I 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:
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.
Let me try to give you a demonstration of the issue:
I asked ChatGPT to design an optimal weekly training schedule for health span and fitness.
and 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.
I went into the following experiment knowing there was a decent chance the language model would give me bad advice.
I was mostly interested to see what would happen.
I used a few different language models to design a training schedule to run a single mile, as fast as I could do it.
I’m a relatively seasoned athlete, so this was nothing like a couch to 1 mile training plan.
However, I’ve never intentionally trained for a short distance running race.
I’ve only ever run as cross-training for other sports.
So I created a Project with Claude Opus and started to see what a training plan might look like.
Here’s an example of asking an LLM to design a training schedule for running a mile.
I’ve summarized the assistant responses, but ensured the training session suggestions were true to the original recommendations.
The actual model responses were even longer as Claude had a lot to say about these plans.
2025-08-18
User
Hey I want to train to run a mile in under 6 minutes. Come up with a training plan for me.
Assistant
Phase 1: Base Building (6-8 weeks)
Build tolerance for short rest intervals safely.
Main Sessions (2x/week):
Start: 4-5 x 400m with 90s rest at sustainable pace
Expect 92-96 seconds initially
Weekly progress: Add 1 rep OR reduce rest by 5s OR improve pace by 2s
Only change ONE variable per week
Easy Days (2x/week):
20-30 minute conversational-pace jogs
Builds aerobic base and aids recovery
Phase 2: Speed Development (4 weeks)
6-8 x 400m at 86-90s with 60-75s rest
Begin only when consistently hitting 90s with 90s rest
Key Guidelines:
Maintain current cycling/weights
Take 1-2 complete rest days weekly
Start conservatively and progress slowly
Keep easy days truly easy
Prioritize consistency over intensity
Success Target: Complete 8 x 400m at 88-90s with 75s rest consistently before attempting mile time trial.
So I gave the main sessions a try and they went ok!
I actually felt like I was ready for a bit more at my fitness level, so time to do some prompt engineering.
… stuff about me, recent workout performance, cycling wattage, etc. …
Help me come up with a training plan over the next 2.5-3 months to run a 6 minute mile.
Assistant
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.
Phase 1: Base Building (Weeks 1-4)
Weekly Structure:
Monday: Easy run (30-40 min)
Tuesday: 6-8 x 400m at 85-90 seconds (90 sec rest)
Wednesday: Cycling/weights
Thursday: 20 min tempo at 7:00-7:30/mile pace
Friday: Rest or easy cycling
Saturday: Long run (45-60 min easy)
Sunday: Weights or rest
Phase 2: Speed Development (Weeks 5-8)
Weekly Structure:
Monday: Recovery run (25-30 min)
Tuesday: Progress to 8 x 400m at 80-85 seconds, then 4-5 x 800m at 2:50-3:00
Wednesday: Cycling
Thursday: 3 x 8 min at threshold pace (6:45-7:00/mile)
Friday: Rest
Saturday: Progression run
Sunday: Explosive weight training
Phase 3: Race Prep (Weeks 9-12)
Weekly Structure:
Monday: Easy recovery (20-30 min)
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
Wednesday: Easy cycling/rest
Thursday: Short tempo or easy run
Friday: Rest
Saturday: Time trials (taper in week 12)
Sunday: Easy run or rest
Key Points
Pacing: Target even 90-second splits per 400m lap
Testing: Mile time trial every 3-4 weeks (expect 10-15 second monthly improvements)
Recovery: Maintain cycling, add explosive strength work 1-2x weekly
Taper: Reduce volume 40-50% in final week while maintaining intensity
With consistent training, your cycling fitness gives you the foundation to achieve a 6-minute mile within 3 months.
Looking 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.
To not spoil the journey, I’ll get back to this later.
I let the model know about my recent workout performance to see if it had anything to say about it.
2025-08-18
User
Last week:
90
90r
90
90r
89
90r
88
90r
91
Today:
75
90r
88
90r
89
90r
88
90r
88
Assistant
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.
Next Week’s Workout:
6 x 400m at 85-87 seconds
Start conservative (87s) for reps 1-2, then drop to 85-86s if feeling good
90-second rest between reps
2-3 Week Progression:
Week 3-4: 7-8 x 400m at 83-85 seconds, add weekly 800m time trial
Week 5-6: 5 x 800m at 2:50-2:55 (key workout for bridging to 6-minute mile)
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.
The model felt pretty good about my performance.
I was having some pacing problems and it called that out as well.
It even threw out a guess on what my mile time would be if I made an attempt at my current level of fitness.
