messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "…[earlier truncated]…\nyle.css\n 614 /home/user/Blindbot/hf_space/static/app.js\n 150 /home/user/Blindbot/hf_space/static/index.html\n 824 /home/user/Blindbot/hf_space/static/style.css\n 385 /home/user/Blindbot/hf_space/app.py\n 1973 total\nAssistant action: Read {\"file_pa... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "As a patient tutor explaining from first principles, i'm a full-stack developer here, at work. I'm rushed and under deadline about type inference with row polymorphism vs. structural subtyping — when you want extensibility without inheritance. I keep hitting a wall. How do you ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are given a `Packet` class with an attribute `nfmark` representing the packet mark. You also have a `Processor` class that allows you to modify the `nfmark` based on the specified operation. The `Processor` class has the following attributes: \n- `op`: A string representing... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that processes a given string to extract words based on a specific pattern defined by a regular expression. The pattern matches words consisting of uppercase letters, lowercase letters, or numeric characters. Your task is to wr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nut={\"replace_all\": false, \"file_path\": \"/home/user/AIArchives/archives/neonstrike/test/playtest.mjs\", \"old_string\": \"// sky vs ground sanity: looking up differs from looking ahead\\ncheck('sky view differs from spawn view', diffFrac(vshots['06-sk... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nANT (tool call) Read input={\"file_path\": \"/home/user/Blindbot/hf_space/app.py\"}\nResult: 1\timport os\n2\timport pandas as pd\n3\tfrom fastapi import FastAPI, Query, HTTPException\n4\tfrom fastapi.staticfiles import StaticFiles\n5\tfrom fastapi.respon... | 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": "…[earlier truncated]…\ntle>Drop Anywhere SVG Stroke Logo Intro</title>\n7\t<style>\n8\t html,body{margin:0;min-height:100%;background:#18181b;display:grid;place-items:center;font-family:system-ui,sans-serif;}\n9\t</style>\n10\t</head>\n11\t<body>\n12\t\n13\t<!-- COPY FROM HERE... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "[Request interrupted by user]\nUSE DIFFUSION GEMMA. ON CPU. not ollama\nAssistant action: WebFetch {\"url\": \"https://unsloth.ai/docs/models/diffusiongemma\", \"prompt\": \"How to run DiffusionGemma locally on CPU? Exact llama.cpp build instructions, branch/PR, llama-diffusion... | 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": "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": "<command-name>/login</command-name>\n <command-message>login</command-message>\n <command-args></command-args>\n<local-command-stdout>Login successful</local-command-stdout>\nAdd a clear & cancel all button.\nAssistant action: Bash {\"command\": \"ls /home... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simple data structure using a dictionary. The function should support adding, retrieving, and deleting key-value pairs while preventing the deletion of a special internal attribute. Implement a function `custom_data_o... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simple text comparison tool. The function should take two strings, `original_text` and `other_text`, as input and identify the differences between them. For each line in the `original_text`, if the line is not present... | 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 monitoring system for tracking changes in the number of requests received within a specific time interval. Your implementation should maintain the last observed count of requests and compare it with the current count. If the current count is d... | 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 function that manages settings related to tensor quantization by storing and retrieving parameters. Your function, `manage_tensor_quantization`, should accept a list of operations and return the results of specific queries. The operations can ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nunt\\\"], g[\\\"channel_count\\\"]) for g in app.guilds_index])\\nEOF\", \"description\": \"Check JS and test guild index build\", \"timeout\": 180000}\nResult: Using the latest cached version of the dataset since Glint-Research/GlintResearchDiscordChats ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a home security system state transitions based on a series of commands. The function should take an initial state and a list of commands. The possible states are 'disarmed', 'armed_away', 'armed_home', and 'triggered'. ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "I'm a frontend specialist here. for a code review, I'm analyzing satellite image of a neighborhood you're considering moving to. I'm theoretical and academic about what the land use mix tells you about commute and property trends. How do you form a hypothesis here? what a plann... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "[Request interrupted by user]\nuse Q4KM\nAssistant action: WebFetch {\"url\": \"https://github.com/ggml-org/llama.cpp/pull/24423\", \"prompt\": \"Does this DiffusionGemma PR support image input / mmproj / multimodal in llama-diffusion-cli? Any server support? What works and wha... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Implement a function `circular_queue_operations(operations: List[Tuple[str, int]]) -> List[Union[bool, int]]` that simulates a circular queue based on a list of operations. The operations are provided as a list of tuples where each tuple consists of an operation name (a string)... | 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 given a function that takes in a dictionary `data` and a list `per`. The `data` dictionary contains the following keys: 'x2' (a list of float values), 'flag' (a boolean value), 'idx1' (an integer), 'idx2' (an integer), 'ransacT' (a float value), 'ransacDelta' (a float v... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a 2D grid representing a map of land and water. Each cell in the grid can either be land (denoted by 1) or water (denoted by 0). The grid is surrounded by water on all sides. You need to calculate the perimeter of the land in the grid. The perimeter of the land is... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates a simple database management system. Your function should be able to perform the following operations: create a new database, retrieve the current database instance, and close the database. Implement a function `mana... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "As a curious learner trying to understand, i'm lazy and looking for best practices at work and need to build a C++ project for Linux x64, macOS ARM64, and Windows x64. I'm a frontend specialist using CMake and cross-compilation toolchain. What I can't figure out: how to handle ... | 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": "<task-notification>\n<task-id>bs8abtl0f</task-id>\n<tool-use-id>toolu_019kaqL23MrSDSE1tZzWjNzN</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/a76c4cd9-16d4-41ba-8d59-e4d53be8ddc8/tasks/bs8abtl0f.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsk-id>bkf17jmvr</task-id>\n<summary>Monitor event: \"full pytest suite completion (/tmp/test.log)\"</summary>\n<event>[Monitor timed out — re-arm if needed.]</event>\n</task-notification>\nAssistant action: Bash {\"command\": \"tail -3 /tmp/test.log; grep... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nveForm\": \"Integrating Blender assets\"}\nResult: Task #3 created successfully: Integrate Blender assets into game UI\nAssistant action: TaskCreate {\"subject\": \"Upgrade in-engine visuals: characters, bloom, sparks\", \"description\": \"Renderer: capsu... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Repo: /home/user/MythosMini — a 1,050,241-param byte-level (vocab 257) looped-shared-block transformer trained on fineweb-edu, benchmarked on WikiText-2 byte PPL, BLiMP, ARC-Easy against the Tiny-ML leaderboard (overall = mean of blimp, arc, normalized wiki score; efficiency = ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that validates whether a given string is a valid email address. An email address is considered valid if it follows the standard format of 'local_part@domain' where the local part can include letters, digits, and certain special cha... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n_all\": false, \"file_path\": \"/home/user/MythosMini/src/mythosmini/training/stm.py\", \"old_string\": \"from collections.abc import Callable\\nfrom dataclasses import dataclass, replace\\nfrom pathlib import Path\\n\\nimport numpy as np\\nimport torch\\... | 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 implementing a function that calculates the total number of parameters in a convolutional neural network (CNN) layer. The function should take the input shape of the layer as a tuple in the format (filter_width, filter_height, input_channels, output_channels... | 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": "You are tasked with implementing a custom learning rate scheduler for a deep learning model. The learning rate scheduler will adjust the learning rate during training according to a polynomial decay schedule. The polynomial decay schedule is defined by the following equation: \... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nidth=device-width, initial-scale=1\\\" />\\n <title>Teich Studio</title>\\n <link rel=\\\"stylesheet\\\" href=\\\"/static/vendor/xterm.css\\\" />\\n <link rel=\\\"stylesheet\\\" href=\\\"/static/style.css\\\" />\\n <link rel=\\\"icon\\\" type=\\\"imag... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that summarizes a given text input. The function should accept two parameters: a string `text` representing the content to be summarized, and an integer `length` specifying the desired length of the summary. The function should return a s... | 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": "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]…\ntuple[str, Any]'\n --> ./pyaot.py:129:5\n |\n 129 | param_names: tuple[str, ...] = ()\n | ^\n\npyaot: checked 52 file(s) — 1 error(s) in 1 file(s), 0 warning(s)\nmake: *** [Makefile:27: pyaot] Error 1\nAssistant action: Bash {\"command\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "100** | 96.2 / 97.8 | 99.8 / **100** |\n\n## Findings\n\n1. **Harder task kills the crossover.** At 3 digits the baseline caught up by 600 steps; at 5 digits it never does — double-decoder hits 100% on both seeds at 2400 steps while baseline tops out 99.6/96.6. Your decompositi... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are given a sorted array of integers `numbers` and an integer `target`. Your task is to implement the `twoSum` function to find the indices of two distinct numbers such that they add up to `target`. The function should return the indices of the two numbers as a list. You ma... