{
  "path": "/posts/2025/running-a-mile-with-llms/index",
  "site": "at://did:plc:mracrip6qu3vw46nbewg44sm/site.standard.publication/self",
  "tags": [
    "language_models",
    "fitness"
  ],
  "$type": "site.standard.document",
  "title": "Running a Mile with LLMs",
  "updatedAt": "2025-09-12T00:29:06.951Z",
  "publishedAt": "2025-09-10T21:07:06.951Z",
  "textContent": "import ChatContainer from '@components/prose/ChatContainer.astro';\nimport ChatMessage from '@components/prose/ChatMessage.astro';\nimport closed from './images/closed.png';\nimport flood from './images/flood.png';\n\nI was not planning on writing about this but after reading Sascha's post, I decided it could be interesting because his demonstration on what it takes to build knowledge happened to relate to prompting a language model for a fitness routine:\n\n> This drives us to one of the most important conclusions of the entire field of note-taking, knowledge work, critical thinking and alike: You, not AI, not your PKM or whatever need to build the knowledge because only then it is in your brain and you can go the next step.\n>\n> Let me try to give you a demonstration of the issue:\n>\n> I asked ChatGPT to design an optimal weekly training schedule for health span and fitness.\n\nand then he proceeds to point out how unless you know some things, you have no way to evaluate whether the model's plan is any good, which I agree with.\n\nI went into the following experiment knowing there was a decent chance the language model would give me bad advice.\nI was mostly interested to see what would happen.\n\nTraining for a mile\n\nI used a few different language models to design a training schedule to run a single mile, as fast as I could do it.\n\nI'm a relatively seasoned athlete, so this was nothing like a couch to 1 mile training plan.\nHowever, I've never intentionally trained for a short distance running race.\nI've only ever run as cross-training for other sports.\n\nSo I created a Project with Claude Opus and started to see what a training plan might look like.\n\nHere's an example of asking an LLM to design a training schedule for running a mile.\nI've summarized the assistant responses, but ensured the training session suggestions were true to the original recommendations.\nThe actual model responses were even longer as Claude had a lot to say about these plans.\n\n<ChatContainer model=\"claude-opus-4-1-20250805\" user=\"Me\">\n  <ChatMessage role=\"user\" timestamp=\"2025-08-18\">\n    Hey I want to train to run a mile in under 6 minutes. Come up with a training plan for me.\n  </ChatMessage>\n\n  <ChatMessage role=\"assistant\">\n    Phase 1: Base Building (6-8 weeks)\n\n    Build tolerance for short rest intervals safely.\n\n    Main Sessions (2x/week):\n\n    - Start: 4-5 x 400m with 90s rest at sustainable pace\n    - Expect 92-96 seconds initially\n    - Weekly progress: Add 1 rep OR reduce rest by 5s OR improve pace by 2s\n    - Only change ONE variable per week\n\n    Easy Days (2x/week):\n\n    - 20-30 minute conversational-pace jogs\n    - Builds aerobic base and aids recovery\n\n    Phase 2: Speed Development (4 weeks)\n\n    - 6-8 x 400m at 86-90s with 60-75s rest\n    - Begin only when consistently hitting 90s with 90s rest\n\n    Key Guidelines:\n\n    - Maintain current cycling/weights\n    - Take 1-2 complete rest days weekly\n    - Start conservatively and progress slowly\n    - Keep easy days truly easy\n    - Prioritize consistency over intensity\n\n    Success Target: Complete 8 x 400m at 88-90s with 75s rest consistently before attempting mile time trial.