Can Artificial Intelligence Design a New Knife Steel?

If you want to support knife steel research, come join us at Patreon.com/KnifeSteelNerds. You get articles and videos before everyone else!

If you’re looking for Knife Steel Nerds Christmas gifts, some good choices are the book Knife Engineering, the book The Story of Knife Steel, and the Buck knife model 501 “The Larrin.”

Video

There is a video version of the following information:

Why Analyze AI Capabilities?

I’ve had multiple people over the past couple years send me steel compositions that ChatGPT came up with. People want to know what I think, and if AI is going to be taking over everything now, including the design of new steels. I took a few of the steel compositions people sent me so I can analyze them to see if they would work. Can ChatGPT come up with new and fresh ideas to revolutionize knife steel? Let’s look at them and see:

Infinisteel

ChatGPT has some grandiose claims for this first steel:

Introducing the revolutionary super steel, InfiniSteel! This cutting-edge material boasts unparalleled toughness, edge retention, and corrosion resistance, surpassing any other steel on the market. By exploiting a unique interplay between various alloying elements, InfiniSteel exhibits remarkable properties that set it apart from conventional steel grades.

The InfiniSteel composition consists of:

Iron (Fe): 75%
Carbon (C): 1.2%
Chromium (Cr): 20%
Vanadium (V): 2.5%
Molybdenum (Mo): 0.8%
Tungsten (W): 0.5%

The biggest issue with this steel is that it won’t harden. When heat treating knife steel the main step is “austenitizing,” the high temperature step before the steel is quenched (rapidly cooled). You can read more about austenitizing in this article. It is called the austenitizing temperature because the steel transforms from the low temperature ferrite phase to the high temperature austenite phase. Ferrite is the normal “phase” of iron at room temperature which has a certain set of properties, such as being magnetic and soft. When you heat up iron to high temperature the atoms rearrange themselves into a different structure called austenite, which has different properties, one of them being that it is not magnetic. When you quench austenite it transforms to the hard steel phase martensite. If you don’t transform to austenite at your heat treatment temperature you will still have soft ferrite after heat treating and thus it will not make a good knife edge.

Some elements are “ferrite stabilizers” and some are “austenite stabilizers.” This steel has a relatively high content of ferrite stabilizers including 20% Cr, 2.5% V, 0.8% Mo, and 0.5% W. This would be ok if there were enough austenite stabilizers, but the only austenite stabilizer in the steel is carbon, and 1.2% is not enough for all of those ferrite stabilizers. ChatGPT is just adding elements in because when it reads random articles online that say that each element does some beneficial thing. It doesn’t know anything about balancing different elements together and it has no idea that it needs to have enough carbon or other austenite stabilizers to go with all of those ferrite stabilizers.

Here’s a detailed explanation of the role each component plays in the alloy and how they contribute to the exceptional performance of InfiniSteel:

Iron (Fe): As the primary element in steel, iron provides the backbone of the material’s structure. It imparts strength and toughness to the alloy, ensuring InfiniSteel can withstand substantial loads and resist deformation under various conditions.

Carbon (C): The addition of 1.2% carbon significantly improves the strength and hardness of the alloy. This results in superior edge retention, allowing InfiniSteel to maintain a sharp edge even after extensive use. Additionally, the high carbon content enables the formation of carbides, which further enhance wear resistance.

Chromium (Cr): Chromium contributes to InfiniSteel’s exceptional corrosion resistance. At 20%, it forms a stable, adherent, and self-healing passive film on the steel’s surface, effectively protecting it from oxidizing agents. This film also enhances the steel’s resistance to various corrosive environments, such as those with high humidity or in contact with aggressive chemicals.

Vanadium (V): Vanadium’s primary function is to refine the steel’s grain structure, leading to enhanced toughness and resistance to impact. At 2.5%, it forms hard vanadium carbides that strengthen the material and improve its edge retention properties. Additionally, vanadium aids in stabilizing the passive film, further enhancing the steel’s corrosion resistance.

