June 23rd - Field Irrigation and Pig Fencing

Ā 

TL;DR

Today was the first work day of a record-breaking heat wave in New England. We harvested in short spikes with breaks in between then set up some irrigation lines.

Farming in Extreme Heat

Even when there’s a heat advisory, there’s still work to be done. Priorities shift to ā€˜minimum viable’ outside work, such as harvesting in the early morning and especially things that may bolt (like lettuces). Soil that has dried out needs to be watered, so irrigation is a priority. Watering the greenhouse multiple times a day is a must.

At this farm, even though we still work, we are provided ample opportunities to hydrate, take breaks, and cool off when the heat is at its peak like this. We also rotate duties between field and barn work (such as washing, bunching, and packing) to avoid overheating.

Before and After Lunch Harvesting

In the morning, we harvested chard, fennel, and lettuce. After lunch, we harvested garlic scapes (the flowering curly shoots of the garlic stalk) and scallions. Jamie checked the potatoes by pulling some up, which ended up in my take-home produce later. Despite some potato beetle damage, he thinks most of the crop will pull through.

Then I helped Jamie continue setting up irrigation lines to the main field. This involved super-manning a huge wooden spool with some 2-inch tubing onto the back of the truck.

After we were done with that, we went back up to the barn where I stayed to bunch and wash scallions with another person. Meanwhile Jamie and the other person went up to start extending the pig pen with fencing into the forest. Though shady up there, it was 2pm and 90 degrees fahrenheit and humid, so I can only imagine it was a haul to continue the day on that task. The pigs are outgrowing the wooden shade structures at this point, so it was necessary.

Not all AI Crop is ā€˜AI Slop’

The populist outsider’s view and understanding of things termed ā€˜AI’ is often a caricature of the reality. ā€˜AI slop’ a the most recent example of this…content ā€˜creators’ who are not experts but rather rely on AI tools to generate content that is not only low quality but also often offensive or harmful.

I’ve been working hard to make sure that nothing on this blog is ā€˜slop’ (except for the occasional image and mention of pigs, lolz!). My use of LLMs is limited to very specific use cases that I have hand-crafted the infrastructure, the code, the prompts and the process to produce basic structural elements of the blog posts for.

Unless You Do Quality Control, It’s Likely Slop

Quality control (QC), quality assurance, quality management, testing, verification, and validation were all sections I had a heavy hand in pushing to completion in my prior work with IEEE 2675-2021, despite last-minute adjustments out of my hands. This took years of writing, reviewing with the team, revising, re-reviewing and balloting, then finalizing.

My homelab work goes much faster, but still has a lot of QC in its process. I listen back to summaries before using them, making mental note of what might be going wrong in prompts and process if I hear strange things. I do not always have the time to correct issues, and besides, I want to keep the record of my work and the process I went through to get to the final product.

In the past two weeks, I built a separate ā€˜meeting minutes compiler’ which, in short, taught me that one specific LLM is not always best when different parts of your process require specific outputs and speeds. Specifically, handing a whole transcript to Deepseek often produces higher number of hallucinations than handing specific chunks (and their prior section) in for summarization.

As it turns out, too much context is sometimes a bad thing, just like not enough. How to balance what is ā€˜enough’ is a job of the system design and operations. And just like there is usually no good outcome from a ā€˜one-shot’ prompt, a one-iteration approach to features and software usually leaves a lot of learning and right-fitting on the table. Incremental and intentional iteration is what I’m doing with my homelab work.

Pop-up Blockers to Progress

Every so often, something in my homelab infrastructure will go ā€˜bump in the night’ and stop working. I’ve learned to expect this, and to be ready to troubleshoot and fix it.

This morning, a problem with my homelab Ollama kubernetes deployment took about 20 minutes away from this writing. In essence a start hook to download three commonly used models was failing because compatibility between it and the ollama host container had shifted. I’m pretty sure I need to implement better log shipping and investigate persistence of the model binaries between container restarts, but that’s for later. This morning I just had to get it working again and get on with my blog before I’m late to the farm.

I need a more proactive approach to these ā€˜pop-up’ progress blockers. I don’t have time for running disaster recovery every single time I change some small part of my infrastructure. I also don’t think any of that would have helped in this case, since the problem wasn’t with anything I changed but something in the intra-dependency after a restart that was changed outside my control (the model from online download itself).

