\"game.input.fire\\\\|game.input.scope\\\" /home/lane/AIArchives/archives/neonstrike/app/public/js/main.js /home/lane/AIArchives/archives... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a security-focused web engineer reviewing OAuth 2.0 / OIDC implementations. Cite the relevant RFCs and BCPs (especially OAuth 2.0 Security Best Current Practice) when explaining design choices."
},
{
"role": "user",
"content": "I'm wiring up 'Sign in with ... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n root\"}\nResult: functions.md\nresearch\nrules\n/home/lane/MythosMini/journal.md\nAGENTS.md\ndata\ndocs\nexp.py\nexp_quantization.py\nhero_check.png\nhero_debug.png\nhero_fancy_final.png\nhero_fixed.png\nhero_restored.png\nissues.json\njournal.md\nMakefi... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "this (writing the result yourself, then continuing as if it ran):\n144\t[you]: ${TOOL_OPEN}\n145\t{\"tool\": \"bash\", \"args\": {\"command\": \"ls\"}}\n146\t${TOOL_CLOSE}\n147\tOutput: file1.ts file2.ts ← FABRICATION. You did not run anything. END after the block and WAIT fo... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that counts the number of unique characters in a given string. Your function should ignore spaces and be case insensitive. Implement the function `count_unique_characters(s: str) -> int` that takes a string `s` as input and returns the nu... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ne\n2\tfrom dataclasses import dataclass\n3\tfrom typing import cast\n4\t\n5\timport torch\n6\tfrom torch import Tensor, nn\n7\tfrom torch.nn import functional\n8\t\n9\tfrom src.mythosmini.config import ModelConfig\n10\tfrom src.mythosmini.training.fp4 imp... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are given a scenario where a mouse is trying to escape from two cats on a 1-dimensional coordinate system. The positions of the two cats and the mouse are represented by integers `x`, `y`, and `z`, respectively. The distance between the mouse and each cat is calculated as t... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n ⠈⠉⠉\n G L I N T R E S E A R C H\n we teach tiny neural networks to think\nAssistant action: Bash {\"command\": \"bun run scripts/build-logo.ts >/dev/null 2>&1; bun build src/index.tsx --compile --outfile dist/glint 2>&1... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of integers representing the scores of a game played by two players, Alice and Bob, taking alternating turns. The game starts with Alice. On each turn, the current player removes either the first or last element from the list, and their score increases by t... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that calculates the sum of all prime numbers within a given inclusive range defined by two integers, `start` and `end`. A prime number is a natural number greater than 1 that has no positive divisors other than 1 and itself. Yo... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nT (tool call) Edit input={\"replace_all\": false, \"file_path\": \"/home/user/MythosMini/tests/test_ralph_helpers.py\", \"old_string\": \"def test_fallback_triggers_after_three_consecutive_failures() -> None:\\n assert ralph.CONSECUTIVE_FAILURE_LIMIT =... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that validates error codes in a testing framework. Write a function called `validate_error_code` that takes in two parameters: an `error_dict` representing an error with the structure: {'errorCode': <integer>, 'errorMessage': <stri... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a simple event notification system in Python. In this system, you will implement two classes: `Observable` and `Observer`. The `Observable` class maintains a list of observers and notifies them when a new event occurs. The `Observer` class processes... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "k, ExperimentConfig, build_dataset, consensus_vote_decode, exact_match,\\n measure_inference_seconds, run_experiment, time_to_target, train_model, voted_double_decode,\\n greedy_double_decode,\\n)\\n\\nfor digits in (3, 5):\\n for seed in (20260612, 7):\\n c = E... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "ustomer worldwide while keeping other Claude models online (2†n=1).\n • The directive was triggered by a reported jailbreak of Mythos 5 that raised national‑security concerns; Anthropic disputes that\n the vulnerability justifies a full recall (2†n=1).\n • Implications\n ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n64 | head; grep -no 'd97757' /home/lane/MythosMini/slm_alliance.html | grep -v base64; grep -cn \\\"Anthropic Serif\\\\|Anthropic Mono\\\" /home/lane/MythosMini/slm_alliance.html\", \"description\": \"Locate font-face blocks, orange uses, font refs\"}\nRe... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "any way to optimize it so it isnt so laggy/choppy? I want a lot more fps and i dont think it's optimized well for that\nAssistant: The choppiness has three big causes: every frame draws ~2.7M grass vertices with culling disabled, ~10k double-sided leaf cards get re-rendered *tw... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nctions.md\", \"limit\": 30}\nResult: 1\t# Function Reference\n2\t\n3\tSingle lookup table for every function in the codebase. Source code contains no comments; this file replaces them. Entry format and a complete example: `docs/rules/documentation.md`.\n4... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.