\n\n  </ChatMessage>\n</ChatContainer>\n\nSo I gave the main sessions a try and they went ok!\nI actually felt like I was ready for a bit more at my fitness level, so time to do some prompt engineering.\n\nRecalibrating based on my fitness level\n\n<ChatContainer model=\"claude-opus-4-1-20250805\" user=\"Me\">\n  <ChatMessage role=\"user\" timestamp=\"2025-08-18\">\n    ... stuff about me, recent workout performance, cycling wattage, etc. ...\n\n    Help me come up with a training plan over the next 2.5-3 months to run a 6 minute mile.\n\n  </ChatMessage>\n\n  <ChatMessage role=\"assistant\">\n    Your cycling fitness shows you have the cardiovascular base needed. A 6-minute mile requires holding 10 mph for 6 minutes - we need to build running-specific speed and neuromuscular power over 12 weeks.\n\n    Phase 1: Base Building (Weeks 1-4)\n\n    Weekly Structure:\n    - Monday: Easy run (30-40 min)\n    - Tuesday: 6-8 x 400m at 85-90 seconds (90 sec rest)\n    - Wednesday: Cycling/weights\n    - Thursday: 20 min tempo at 7:00-7:30/mile pace\n    - Friday: Rest or easy cycling\n    - Saturday: Long run (45-60 min easy)\n    - Sunday: Weights or rest\n\n    Phase 2: Speed Development (Weeks 5-8)\n\n    Weekly Structure:\n    - Monday: Recovery run (25-30 min)\n    - Tuesday: Progress to 8 x 400m at 80-85 seconds, then 4-5 x 800m at 2:50-3:00\n    - Wednesday: Cycling\n    - Thursday: 3 x 8 min at threshold pace (6:45-7:00/mile)\n    - Friday: Rest\n    - Saturday: Progression run\n    - Sunday: Explosive weight training\n\n    Phase 3: Race Prep (Weeks 9-12)\n\n    Weekly Structure:\n    - Monday: Easy recovery (20-30 min)\n    - Tuesday: Race-pace work - progress to 3 x 1200m at 4:30 (5:00/mile pace), then 2 x 1 mile at 6:15-6:20\n    - Wednesday: Easy cycling/rest\n    - Thursday: Short tempo or easy run\n    - Friday: Rest\n    - Saturday: Time trials (taper in week 12)\n    - Sunday: Easy run or rest\n\n    Key Points\n\n    - Pacing: Target even 90-second splits per 400m lap\n    - Testing: Mile time trial every 3-4 weeks (expect 10-15 second monthly improvements)\n    - Recovery: Maintain cycling, add explosive strength work 1-2x weekly\n    - Taper: Reduce volume 40-50% in final week while maintaining intensity\n\n    With consistent training, your cycling fitness gives you the foundation to achieve a 6-minute mile within 3 months.\n\n  </ChatMessage>\n</ChatContainer>\n\nLooking back at this plan with the benefit of hindsight, I realized I didn't even bother looking at phase three of the plan, which looks _very_ ambitious to me, even in retrospect.\nTo not spoil the journey, I'll get back to this later.\n\nI let the model know about my recent workout performance to see if it had anything to say about it.\n\n<ChatContainer model=\"claude-opus-4-1-20250805\" user=\"Me\">\n  <ChatMessage role=\"user\" timestamp=\"2025-08-18\">\n    Last week:\n    90\n    90r\n    90\n    90r\n    89\n    90r\n    88\n    90r\n    91\n\n    Today:\n    75\n    90r\n    88\n    90r\n    89\n    90r\n    88\n    90r\n    88\n\n  </ChatMessage>\n\n  <ChatMessage role=\"assistant\">\n    You're ahead of schedule! Your consistent 88-89 second 400m reps show excellent improvement, but that 75-second opener was too fast for this training phase. While impressive, going 15 seconds faster than race pace can compromise your workout and doesn't build the specific endurance needed for a 6-minute mile.