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\"description\": \"Typecheck and rerun table test\"}\nResult: TSC_CLEAN\nAssistant action: Bash {\"command\": \"sleep 20 && tmux capture-pane -t glinttest3 -p -S -60 | grep -v '^$' | tail -35\", \"description\": \"Capture table render result\"}\nResult: ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nttps://arxiv.org/abs/2306.11644\"},{\"title\":\"Textbooks Are All You Need Suriya Gunasekar Yi Zhang Jyoti Aneja\",\"url\":\"https://arxiv.org/pdf/2306.11644\"},{\"title\":\"Small Language Models (SLMs) Can Still Pack a Punch: A survey\",\"url\":\"https:/... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Please look at how you could improve this python AOT compiler to be ready for real-world use.\nAssistant action: Bash {\"command\": \"git status --short && ls -la\", \"description\": \"Check repo state\"}\nResult: D pyaot/__init__.py\n D pyaot/__main__.py\n D pyaot/__pycache__... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list `x` containing a sequence of elements. Your task is to implement a function `manipulate_list(x)` that simulates a specific manipulation process on the list according to the following rules:\n1. While the length of `x` is greater than 1, perform the followin... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simple GUI application behavior. This function takes a list of boolean values representing the visibility of a status bar, where 'True' means the status bar is visible and 'False' means it is hidden. The function shou... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that determines if a scheduled tour is valid based on the following criteria: The tour should have a date that is not in the past, a start time that is during the day (from 06:00 to 18:00), a number of available slots between 0 and 20 (in... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a secure password verification system. Your goal is to create a function `verify_password` that checks if the given password matches the provided hashed password. The password and hashed password are represented as strings. The hashed password i... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given two sets of eigenvalues for a material's band structure, represented as nested lists within dictionaries. Each eigenvalue is a pair of values, where the first value represents the energy level and the second value represents the momentum. Your task is to compare t... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntchPlan(micro_batch=new_micro, grad_accum=new_accum)\n30\t\n31\t\n32\tdef time_probe_steps(step_fn: Callable[[int], None], batch_si …[truncated]\nAssistant action: Read {\"file_path\": \"/home/user/MythosMini/src/mythosmini/training/fp4.py\"}\nResult: 1\t... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Continue the MythosMini task: check /tmp/salvage.log. If it OOM'd again due to paperclip's src/train.py GPU process, kill that training child process (allowed) and relaunch /tmp/salvage_run.py. When finished: add scores.md rows, journal verbatim (incl. STM round 3 NaN + deleted... | 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 calculating the median of a list of input and output voltages based on an electronic device's specifications. You are given the input voltage, output voltage, and output current of a device. Your task is to implement a function that takes the input voltage, ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that retrieves the version of a library given its module name as a string input. Implement a function called `get_library_version(library_name: str) -> str` that takes the name of a library and returns its version. The version should be r... | 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 given a list of strings representing the encoded contents of files. Each string is encoded using 'utf8' and may contain a variety of characters. Your task is to implement a function `decode_files` that takes a list of these encoded strings as input and returns a list of... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\nAssistant action: Bash {\"command\": \"ls -la /c/Users/user/CascadeProjects/windsurf-project-10/backend/ | grep -iE \\\"env|\\\\.db\\\" ; ls /c/Users/user/CascadeProjects/windsurf-project-10/backend/tests/\", \"description\": \"Check for env files and l... | 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 implementing a function that simulates the retrieval of labels associated with tasks in a project management system. The function takes a unique identifier (uid) for a label and returns the corresponding label if it exists. However, it must also handle vario... | 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>b53txn1o2</task-id>\n<summary>Monitor event: \"efficiency measurement results\"</summary>\n<event>{\"measure\": \"time_to_90\", \"digits\": 5, \"seed\": 20260612, \"double_seconds_to_target\": 23.83, \"baseline_seconds_to_target\": 16.54, \"double_... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "persona stability, system prompts, and j\nAssistant: Test 1 passed: file correct, content correct, no nudges. Now Test 2: multi-step edit (create config.json then change a value). This tests edit_file matching.\nAssistant action: Bash {\"command\": \"mkdir -p /tmp/glint-test-02... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a staff engineer reviewing pull requests. Push back when something is risky. Cite specific line-level concerns and suggest concrete alternatives."