Molybdenum (Mo): Molybdenum strengthens the steel matrix and improves its resistance to high-temperature creep and stress rupture. At 0.8%, it also contributes to the formation of a more stable passive film, increasing the corrosion resistance of InfiniSteel.

Tungsten (W): The addition of 0.5% tungsten enhances the high-temperature performance and hardness of InfiniSteel. It forms carbides that provide excellent wear resistance, contributing to the alloy’s outstanding edge retention properties.

Through this unique interplay of alloying elements, InfiniSteel achieves an unprecedented level of performance in terms of toughness, edge retention, and corrosion resistance. The combination of carefully selected constituents enables the alloy to outshine any other steel on the market, making it the ideal choice for a wide range of demanding applications, such as aerospace, automotive, marine, and cutting tools industries.

The explanations of what the different elements are doing are also very dumb and obviously based on random articles from non-experts online. For example, under iron it says that the iron “imparts strength and toughness to the alloy.” This is a very odd thing to say about the steel since steel is made up of iron. Iron is pretty soft before we add other elements to it, especially carbon. So why would you describe iron as imparting “strength”? Sounds like something a dumb AI would write.

It also says that “Vanadium’s primary function is to refine the steel’s grain structure, leading to enhanced toughness and resistance to impact.” Small amounts of vanadium, like 0.1-0.2%, are added to prevent grain growth. In knife steels when you have 0.3% or more added, that is for wear resistance. In that case it is adding wear resistance and reducing toughness. So the claim by the AI that the vanadium is added for enhanced toughness is nonsense.

The AI also says that molybdenum was added for “its resistance to high-temperature creep and stress rupture.” High temperature creep is when a material is held under stress at relatively high temperature for long periods of time. The material slowly deforms, which is called creep. Resisting creep is totally unnecessary in a knife, and the AI is just pulling things from various places to support its choices in a seemingly random way.

No manganese or silicon was added to the steel. These are not always shown on datasheets but are present in all tool steels that I am aware of. I would say it just didn’t mention them, but it also gave the percentage of iron (75%) which leaves no more room for Mn and Si.

User
Please provide a detailed analysis of Infinisteel vs Magnacut?

ChatGPT
InfiniSteel and MagnaCut are both high-performance steels designed for demanding applications. Here’s a detailed analysis comparing their properties and performance:

Composition:

MagnaCut:
Carbon (C): 1.15%
Chromium (Cr): 17.0%
Manganese (Mn): 0.6%
Nickel (Ni): 0.3%
Nitrogen (N): 0.18%
Vanadium (V): 4.0%
Molybdenum (Mo): 2.0%

Comparison:

Toughness: Both InfiniSteel and MagnaCut boast high levels of toughness due to their vanadium content, which refines the grain structure of the steel. InfiniSteel contains 2.5% vanadium, while MagnaCut has a higher vanadium content at 4.0%. The higher vanadium content in MagnaCut might result in slightly better toughness compared to InfiniSteel.

Corrosion resistance: InfiniSteel has a higher chromium content (20%) than MagnaCut (17%). This results in better passive film formation and, consequently, superior corrosion resistance. Additionally, MagnaCut’s nitrogen content (0.18%) further enhances its corrosion resistance. However, InfiniSteel is likely to have the edge in this category due to its higher chromium content.

…

The person who sent me this also asked ChatGPT how the steel would compare to MagnaCut. Somehow ChatGPT managed to get the composition of MagnaCut wrong. MagnaCut has 10.7% chromium but ChatGPT says it has 17%. It also has 0.2% nitrogen as a target, so the 0.18% nitrogen that ChatGPT reports could technically be a nitrogen content that would be seen in an individual bar of steel, but that is not the target composition. And it also reports that MagnaCut has 0.3% nickel, even though nickel is not added to the steel and is not reported in the datasheet.

ChatGPT also repeats its mistake from earlier, saying that vanadium in higher amounts leads to more toughness. So it says that MagnaCut would have higher toughness because it has 4% vanadium instead of the 2.5% in “Infinisteel.” That is not how it works.