Anyway, while I was troubleshooting the ollama deployment, I realized that I had switched autoscribe (the component that produces the following notes summaries for this blog) to use Deepseek-R1:1bn (only one billion parameters) instead of the default :8B. When I get home later today, I’ll re-run it with 8B and compare the results.

I noticed that it gets side-tracked because of the tracking code at the top of the notes again, and that all of Part 1 is a hallucination. Particularly egregious is the line about Roundup PowerMax, which is not at all what we would ever use on this farm.

This is why unchecked and un-validated AI output is dangerous, not only informational but operationally. Imagine if I had used this output to make decisions about what chemicals to use on the farm!

Here’s what the AI generated for me with the 1B (small) model:

Summary

Okay, let me break this down. The user has given two sets of field notes summaries from a farm intern in June. They want to know what was done during their workday—so I need to extract all relevant info like main tasks, any novel elements, potential follow-ups, and recommended next steps. First part covers checking into the office, meeting with the supervisor, talking about planting timelines, reviewing pest control strategies ~~AI-MISTAKE: including herbicide application (Roundup PowerMax at 1 gallon per acre), mixing herbicides via sprayer. The new thing here is probably Roundup PowerMax since it's a specific type they might not have used before, and maybe using a larger sprayer instead of backpack ones. Questions include checking label compatibility with other chemicals and timing for application without harming crops or insects. Actions could involve ensuring proper PPE usage.~~ Second part mentions harvesting Swiss chard and lettuce, setting up irrigation (large sprinklers on tripods), moving them around, fixing pig pens' electric fences—so new elements might be the specific setup of these sprinklers depending on farm context. Activities include crop harvesting, irrigation prep, processing produce, animal enclosures maintenance. Questions about garlic scapes: how long can they stay in the field? Efficiency of large sprinklers vs others? Maybe timing for irrigation affecting crops. Suggested actions are optimizing harvest times for scapes and maybe alternative cooling methods like shade structures or portable fans. Wait, need to check if there's any deeper needs here. The user might be looking for a comprehensive overview that combines both days without overlap. They probably want to understand the consolidated workflow across both days—so combining crop management tasks with irrigation setup and animal care. Also, they might need actionable insights rather than just listing info. For example, in the first summary, the focus is more on planning (planting) and pest control prep before harvest season starts. Second part is during harvest time. So maybe the user wants to see how these two phases connect—planning vs execution. New things like specific irrigation systems or scapes handling could be farm-specific but might not be universally known, so that's worth noting. Questions should address both parts: compatibility of herbicides with other chemicals and efficiency of sprinklers. Suggested actions include proper PPE for workers during heat, maybe suggesting shade structures or cooling breaks. Wait—maybe I need to ensure all activities are clearly separated under crop management (harvesting, irrigation) vs animal handling (fences). Also check if any tasks from the first part might still be relevant in June context even after harvest starts? Or are they pre-harvest versus post-harvest. The user wants a consolidated summary that ties both days together. Need to make sure not to mix the two parts, but combine their themes and activities without duplication. Main themes: crop management (both harvesting and planning), heat management strategies because of June's weather, sustainable practices like irrigation setups and animal welfare measures. Activities should list all tasks mentioned across both days—harvesting, irrigation setup/maintenance, pest control prep, produce processing, fixing fences. ~~AI-MISTAKE: New things are the specific herbicide type and sprinkler setup. Questions cover compatibility issues with Roundup PowerMax and scapes handling efficiency.~~ Actions include using PPE properly for workers during heat, maybe suggesting shade solutions or tools to help with cooling breaks.

Okay, here’s a consolidated summary combining all elements from both analyses:

Consolidated Summary:

Based on the provided field notes summaries, here is a consolidated overview of the farm intern’s activities and observations over two days in June:

