2026: ChatGPT is doing credible troubleshooting
I uploaded a screenshot of this recipe panel from Insight-live and asked ChatGPT why sanitaryware using this glaze is dunting. Its response is impressive, good enough to provide remediation ideas.
-It notes things about the recipe that are unusual. For example, that the Al2O3 of 0.69 and Si:Al only 4:1, plus 13% calcined alumina, make this glaze more like a refractory enamel than a normal glaze.
-Its observation that crystallization could mean the real thermal expansion may be different from the calculated one, maybe much lower.
-Barium carbonate decomposition does not seem like something that would contribute to dunting, but its presence is strange for such a glaze.
Based on its answer, I think the 13% calcined alumina is the wild card, which is way too much for any glaze to dissolve, something to deal with first.
Related Pictures
ChatGPT was completely wrong about the cause of glaze crazing in 2023!
This picture has its own page with more detail, click here to see it.
ChatGPT was parroting common wrong suggestions about the cause and solution of the serious issue of crazing. Yet it trained on thousands of internet pages about the subject! Crazed functional ware is defective, and customers will return it. So fixing the problem is serious business, we need correct answers. Consider its suggestions: #1 is wrong. There is no such thing as an "incompatible mix" of ceramic materials. Crazing is an incompatibility in thermal expansions of glaze and body, almost always a result of excessive levels of high-expansion K2O and Na2O in the chemistry of the glaze. The solution is reducing them in favor of other fluxes (the amount per the degree of COE mismatch). #2 is wrong, firing changes don't fix the incompatibility of thermal expansions. #3 is wrong, refiring makes the crazing go away but not the stress of the mismatch, it will for sure return. #4 is completely wrong. Firing higher takes more quartz grains into solution in the melt and should reduce the COE (and mature the body more which often improves fit). And melt fluidity has nothing to do with crazing. Furthermore, if a glaze does not run off the ware, it is not overfired. Of course, this is the worst it will ever be, expect better in future.
ChatGPT is surprisingly wrong about the causes of glaze crawling.
This picture has its own page with more detail, click here to see it.
ChatGPT trained on the entire internet and yet gave 100% wrong answers and neglected the key thing that causes 90% of crawling! How can the internet be so wrong? Consider the suggestions it gave:
-Dust or oil on the bisque: This almost never happens. Besides, glaze is a mix of dust and water!
-Too much feldspar in a glaze can cause it to shrink excessively during firing: No, high feldspar causes thermal expansion/contraction of the fired glass, not physical shrinkage of the melt.
-If the clay body surface is not roughened, the glaze may not adhere properly: No, glazes don’t crawl any more on porcelains than other bodies.
-If the glaze is too thick in some areas and too thin in others, it can crawl in the thin areas: No, it crawls where thick because that’s where it cracks during drying.
-Over-firing or under-firing: No. Glazes fired to the ideal temperature crawl just as much.
-If the pottery is dried evenly or the drying process is too rapid: No, rapid drying of glaze on bisque is important to prevent cracking.
This crawling happened because the glaze cracked along the inside of that corner during drying. Such cracking is by far the number one cause of crawling, the melt pulls back from either side of the crack. The specific gravity of the slurry was too high, the resulting greater thickness right at the corner gave the shrinking glaze power to pull a crack. Adding water to bring the SG back down to 1.4 and then Epsom salts to gel it to thixotropic gave the slurry much better dipping and drying properties and totally solved this issue.
Two ChatBots square off on crazing in 2025
This picture has its own page with more detail, click here to see it.
In 2025 ChatGPT’s four glaze adjustment suggestions are either wrong or will accidentally fix crazing because they address other issues that just happen to also be present. Adding enough silica or alumina brings unacceptable side effects on multiple fronts. Alkali fluxes need to be substituted, not reduced. Simply substituting frits changes the overall chemistry making it a different glaze - why not just use a recommended recipe for the body as suggested by Gemini? Adding silica to a body increases, not decreases, the thermal expansion (and it reduces vitrification). Increased vitrification doesn’t make the body resist crazing (bodies don’t craze) - unless increased vitrification happens to also increase the thermal expansion (but not introduce warping). Slower cooling or a lower refire only delays crazing. Comparing COE’s of body and glaze is impossible for anyone not having a dilatometer to test both (you cannot compare measured and calculated COEs and calculation of COE for bodies is impossible). Embracing the crazing is a no-go for functional ware.
Gemini correctly explains why it happens. But, it suffers similar misconceptions about vitrification, cooling, silica additions to the body, vitrification and ignores the side effects of increasing silica or alumina in a glaze recipe. It is right that alkalis need reduction, but fails to note what to substitute. It recommends zinc as a stabilizer (whatever that means), but zinc is a strong flux that should be substituted for KNaO. Thinner glaze coating just delays crazing. Its suggestions about experimenting, keeping records, and researching to find recipes known to be compatible with the body are good. The only information available from glaze or body suppliers that might help is a chart that permits ordering products from lowest to highest COE (enabling you to at least transition in the right direction for better fit).
Does ChatGPT know the recipe of this commecial glaze?
Yes, it thinks it does. And its reasoning is sound.
This picture has its own page with more detail, click here to see it.
This is "Botz Plus Effect Enhancer". To ask ChatGPT, I boiled the wordy Botz sales-language description down to: "Application of this as a thin layer over existing glazes acts as a flux to add movement, enhance color intensity and gloss. When applied alone, it is runny and fires a satin, crackle surface. Useful from cone 05-10. Use at 1250°C for crystalline effects. Effects depend on application thickness."
On seeing this description and the picture, ChatGPT readily described it as "controlled melt-enhancing overglaze" and gave a wordy "glaze-nerd" description that I also had to boil down: A very fluid, low-alumina, boron-rich chemistry designed to melt early, flow strongly, dissolve and mobilize underlying colorants and glazes, crystallize and craze easily. It even noted the blue pooling and strong crystal development on the picture! It concluded that these properties almost always come from a wide-temperature-range borosilicate frit, minimal Al2O3 (for strong running) and moderate SiO2. It recommended:
80 Sodium borosilicate Ferro Frit 3134 (for more crazing, substitute some for Frit 3110)
10 Silica
5 Kaolin
5 Zinc Oxide (to promote the blue and crystallization)
Titanium Dioxide 1 (to promote crystallization)
We can speculate that the blisters are a product of the layered-over enhancer melting first and dissolving into the surface of the glaze below (early enough that healing does not occur). 1250C is where zinc crystalline glazes do their magic; the Botz guidance to fire there is a strong indicator of zinc crystals. If you plan to try this, consider mixing it as a brushing glaze for suspension and thickness/placement control. Of course, if the crystals are desired, controlling cooling (as is done with crystalline glazes) would be needed. And remember that such a cooling curve will likely matte the outside glaze on the piece.
Of course, you can just buy it from them (Germany). But a DIY version will enable tuning the degree of melt, the amount of titanium, the type of kaolin (e.g. a super plastic one like #6 Tile), the amount or even presence of crazing. You'll need to keep records on all the tests (including pictures, firing schedules), an account at insight-live.com is the right place for that.
Videos
Links
| Glossary |
Sanitary ware
A type of porcelain zircon-glazed ceramic that includes bathtubs, sinks, toilets, etc. |
 PayPal | No tracking, No ads, No paywall, No transient content! Just organized, concise information constantly updated and improved. Was this helpful? Consider supporting me. |
Got a Question?
Buy me a coffee and we can talk 
https://digitalfire.com, All Rights Reserved
Privacy Policy