I was seeing improvements and feeling better in the workouts.
It felt like I was on some kind of right track, so I kept at it.
2025-08-26
User
Here was week 2 from today:
82
90r
90
90r
85
90r
88
90r
84
90r
86
Assistant
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.
Next Week Training Options:
Option A (Recommended): 7-8 x 400m @ 83-87 seconds with 75-second rest
Option B: 4-5 x 600m @ 2:10-2:15 with 90-second rest
Accelerated Timeline:
Week 4: 8 x 400m @ 82-85s with 60-second rest + 1200m time trial
Week 5-6: 5-6 x 800m @ 2:45-2:50
First Mile Time Trial: Week 4 (predicted 6:15-6:25)
Current Mile Fitness Estimates:
Current: 6:20-6:30
Week 4: 6:10-6:15
Week 8: 6:00-6:05
Week 12: Sub-6:00 achievable
This Week’s Focus:
Thursday tempo: 6:45-7:00 pace
Saturday long run: 7:30-8:00 pace (easy)
Add 4 x 100m strides after Monday’s easy run
Watch for: Achilles/calf tightness and shin splints as speed increases.
The 6-minute mile goal is looking very achievable—possibly by Week 8-9 rather than Week 12!
This threw me off.
Based on where I was at, these goals felt very ambitious and I wasn’t feeling good about it.
I 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.
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.
Current Fitness Assessment:
You can hit 82-86 seconds WITH full recovery
6-minute mile requires 90-second laps WITH NO recovery
Realistic current mile time: 6:45-7:00
Realistic 12-Week Timeline:
Week 4: 6:35-6:45
Week 8: Breaking 6:30 would be good progress
Week 12: 6:10-6:20 is a realistic target
Sub-6:00 Reality Check: This is a stretch goal requiring exceptional lactate buffering. Most runners need to comfortably run 75-80 second 400s to break 6:00.
Today’s Session Assessment:
Your 86-second average with 90 seconds rest shows you’re exactly where you should be for Week 2, but the brutal math reveals the challenge: you’re running faster than goal pace WITH recovery, while the goal requires slightly slower pace WITH zero recovery.
Honest Prediction: Based on current performance, you’re tracking toward 6:25-6:35 by Week 12.
Hmm ok.
So I showed some doubt and the model followed my lead and pulled back where it estimated I would be.
By design, I basically had no idea about where I should be, the type of progress I could expect, or whether the initial or secondary predictions were reasonable.
The points about rest between intervals made sense considering I didn’t have enough experience or knowledge to push back against them.
It was true that I would need to run 4 laps with no rest.
And that sounded harder than most of the things I had been doing.
So I continued the plan with more conservative expectations about how performance might improve, still following the second plan the model gave me after I told it my fitness level.
Recent tempo run: 1:47 per 400m (7:09/mile pace) with excellent consistency
Goal mile pace needed: 1:30 per 400m (6:00/mile)
Gap to bridge: 17 seconds per lap
The Reality:
Your threshold pace is currently 7:00-7:10/mile. To run a 6:00 mile, you need to run significantly faster than this threshold pace, but only sustain it for 6 minutes instead of 21+ minutes. This 70-second per mile gap is substantial but achievable with 9 weeks of focused training.
Recommended Weekly Structure:
Friday: Easy 25-minute run + 8 x 30 seconds at 6:00 pace (90 sec easy jog recovery)
Saturday: 50 minutes truly easy (7:45-8:15 pace) for aerobic base
Tuesday: 8 x 400m with 75 seconds rest, targeting 87-90 seconds per 400m
Key Focus: The 400m/800m interval work is critical - it trains the faster energy systems above threshold that you’ll need for the mile. Your finishing kick shows you have speed reserve; now we need to bring your threshold closer to race pace through consistent tempo work.
Claude wasn’t so enthusiastic about the tempo performance with regard to my chances for a 6-minute mile.
The mile time projections at the different week marks were varying all over the place.
Because the original training plan was further up in the chat (I had this conversation in one long chat), it was a pain to scroll back to the original plan and the model kept suggesting new plans anyway, with different rest durations that were kind of close to the original plan.
I decided to just ask the model to tell me what the workout was for today and go with that.
2025-09-03
User
What is today’s workout?