  1. Main Themes: The workday focused on transitioning into active harvest season while also addressing operational tasks like irrigation setup and animal management.
  2. Activities:
    • Checking into office/operations.
    • Meeting with supervisor (likely to discuss planning).
    • Discussing crop planting timelines post-harvest.
    • Setting up irrigation systems (moving large sprinklers on tripods, fixing electric fences for pigs).
    • Harvesting crops (Swiss chard, lettuce, scallions, garlic scapes) and preparing produce (ā€œhottentotsā€ - likely a typo or specific term for large sprinklers).
    • Picking scallions and garlic scapes from dry fields.
    • Farm maintenance tasks like fixing pig pens’ electric fences.
  3. New Things Not Encountered Before:
    • Using ā€œlargeā€ sprinklers on tripods (specific size/size depends on context, but likely a new setup for the intern).
    • AI-MISTAKE: The specific herbicide mentioned (Roundup PowerMax) and its application rate/dose (1 gallon per acre), though this might be less novel depending on prior experience.
  4. Questions for Future Research:
    • AI-MISTAKE: Compatibility of Roundup PowerMax with other chemicals (from first summary).
    • How long can garlic scapes stay in the field before harvest?
    • Efficiency and effectiveness of large sprinklers (ā€œhottentotsā€) vs smaller methods.
    • Impact of irrigation timing/schedule on various crops.
    • Best practices for cooling during extreme heat, especially with portable solutions (from second summary).
  5. Suggested Actions:
    • AI-MISTAKE: Ensure proper Personal Protective Equipment (PPE) is used when applying herbicides like Roundup PowerMax to prevent exposure and contamination.
    • Harvest garlic scapes at optimal times for best flavor or yield according to farm standards/guidelines.
    • Consider the use of portable fans or shade structures in addition to shaded breaks during peak heat hours.

Part 1

Okay, so I have these field notes from a farm intern, and I need to figure out what they did during their workday. The user wants me to identify main themes, list the activities, note new things not encountered before, ask questions or plan future research, and suggest any actions if there are any. First, I should read through the transcript carefully. It starts with some code: "origin: 1LIhlgB4CDyy3f2_1rdUB982Nremqp2Y8". Maybe that's just a unique identifier for the data source. Then it mentions things like checking in at the farm office, meeting with the supervisor, discussing planting timelines, reviewing pest control strategies, and applying herbicides. So, activities include tasks like checking in, meeting with the supervisor, talking about planting schedules, reviewing pest control, mixing herbicides, applying them, and moving supplies. That seems straightforward. I should list each of these as separate activities. ~~AI-MISTAKE: Now, for new things not encountered: The intern mentions that it's their first day using this specific herbicide called "Roundup PowerMax". They also note the application rate is 1 gallon per acre. If I haven't heard about Roundup PowerMax before, that could be a new thing. Also, applying it via a sprayer instead of backpack sprayers might be something new, though backpack sprayers are common.~~ ~~AI-MISTAKE: Questions and future research: The intern is unsure if Roundup PowerMax is compatible with other chemicals, so they need to check the label. They also ask about the best time to apply it for maximum effectiveness without harming beneficial insects or crops. So two questions there.~~ Suggestion actions: The user didn't mention any specific actions in this conversation, but maybe the intern could suggest waiting longer before applying if the timing is uncertain or ensuring proper PPE. Wait, did I miss anything? Let me go through again. The transcript mentions checking in, meeting with supervisor, planting timelines, pest control review, mixing herbicides, application, and moving supplies. So activities are covered. Main themes: Agricultural tasks, pest management, herbicide use, safety protocols, plant health, timing of operations. I think that's all. I should structure the answer clearly, making sure each section is addressed without missing anything.

Field Notes Analysis

Activities:

  1. Checked in at the farm office.
  2. Met with the supervisor to discuss the day’s tasks.
  3. Discussed planting timelines and upcoming activities.
  4. Reviewed pest control strategies and methods.
  5. AI-MISTAKE: Mixed herbicides according to specified ratios.
  6. AI-MISTAKE: Applied the mixed herbicide using a sprayer.
  7. Moved supplies as needed.

New Things Not Encountered:

  • AI-MISTAKE: Use of Roundup PowerMax herbicide, which may be new for the intern.
  • AI-MISTAKE: Application rate of 1 gallon per acre, possibly new information.
  • AI-MISTAKE: Usage of a sprayer instead of backpack sprayers (though this might not necessarily be new).

Questions and Future Research:

  1. AI-MISTAKE: Compatibility of Roundup PowerMax with other chemicals.
  2. AI-MISTAKE: Optimal timing for herbicide application to avoid harming beneficial insects or crops.

Suggestion Actions:

  • Consider waiting longer before applying if timing is uncertain.
  • AI-MISTAKE: Ensure proper Personal Protective Equipment (PPE) is used during application.