\n\n    Next Week's Workout:\n\n    - 6 x 400m at 85-87 seconds\n    - Start conservative (87s) for reps 1-2, then drop to 85-86s if feeling good\n    - 90-second rest between reps\n\n    2-3 Week Progression:\n\n    - Week 3-4: 7-8 x 400m at 83-85 seconds, add weekly 800m time trial\n    - Week 5-6: 5 x 800m at 2:50-2:55 (key workout for bridging to 6-minute mile)\n\n    Bottom Line: You likely could run 6:15-6:20 right now with proper pacing. That 75-second speed shows you have the raw ability - focus now is on controlled, sustainable pace. Every rep at 85-90 seconds builds the exact endurance adaptations you need. Save the blazing fast reps for later phases with full recovery.\n\n  </ChatMessage>\n</ChatContainer>\n\nThe model felt pretty good about my performance.\nI was having some pacing problems and it called that out as well.\nIt even threw out a guess on what my mile time would be if I made an attempt at my current level of fitness.\n\nI was seeing improvements and feeling better in the workouts.\nIt felt like I was on some kind of right track, so I kept at it.\n\n<ChatContainer model=\"claude-opus-4-1-20250805\" user=\"Me\">\n  <ChatMessage role=\"user\" timestamp=\"2025-08-26\">\n    Here was week 2 from today:\n\n    82\n    90r\n    90\n    90r\n    85\n    90r\n    88\n    90r\n    84\n    90r\n    86\n\n  </ChatMessage>\n  <ChatMessage role=\"assistant\">\n    Performance Update: Crushed Week 2 with a 3-second improvement! Week 1 averaged ~89 seconds, Week 2 averaged ~86 seconds. You're showing Week 4-5 fitness ahead of schedule thanks to exceptional aerobic adaptation.\n\n    Next Week Training Options:\n\n    Option A (Recommended): 7-8 x 400m @ 83-87 seconds with 75-second rest\n    Option B: 4-5 x 600m @ 2:10-2:15 with 90-second rest\n\n    Accelerated Timeline:\n\n    - Week 4: 8 x 400m @ 82-85s with 60-second rest + 1200m time trial\n    - Week 5-6: 5-6 x 800m @ 2:45-2:50\n    - First Mile Time Trial: Week 4 (predicted 6:15-6:25)\n\n    Current Mile Fitness Estimates:\n\n    - Current: 6:20-6:30\n    - Week 4: 6:10-6:15\n    - Week 8: 6:00-6:05\n    - Week 12: Sub-6:00 achievable\n\n    This Week's Focus:\n\n    - Thursday tempo: 6:45-7:00 pace\n    - Saturday long run: 7:30-8:00 pace (easy)\n    - Add 4 x 100m strides after Monday's easy run\n\n    Watch for: Achilles/calf tightness and shin splints as speed increases.\n\n    The 6-minute mile goal is looking very achievable—possibly by Week 8-9 rather than Week 12!\n\n  </ChatMessage>\n</ChatContainer>\n\nThis threw me off.\nBased on where I was at, these goals felt very ambitious and I wasn't feeling good about it.\nI assumed the model was painting a rosier picture than reality based on past experience of models making things up and generally being wrong and unreliable about all sorts of things.\n\nI had doubts\n\n<ChatContainer model=\"claude-opus-4-1-20250805\" user=\"Me\">\n  <ChatMessage role=\"user\" timestamp=\"2025-08-26\">\n    I need you to be realistic\n  </ChatMessage>\n  <ChatMessage role=\"assistant\">\n    Reality Check\n\n    The Gap: While your 82-86 second 400m repeats with 90 seconds rest are solid, there's a significant difference between interval work with recovery and holding 90-second laps for 4 consecutive laps without rest.\n\n    Current Fitness Assessment:\n\n    - You can hit 82-86 seconds WITH full recovery\n    - 6-minute mile requires 90-second laps WITH NO recovery\n    - Realistic current mile time: 6:45-7:00\n\n    Realistic 12-Week Timeline:\n\n    - Week 4: 6:35-6:45\n    - Week 8: Breaking 6:30 would be good progress\n    - Week 12: 6:10-6:20 is a realistic target\n\n  ",
  "canonicalUrl": "https://www.danielcorin.com/posts/2025/running-a-mile-with-llms/index"
}