My suspicion is that any size in this range would work just fine. You are asking for (and LLMs are gladly spending tokens on) more precision than is available from the sources and reasoning they have.
Did you try at least a few options to see if any of the warnings or predictions were correct at this granularity? I'd expect the differences to be very difficult to notice.
Later on, out of curiosity, I did try a 3/32″ pilot hole, on a separate scrap piece. I did see the phenomenon that ChatGPT and Claude were warning about, where the surface of the material mushroomed up and ruined the surface finish. A 1/8″ pilot hole seemed to work fine, but I didn't conduct a rigorous stress test to determine whether it was significantly weaker than the 7/64″ hole. It's entirely possible that I could have used a 1/8″ bit and it would have worked fine.
Yes, my usage of 6 LLMs for this was gratuitous. It was less about getting practical advice and more about seeing how different LLMs would handle a question for which there wasn't a single "correct" answer based on internet sources, and how they'd respond to feedback from the user about other approaches. I learned that ChatGPT and Gemini tend to fixate more and push back against the user, while Claude is less committed to its answer. ChatGPT, Gemini and Claude all seemed to have a similar level of detail while the quality of the answers provided by Meta AI, Deepseek and Kimi was a step below.
This enabled me to use Said Achmiz's SDI approach[3]to make a final decision.
Just to be clear, I think you might mean Alicorn's SDI approach?
I reference Said Achmiz's post specifically, because his post has an elaboration on Alicorn's approach, where he considers what the various approaches he's researched reveal about the structure of the underlying system and combines that with his background knowledge to improve the improvisation step.
In my case, I used my (admittedly limited) background knowledge of the behavior of wood to try to determine what the most important considerations were when choosing the screw type. In this case, it was the diameter of the solid root, and whether undersizing the hole would place undue strain on the board.
Is it possible that anything in the 3/32 to 1/8 range works just fine? My reference point for screws is mostly sinking wall plugs into plasterboard/masonry, where you quite often see plugs accepting a wide variety of screw sizes e.g. 3.5 to 5 mm. I imagine particleboard is less forgiving, but is it that much less forgiving?
I answered the question in my other reply, but to reiterate, I did observe surface marring with a 3/32″ hole. I didn't notice any specific difference with a 1/8″ hole, but I didn't test it rigorously enough to see if the hold the screw had on the board was weaker.
Jeez, I usually just eyeball the screw against the available bits.
I probably wouldn't expect wood screws to hold in particle board at all, though. Definitely not #8s. That may be why the charts don't tell you.
tl;dr: When driving #8 wood screws into particleboard, use a 7/64″ drill bit for the pilot holes
Last Sunday, when helping my dad with a "woodworking" [1] project, I ran into a question. In order to attach two pieces of particleboard to each other using corner braces, I needed to drive some wood screws into the particleboard. But what size pilot hole should I drill for my #8 screws? I only had my phone handy, and on its limited screen I couldn't find any obvious answers from Google. The size charts I saw referenced hardwoods and softwoods, but made no mention of engineered materials like particleboard.
Not finding a straight answer from a web search, I turned to LLMs. Six of them in fact. I posed the following query to Gemini, ChatGPT, Claude, Meta AI, DeepSeek and Kimi:
The question was deliberately left somewhat ambiguous. I wanted to see how various LLMs would handle the ambiguity and how they'd react to follow-up responses.
Gemini (Gemini 3.1 Pro, Thinking level: extended) insisted on a 3/32″ [2] pilot hole. Its logic was that the screw threads should have maximum contact with the particleboard fibers, and therefore a smaller hole, just a bit smaller than the root of the screw, was the best option. When asked follow up questions, it too didn't change its recommendation, and insisted that the reduced structural integrity of particleboard means that it should be treated more like an ultra-soft softwood rather than a hardwood. While it mentioned a 7/64″ pilot hole as a possibility, it insisted that 3/32″ was the best starting point.