Assistant
Today’s Workout Summary
Main Set: 8 x 400m with 60-second rest
Pacing Strategy:
Reps 1-2: 87-88 seconds (conservative start)
Reps 3-6: 85-88 seconds (find rhythm)
Reps 7-8: Hold on, accept what comes
Expect:
Slower than last week (88-92 is fine)
Incomplete recovery between reps
Heavy breathing throughout
Warmup: 10-15 min easy + 4 x 100m strides
Cooldown: 10 min easy jog
You crushed this week’s workout, running 400m repeats at an 88.6-second average with only 60-second rest - just 2.5 seconds slower than last week despite 33% less recovery time. Most athletes lose 5-7 seconds with reduced rest, so this shows exceptional cardio adaptation.
Current Mile Projection
Current fitness level: 6:25-6:30 mile (ahead of schedule)
Week 8 projection: Sub-6:20 very likely
Week 12 goal: Sub-6:00 increasingly realistic
Key Insights
Your ability to hold 88-91 seconds with incomplete recovery proves you can sustain goal pace (90 seconds) when pre-fatigued - exactly what mile racing demands. The minimal fade between first and last rep shows strong lactate tolerance.
Next Week’s Workout (Week 4)
Distance: 8 x 400m
Rest: Reduce to 45-50 seconds
Target pace: 90-93 seconds
Purpose: Complete cardio adaptation phase
You’re ahead of schedule and starting to look like the athlete you remember being. This workout was a statement of your progress toward that sub-6:00 mile goal.
This was a confidence building session for me.
I had expected the reduction of rest from 90 to 60 seconds to hit hard and negatively affect my performance.
The fact that I was able to continue executing the “plan” despite fatigue felt like a big win.
It seemed like I had exceeded Claude’s expectations for me, at least, after I had given it a reason to doubt its initial predictions.
Either way, it was excited.
Again, I didn’t really consider the implications of the feedback I was giving the model and I was somewhat wary of whether its plans were actually reasonable.
I definitely wasn’t putting blind trust in the plan and was pushing back, but I was also not very informed, so it’s not as though I was coming from a position of expertise.
Warm-up: 10-15 min easy, drills, 4-6 strides; optional 1 x 200 at ~45 three minutes before
Target even splits: 200 in 45, 400 in 90, 600 in 2:15, finish 2:58-3:00
Cool-down: 10 min easy
Results guide:
Green (≤3:00 both): proceed as planned
Yellow (3:01-3:03): open slightly conservative
Red (≥3:04 or fade): consider delaying race or adjusting to 6:05-6:10 goal
Sat 9/6
15-20 min very easy + 4 strides
Light mobility, stay off feet otherwise
Sun 9/7 — Race Day
Warm-up (40-50 min pre-race):
10-15 min easy jog, drills, 4-6 strides
Optional: 1 x 200 at ~45 three minutes before start
Pacing Strategy:
Mile: 45/90/3:00/4:30/finish hard
1600m: 90-89-89-88 (sub-5:58)
Key Rules:
Don’t go faster than 45 for first 200
If lap 1 = 92: go 89-89-87
If lap 1 = 88: settle to 90-90, kick last 200
Race Logistics:
Wear your usual fast shoes
Eat carb-focused meal 2-3h before
Hydrate with 300-500ml water + pinch of salt in final 2-3h
Send me your Friday 2 x 800 times and I’ll confirm your exact pacing strategy. You’re ready—nail the first lap and everything else follows.
User
2x800m 120r
3:04
120r
3:02
Assistant
Quick mile plan (yellow readiness): open a touch conservative, then squeeze late.
Race pacing
Default (1600 m): 91 - 90 - 90 - 88 = 5:59
If you open slow (92): 92 - 90 - 89 - 88
If you open fast (≤89): settle to 90-91 on lap 2, 90 on lap 3, kick last 300-200
Full mile (1609 m): hit 1600 in 5:57-5:58; the extra 9 m is your kick
Checkpoints and in-race adjustments
First 200 ≥46; relax, tall posture, light quick cadence
400 ~91 feeling controlled
800 in 3:01-3:03; commit to 89-88 over last two laps
Lap 3 cue: hold cadence, “hips tall, push the ground”
Last 500-300: start squeezing; last 200 go arms-first and commit
Warm-up (start 40-50 min before)
10-15 min easy jog
Drills: leg swings, skips, high knees, butt kicks
4-6 strides building to mile effort
Optional: 1 x 200 at ~45-46 about 3 min before start
Day-before (easy)
15-20 min very easy + 4 relaxed strides; light mobility; otherwise off your feet
Logistics
Wear the shoes you’ve been doing fast work in; lace securely
Carb-centric meal 2-3 h pre-race; optional 15-30 g carb 15-30 min before
Caffeine only if you’re used to it
If windy, tuck on straights, push tailwind sections
Bottom line: Open under control (91), settle, then squeeze. If you’re ~3:02 at 800 feeling smooth, 5:59-6:01 is there with a committed last 600-400.