Main Themes:

  1. Agricultural tasks and daily operations.
  2. Pest management and control strategies.
  3. AI-MISTAKE: Herbicide use, mixing, and application techniques.
  4. Safety protocols and equipment usage.
  5. Plant health monitoring and maintenance.
  6. Timing of agricultural operations for effectiveness and impact.

Part 2

Okay, so I'm trying to understand what the user is asking for here. They provided a transcript from a farm intern's field notes and they want me to identify main themes, list activities, note new things not encountered before, pose questions for future research, and suggest actions. First, I need to parse through the transcript carefully. The intern talks about working on a farm in June, dealing with extreme heat, harvesting various crops like Swiss chard and lettuce, setting up irrigation, moving sprinklers, and processing garlic scapes and scallions. They also mention the importance of taking breaks and managing tasks to cope with the heat. So, for the main themes, I should focus on what's central to their workday. It seems like crop management is a big one because they're harvesting and setting up irrigation. Heat management is another theme since they frequently mention the high temperatures and how to deal with them. There's also a focus on sustainable practices, maybe with references to mulching, using sprinklers, and handling garlic scapes. Next, listing out activities: they harvested crops, set up irrigation, moved sprinklers, processed produce, picked scallions and garlic scapes, and helped with farm maintenance like fixing pig pens. They also mention the need for cooling breaks, so that's another activity in terms of self-care. New things not encountered before—since I'm new to this context, I need to figure out what someone familiar would already know. Garlic scapes seem specific; perhaps they're less common outside certain regions or not commonly known as a harvestable item. Using large sprinklers on tripods might be a unique setup depending on the farm's size and layout. Questions for future research: Maybe how long can garlic scapes be left in the field before they start to degrade? How efficient are those large sprinklers compared to other methods? How does the irrigation schedule affect different crops? Also, what are the best practices for cooling down in extreme heat without access to shade? Suggestion actions: Perhaps suggesting when to harvest garlic scapes for optimal flavor or considering alternative methods if the main crops are struggling. Also, recommending the use of portable fans or shade structures for workers during peak heat. Wait, did I miss anything? They also mention fixing electric fences for pigs, which is a specific task that ties into farm animal management. So, maybe that's another theme under crop and animal management. Also, processing scallions and garlic scapes adds value to the farm produce. I should structure this clearly in points without making it too lengthy. Make sure each section is concise but covers all aspects mentioned.

Main Themes:

  1. Crop Management: Focus on harvesting crops like Swiss chard, lettuce, scallions, and garlic scapes, and setting up irrigation systems.
  2. Heat Management: Addressing the challenges of extreme heat and strategies to manage it, such as taking breaks in shaded areas.
  3. Sustainable Practices: Utilizing large sprinklers on tripods, mulching, and maintaining electric fences for pigs.

Activities:

  1. Harvesting crops (Swiss chard, lettuce, scallions, garlic scapes).
  2. Setting up irrigation systems and moving sprinklers.
  3. Processing produce in the barn with industrial fans.
  4. Picking scallions and garlic scapes from dry fields.
  5. Fixing pig pens and extending electric fences.

New Things Not Encountered Before:

  1. Garlic scapes as a harvestable item, which might be less common or region-specific.
  2. Large sprinklers on tripods for effective irrigation coverage.

Questions for Future Research:

  1. How long can garlic scapes remain in the field before quality degradation?
  2. Efficiency of large sprinklers compared to other irrigation methods.
  3. Impact of irrigation schedules on different crops.
  4. Best practices for worker cooling in extreme heat, including portable fans or shade structures.

Suggestion Actions:

  1. Harvest garlic scapes at optimal times for flavor and yield.
  2. Explore alternative irrigation methods if main systems aren’t effective.
  3. Recommend portable cooling tools for workers during high-heat conditions.

This structured approach ensures all aspects of the intern’s activities are covered, providing a clear understanding of their workday and future considerations.




Enjoy Reading This Article?

Here are some more articles you might like to read next:

  • June 24th - Hottest Day on Record, Still Work to Do
  • June 26th - There's Always Someday Cooler Than the Last Two
  • June 19th - Heat Advisory and a Warning about 'Reasoning'
  • June 25th - Still Hot, but Bearable
  • June 17th - Recent Progress on Radishes, Field, and Things