ChatGPT (ChatGPT 5.5, Thinking, effort level: extended), on the other hand, insisted that the pilot hole should be 1/8″. It said that particleboard is brittle and behaves more like a hardwood, and therefore a larger hole size is necessary. While it said that 7/64″ is a possibility, it recommended 1/8″ to minimize the risk of cracking the board. It did not change its recommendation when asked follow-up questions, and insisted that 1/8″ was the correct bit size, although it did suggest trying smaller bits on scrap pieces of particleboard in order to determine whether it would result in surface marring or splitting. Its data table also listed the possibility of going higher than 1/8″ to 9/64″, if there was a significant risk of splitting the wood.
Claude (Claude Opus 4.8, Thinking) said that the best starting point was 7/64″, splitting the difference between Gemini and ChatGPT. It also claimed that particleboard behaved more like hardwood than softwood, but it had a different estimate for the diameter of the root of the wood screw, which explained its logic in choosing 7/64″ as a starting value. When asked about other options, it didn't insist that 7/64″ was the absolute correct value, saying instead that it was a reasonable middle ground between 3/32″ and 1/8″. It specifically said that 3/32″ is fine if the risk of surface marring is acceptable and the hole is in the interior of the board where the risk of splitting is low.
Meta AI (Thinking mode) also agreed that 7/64″ was the best starting point. However, instead of basing its recommendation on the logic of screw root and thread diameters and the properties of particleboard, it quoted several web charts recommending a 7/64″ for hardwood, and claimed that because particleboard behaves more like hardwood than softwood, 7/64″ is the best starting point. Like Claude, it also wasn't very committed to its recommendation, saying that if you only have a 1/8″ bit, that's fine too.
DeepSeek (Thinking) was the only one of the models I tested which didn't have a web search (that's available for the Instant model only). Its initial recommendation was for 1/8″ as a starting point, and stepped up the bit size to 9/64″ for pilot holes near an edge or corner. However, when I asked it whether 7/64″ was acceptable, it agreed with me, and even went so far as to say that 7/64″ is the better option if I want to prioritize hold strength.
Kimi (K2.6 Thinking) behaved much like DeepSeek. It started off recommending a 1/8″ pilot hole, but when I asked about 7/64″ it said, "You're right to push back," and changed reasoning to agree with my question, changing its answer to prioritize thread engagement over minimizing the risk of splitting the board.
All the models emphasized the risk damaging the surface finish of the particleboard by overtightening, suggesting that, at the very least, the final few turns of the screw should be done by hand. They also suggested drilling countersinks to allow the screw heads to sit flush against the surface of the particleboard.
While the models didn't come to a strong consensus on the size of the bit I should use to drill the pilot hole, they did give me a rough range of bit sizes, from 3/32″ up to 9/64″, along with parameters I should consider (hold strength vs. risk of surface damage or splitting the board) when choosing whether to use a larger or smaller bit. This enabled me to use Said Achmiz's SDI approach [3] to make a final decision.
I did some further research into my specific screws and it turns out that 3/32″ was less than the diameter of the solid root at the center of the screw, so going with a hole that small would have risked surface damage and would have made the screw unnecessarily difficult to drive with hand tools. At the same time, I also found out that a 1/8″ pilot hole would be larger than the screw root, and would potentially not offer enough material for the screw threads to grip effectively. As a result, I chose the "Goldilocks option" and drilled 7/64″ pilot holes. It worked well. There was no marring of the surface finish when driving the screws, and the screws gripped the wood tightly enough that subsequent moderately rough handling, including one accidental drop, didn't cause any of the screws to rip out. I didn't bother drilling countersinks, as the corner braces I was using had countersunk holes built in, but the reminder to do was valid, and is something I'll be keeping in mind for the future.
This experience was a strong validation of the SDI approach, and showed that SDI works just as well with multiple LLMs as it does with web searches. Furthermore, seeing the insistence of e.g. Gemini and ChatGPT on the correctness of their respective answers reinforced the importance of getting a variety of responses, and showed that, on questions where there is not a strong Internet consensus on the correct answer, different models will choose different salient aspects of the problem and will potentially fixate on them. It's important to recognize when this is happening, and ensure that, when following a LLM's advice, you haven't inadvertently replicated the LLM's biases.
I don't consider particleboard to be wood, hence the scare quotes ↩︎
All units will be imperial in this post, because that's just how woodworking is ↩︎
Hence the title of this post ↩︎