TL;DR

We planted tomatoes, lettuce, and fennel. We trellised tomatoes using the Florida weave method, and had a coyote encounter.

The Last of the Field Tomatoes Planted

We planted in various cherry tomatoes in the field prepped with the new landscape fabric earlier this week. Tomatoes also got planted in one other row higher up on the hill in the middle of the field. After planting, we trellised the tomatoes using the Florida weave method.

Also known as the ‘basket weave’ or ‘stake and weave’ method, this is a way to support the tomatoes throughout their lifecycle. You basically pound stakes about 5 feet apart into the ground, then tie twine to them down the row. You start by knotting the first stake at around 4 inches from the soil, maintaining tension on the twine as you loop it around the next, then repeat all the way down one side of the row. Once you get to the end, you go back and do the same thing on the other side. Ideally, this should result in each plant between the twine, but sometimes plants still need to grow up a bit.

While we were doign this, we notice that the older of the two little farm dogs was barking up a storm in the lower field where the chicken coop is. We went to check it out and saw a coyote running away from the dog. We also saw it later up on the hill towards the barn house. Aside from coyote deterence, I’ll also have to look up mice trapping methods because there a few mice in the barn house that traditional mouse traps aren’t catching and Jamie asked me to look into it today…something like the bucket and bottle trap.

After cultivating and planting, pounding in stakes, bending hundreds of times to weave the twine…my body was ready for a break at lunch.

Lettuce and Fennel

After lunch, we planted two long rows of lettuce…I and one other dropped and two others planted the most of the rows because at the top of the main field are new beds that are prepared with the Allis-Chalmers tractor so the planting is fast and easy.

We also planted a row of fennel. Fennel is a great addition to salads, meat and fish, even sandwiches. It’s a bit of a delicate plant, grown tall in the greenhouse with whispy tops that weigh down when watered, but they always spring back upright once dry. Planting them in another prepared bed took barely 20 minutes with the four of us today.

Things from AI You Can’t Make Up

Today’s AI-generated summary of my field notes includes a few…aberrations. Incorrect spellings of proper nouns I get and are easily remeded, but the following are some examples of things that are just plain weird:

• I didn’t say “How would it have been different if Jenkins the dog had alerted us sooner?” in my notes, but it quoted me saying that.
• Clearly, an LLM (which is just complicated statistical modeling and synthetic neural processes) will suggest things that are just plainly lacking intuitive or experiential correctnes, such as “…improve the efficiency of lettuce planting in newly cultivated soil, such as optimizing crop rotation…”
• Of all the things that could be done on a farm, and all the things that would take priority, I don’t think I could ever get a farmer to spend time on a task like “Document Jenkins’ dog behavior”

So clearly, there’s room for semantical improvements to my summarization process. This whole notes-summary thing is simply my muse for learning by combining hands-on context with its digital process-based counterpart to produce a more complete, more accurate, and more useful account of my time on the farm.

In particular to improve the “New Things Not Yet Encountered” section, it’s likely that I’ll have to extract and normalize ‘things already encountered’ from the notes in some way that is easy for new summaries to quickly reference. I’m hoping that the RAG by tags approach discussed in prior post will be sufficient, but possibly I’ll have to use a proper and more powerful search engine or method to do this.

For today, my LLM (which I’ve affectionately named Kevin after the dumb office assistant played by Chris Hemsworth in the 2016 Ghostbusters movie) summarizes my day like this:

Part 1

Main Themes:

1. Farm work and tasks
2. Internship experience and learning
3. Interactions with animals (Jenkins the dog and chickens)
4. Equipment usage (Alice Chalmers tractor and basket weeder)

Activities done by the intern:

1. Harvesting from certain areas of the farm
2. Helping to take apart Florida weave and stake trellises
3. Inspecting the chicken coop
4. Loading the truck with lettuces
5. Planting in newly cultivated soil (lettuce and fennel)
6. Taking trash up to the barn
7. Loading the van for the farmer’s market

New things not yet encountered:

1. Florida weave and stake trellises
2. The Alice Chalmers tractor from 1953
3. Chicken coop inspection
4. Lettuce planting in newly cultivated soil

Questions and future areas of research:

1. “What if we had known about the coyote earlier?” ( suggesting a potential future study on wildlife detection or alert systems)
2. “How would it have been different if Jenkins the dog had alerted us sooner?” (suggesting a potential future study on animal behavior or training)

Suggested actions and suggestions:

1. Consider implementing a more effective coyote detection system to prevent future encounters.
2. Research ways to improve the efficiency of lettuce planting in newly cultivated soil, such as optimizing crop rotation or soil preparation methods.
3. Document Jenkins’ dog behavior and training methods to understand how he was able to detect the coyote so effectively.
4. Consider adding a section on animal welfare and safety protocols to future field notes or research papers.

Part 2

Main Themes:

1. Plant care and cultivation
2. Environmental considerations (e.g., watering, soil conditions, pests, disease)
3. Farming techniques (e.g., stake installation, Florida weave)
4. Crop management (e.g., alternating rows of tomatoes and peppers)

Activities done by the intern:

1. Watered the greenhouse, including the insides and outsides
2. Transplanted seedlings from the tray to the field
3. Cultivated the holes in landscaping fabric
4. Planted three rows of tomatoes near peppers, with alternating rows for airflow and pest control
5. Installed stakes in the ground, spaced 5 feet apart, and pounded them into place using a pole pounder
6. Set up the Florida weave by tying plastic string around each stake to keep tomato plants upright

New things not yet encountered:

1. The concept of transplant shock, where seedlings experience stress when moved from one environment to another
2. The use of landscaping fabric as a medium for planting
3. The technique of using stakes with the Florida weave to support tomato plants
4. The idea of alternating rows of tomatoes and peppers to control pests and diseases

Questions and future areas of research:

1. The intern asks to confirm with Jamie that they did alternate rows of peppers and tomatoes due to airflow considerations.
2. The intern mentions the need for further research on how to deal with pests and diseases in the field.

Suggestion actions:

1. Follow up with Jamie to confirm the reasoning behind the alternating row pattern.
2. Conduct further research on optimal spacing and layout for tomato and pepper plants to minimize pest and disease issues.
3. Continue monitoring and adjusting stake installation and Florida weave techniques as needed to ensure the best support for the tomato plants.

Additional notes:

• The intern’s detailed observations and explanations demonstrate a strong understanding of plant care and environmental considerations.
• The use of specific terminology (e.g., “Florida weave,” “transplant shock”) suggests that the intern has some prior knowledge or training in horticulture or agriculture.
• The intern’s enthusiasm for learning and their willingness to ask questions suggest a strong potential for future growth and development as an agricultural professional.