},
{
"role": "user",
"content": "Review this PR. The author says it 'fixes a race condition in our user signu... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n// One ticker drives spinner, elapsed, tps, AND the throttled stream flush —\\n // streaming deltas only repaint ~8x/s instead of per-token, which kills the\\n // layout flicker on fast generations.\\n useEffect(() => {\\n if (!running) return;\\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": "1. Goal was not needed here. 2. SHould have just greeted me. 3. Update the website to be more accurate with recent changes. 4. improve tps counter accuracy. chat log: ✦ glint v1.0.0 · Glint Research · a tiny agent that punches above its weight\n groq/compound · session 1757f24... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "make it more effecent\nAssistant: Two efficiency levers: (1) training — talker converges far faster than thinker (oracle 100% early), so train it on a fraction of the steps; (2) inference — consensus voting that stops sampling candidates once they agree, instead of always payin... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n);\\n line-height: 1.6;\\n min-height: 100vh;\\n}\\n\\n::selection {\\n background: #b14e2826;\\n color: var(--ink);\\n}\\n\\n/* ── Motion ── */\\n@keyframes rise {\\n from { opacity: 0; transform: translateY(18px); }\\n to { opacity: ... | 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": "…[earlier truncated]…\nwards;\\n }\", \"new_string\": \" stroke-dasharray:0 var(--path-length);\\n stroke-dashoffset:var(--dash-offset);\\n opacity:0;\\n animation:\\n aiLogoDrawSegment202606 var(--segment-duration,.12s) cubic-bezier(.32,.02,.11,1)... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "User: Can you build an app that looks at my claue code history, looks at my chats with every model, and provides a count on how many times x model has been used?\nAssistant: Claude Code store chats as JSONL in `~/.claude/projects/`. Each assistant message have `message.model`. ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nde|updated|edited|saved|built)|was (?:created|written|executed|run|made|updated|edited|saved|built)|successfully (?:created|wrote|written|ran|executed|updated|built)|script has|file now contains|the output (?:is|was))/i;\", \"new_string\": \" /\\\\b(?:I ... | 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": "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(body),\n130: streamError: null,\n135: if (!response.ok || !response.body) {\n136: const bodyText = await response.text().catch(() => \"\");\n144: streamError: null,\n146: httpError: { status: response.status, bo... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a simple language translation system. Write a function `translate(lang: str, key: str) -> str` that takes a language code and a string key as input and returns the corresponding translated string from a predefined dictionary of translations. If ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with simulating a simple game character movement system. The game character can move in four cardinal directions (up, down, left, right) based on keyboard inputs. Given the initial position of the character and a list of movements (each movement being one of 'up'... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of edges in a graph, where each edge is represented as a tuple containing two nodes and a weight. Your task is to implement a function that calculates the size of each edge based on its weight according to the formula `round(10 * ((max_weight - weight) / (m... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a string representing a 2D map where each character corresponds to a cell in a grid. The characters represent the following: '.' for an empty cell, 'v' for a cell with a downward arrow, '>' for a cell with a rightward arrow, '^' for a cell with an upward arrow, an... | 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": "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 organizing image data for a machine learning project. Implement a function `process_data` that takes in the following parameters: 1. `data_split` (string): Indicates whether the data is for training or testing. It can take the values 'training' or 'testing'.... | 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": "I'm a tech lead reviewing code and I'm working for a code review. I'm frustrated and stuck about how to implement a circuit breaker pattern across three microservices in a C# Tauri app with Cassandra. I need to understand the approach. What assumptions would you make? Also, How... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are given a string `text` and an integer `n`. Your task is to write a function `top_n_words(text: str, n: int) -> List[str]` that returns the top `n` most frequently occurring words in the text. A word is defined as a sequence of alphanumeric characters, excluding any punct... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Create a functonal clone of the popular site Roblox, you should include all assets required. It must have the following: 1. default pre-made games 2. a game maker\n with full colaberation with other users. 3. multiplayer lobbies with REAL players/connections 4. game configs. 5... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Look for uniqe archetectures now.\nAssistant: Hunt exotic architectures.\nAssistant action: WebSearch {\"query\": \"arxiv 2026 novel language model architecture beyond transformer\"}\nResult: Web search results for query: \"arxiv 2026 novel language model architecture beyond tr... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n57)\n assert torch.isfinite(logits).a …[truncated]\nAssistant: Conventions clear. Writing experiment module sandbox-first in `tests/`.\nAssistant action: Write {\"file_path\": \"/home/user/MythosMini/tests/double_decoder.py\", \"content\": \"from datac... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the sentiment score for a given list of reviews. Each review is represented as a list of integer word indices. The function should take a list of lists, where each inner list represents a review, and return a list of s... | 1 | v3-rft-acecode | true |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.