I popped my new plans and tune up 2x800m results over to Claude and its response left me confused.
2025-09-05
User
2x800m 120r
3:04
120r
3:02
Assistant
Your Recent 800m Performance: 3:04, 3:02 (91.5 seconds per 400m) - excellent pacing with a negative split and strong consistency.
Key Insight: You held near-goal pace for 800m, which shows you can maintain the right speed for half your target distance. Your 800m pace (3:00-3:03) is right on target for a 6:00 mile.
Current Mile Fitness Estimate: 6:20-6:25
Next Steps for 800m Training:
Next time: 3 x 800m at 3:00-3:05 (2 min rest)
Week after: 4 x 800m at 3:00-3:05 (90s rest)
The Challenge: To run a 6:00 mile, you need to hold these 800s back-to-back without rest. Currently you’re completing 800s with 2:00 rest - the goal is eliminating that recovery time while maintaining pace.
These 800m workouts are arguably more important than 400m repeats for your mile goal, as they build the speed endurance needed for your target time.
Since I had had the conversation about the shortened timeline outside this thread, Claude didn’t know what I was talking about.
I had two days left and I was going to race on 2025-09-07.
Claude seemed to think I had 6:20-6:25 pace potential given the 2x800m workout.
GPT-5 thought I could be within a few seconds of 6:00.
I wasn’t sure what to think.
I definitely wished I had more time and had run more 600m and 800m workouts.
800m felt very different from 400m the way I was trying to run them.
I had gone from 90s rest between 400s to 60s to 0s for the 2x800m.
That workout was tough, though I think my pacing could have been better.
I woke up Sunday morning on 2025-09-07 and it was raining.
I went through a pretty standard race prep routine I have.
I eat a banana and make sure I am awake several hours before the race.
After sitting around for about two hours, the rain actually let up, so I went down to the track to do my warmup, planning to just race in the rain if I had to.
I had finished my dynamic warmup and was starting to do strides when I saw this.
Well not actually this.
What I saw was water midway through the fifth lane of the track.
I took this picture after everything was done and 20-30 minutes more draining.
If it had only been this bad, I probably wouldn’t have changed much, but at the time, it was so flooded I had to adjust.
I decided to run the race in lane 6.
I did some quick research on my phone, and found I needed to do (1600 / 438.33) 3.65 laps.
I sized up the final corner before the last 100m, took the midpoint of the turn (0.125+ 0.50 = 0.625) and added a little bit to that.
That would be my finish point on the fourth lap.
It was hacky but I was going to try and make it work.
I went over to my normal starting spot, went out to lane 6, and off I went.
Running in lane 6 was weird.
The turns are longer and I couldn’t pace myself at all since I didn’t know the target 200m or 400m times with the adjusted number of laps.
It was not an optimal setup.
Perfect weather though, minus the wet.
I ran the race a bit conservatively through the first half and had a decent amount left in the tank to push the last 1.65 laps.
I clocked the finish at 6:11.
I was a bit surprised when I saw it.
I was sure I’d started too conservatively to put up 6:00, but 6:11 felt like a pretty good result.
I did take a look at the stopping point and decided it was probably a touch short of 1600m.
So I’m going to call it a 6:15.
Looking back on this process, one thing that surprised me was something Claude said on 2025-08-26
2025-08-26
Assistant
Current Mile Fitness Estimates:
Current: 6:20-6:30
Week 4: 6:10-6:15
Week 8: 6:00-6:05
Week 12: Sub-6:00 achievable
I didn’t know it at the time, but roughly two weeks later I would attempt the mile and finish with a time right in the range Claude predicted.
This was before Claude recalibrated its prediction based on my prompt to “be realistic” that same day.
That said, Claude made plenty of other predictions in the neighborhood of my goal, so it isn’t so surprising it got one of them right.
It seemed like Claude might have had a better sense of my capabilities than I did.
However, when I showed uncertainty, it went with me.
Maybe it should have pushed back.
I’m not sure how I would prompt for that, avoiding leading it to adjust its predictions to be less ambitious, if its pattern matching suggested its plan could actually be possible for me to execute.
Maybe it was all a coincidence.
I think there’s a chance I might have performed better on a nicer day.
But it’s equally possible I might have started too aggressively and then faded too much.
Unfortunately, I won’t have the chance to find out but I’m glad I got to give this a shot before the track closed.
Maybe it’s for the best.
I’ll need to do some proper research to learn if Claude was proposing reasonable plans for me.