My Grade: D-

It is difficult to give the steel high marks when you can’t harden it.

Ultravium Steel

— create a unique composition of elements for a great blade steel that does not exist yet…
ChatGPT:
Creating a unique composition for a great blade steel requires a deep understanding of metallurgy and the desired properties in the resulting steel. While this composition doesn’t exist yet, we can propose an innovative blend of elements to produce an exceptional blade steel:

Name: Ultravium Steel

Composition:

Carbon (C): 2.5%
A higher carbon content contributes to increased hardness, making the blade exceptionally sharp and able to hold an edge for extended periods.
Vanadium (V): 7%
Vanadium adds wear resistance, enhancing the blade’s durability and edge retention. It also aids in fine-grain structure formation, crucial for sharpness.
Molybdenum (Mo): 3%
Molybdenum boosts the steel’s strength, toughness, and resistance to corrosion. It also helps maintain blade sharpness under high-stress conditions.
Tungsten (W): 5%
Tungsten further improves hardness, wear resistance, and overall blade performance. It enhances the steel’s ability to withstand extreme temperatures.
Niobium (Nb): 1.5%
Niobium promotes grain refinement, which contributes to sharpness and overall blade strength. It also adds stability to the steel’s microstructure.
Cobalt (Co): 2%
Cobalt increases the steel’s strength and high-temperature performance, making it ideal for blades subjected to extreme conditions.
Copper (Cu): 0.5%
Copper adds a touch of corrosion resistance to the steel while maintaining its strength and hardness.
Silicon (Si): 1%
Silicon enhances the steel’s toughness and resistance to wear, improving its overall durability.

ChatGPT starts out by saying that a unique composition for knife steel “requires a deep understanding of metallurgy,” which I agree with. However, this composition shows that ChatGPT also does not have this required deep understanding. The approach appears to have been adding large amounts of most of the major elements. This steel is a good example of how ChatGPT “reads” things online that say all the positive things that different elements do. When a layman reads about different elements this is also typically what they see. It says what an element does to improve properties but it doesn’t usually explain the tradeoffs or how elements are balanced or how they work together. It says that molybdenum “helps maintain blade sharpness under high-stress conditions.” I don’t know what that means or how molybdenum is helping. Is a “high stress” condition one where an individual is under attack? Or is “high stress” referring to “engineering stress” where a load is being applied to a knife? It says that tungsten is added “to withstand extreme temperatures.” What kind of temperatures? Is this a knife for use in volcanoes? It says that niobium is for grain refinement, but 1.5% is way more than necessary for grain refinement. That amount is for wear resistance and ChatGPT didn’t even mention wear resistance. Cobalt was added again for “high-temperature performance,” “for blades subjected to extreme conditions.” And again I say that if the temperature is too high for the knife it is way, way too hot for humans. Copper is added for “a touch of corrosion resistance” for some reason.

There is a big omission with this steel, however, which is chromium. ChatGPT didn’t add any of it. This means the steel does not have any corrosion resistance to speak of (that 0.5% copper isn’t doing much). But chromium is also added to steels for other reasons. It is present in nearly all high alloy tool steels, in part so that it has high “hardenability” so that it can be quenched more slowly and still fully harden. Not adding it is very strange for this steel.

Heat Treatment:

Ultravium Steel would undergo a precise heat treatment process, including quenching and tempering, to maximize its hardness, toughness, and fine-grain structure. The ideal hardness level would be around HRC 65-66.
Properties:

Ultravium Steel would be renowned for its exceptional hardness, wear resistance, and edge retention. It would maintain sharpness even under heavy use and extreme conditions.
The steel’s fine-grain structure would contribute to its ability to take and hold a razor-sharp edge.
Superior strength and toughness would make it suitable for a wide range of cutting applications, from fine slicing to heavy-duty chopping.
Ultravium Steel would exhibit excellent corrosion resistance, reducing the need for extensive maintenance and ensuring longevity.
It would be an ideal choice for high-performance knives, cutting tools, and blades used in demanding environments.
Applications:

Chef’s knives: Ultravium Steel would excel in the kitchen, making it a favorite among professional chefs and culinary enthusiasts.
Survival and outdoor knives: Blades made from this steel would prove highly reliable in rugged outdoor conditions.
Industrial cutting tools: Ultravium Steel would be sought after for its ability to withstand heavy use in manufacturing and construction.
Military and tactical knives: Its strength and durability would make it suitable for combat and tactical applications.
Artistic blades: Bladesmiths and artisans would appreciate its ability to hold intricate patterns and designs in damascus or layered steel.
While this hypothetical Ultravium Steel may not exist yet, advancements in metallurgy continue to push the boundaries of what’s possible. Such an innovative blend of elements could revolutionize the world of blade steel, offering exceptional performance and versatility to knife makers and users alike.

ChatGPT then claims that Ultravium would have “excellent corrosion resistance” which it certainly would not have without any chromium. It also says that bladesmiths would like it for “its ability to hold intricate patterns and designed in damascus or layered steel.” I don’t know what it means to “hold” an intricate pattern. But bladesmiths would likely not prefer this steel for Damascus because the high alloy content would make it more difficult to forge weld.

My Grade: C-

Since this steel hardens I will give it a C-. Can’t give higher than that since it skipped chromium while claiming the steel would have high corrosion resistance.

MagnaCut+

— ChatGPT
Hypothetical Composition for “MagnaCut Plus”
• • •
Element Proposed Content

Carbon (C) 1.05%
Chromium (Cr) 11.5%
Vanadium (V) 3.0%
Molybdenum (Mo) 2.0%
Tungsten (W) 0.5%
Nitrogen (N) 0.3%
Niobium (Nb) 0.5%
Cobalt (Co) 1.5%

Expected Improvements
• Wear Resistance: The increase in vanadium and tungsten would lead to harder vanadium and tungsten carbides, resulting in better edge retention.
• Toughness: The slight decrease in carbon and the introduction of cobalt would help maintain or even improve toughness.
• Corrosion Resistance: The increase in chromium and nitrogen should enhance resistance to rust and corrosion.
• Grain Refinement: More niobium would aid in creating a finer grain structure, resulting in better overall balance.
Potential Drawbacks
• Higher Cost: Adding tungsten and cobalt increases the cost of production.
• More Challenging Heat Treatment: The changes may require more precise heat treatment to unlock the full potential of the alloy.
• Diminished Ease of Sharpening: Higher vanadium content can make sharpening slightly more difficult.
This proposed “MagnaCut Plus” would aim to push the limits of what MagnaCut offers without compromising the balanced properties that make it so desirable. It would likely excel in applications requiring even greater edge retention and toughness, such as high-performance cutting tools and hard-use knives.

This steel was requested by the user to be an improvement on MagnaCut. However, ChatGPT offers from very strange reasoning:

“The increase in vanadium and tungsten would lead to harder vanadium and tungsten carbides, resulting in better edge retention.”

The vanadium content was reduced from MagnaCut, down to 3% from 4%. So I don’t know why ChatGPT thinks it has increased vanadium. It also claims that it added tungsten to form “tungsten carbides.” In these types of high alloy steels, adding a tiny amount of tungsten does not lead to the formation of any carbides that are tungsten-rich. The tungsten incorporates into other carbide types such as vanadium-rich or chromium-rich carbides. And those carbides would not be any harder. A small addition of tungsten seems to be a theme for ChatGPT and I don’t really see the point. To be fair, there are several stainless steels from Takefu where they added small amounts of tungsten and claimed similar reasoning. But I have also been on record saying I think that the tungsten is unnecessary in these steels.

“More niobium would aid in creating a finer grain structure.” The niobium content is less than MagnaCut, 0.5% vs 2%. so it does not have “more niobium.”

“The changes may require more precise heat treatment to unlock the full potential of the alloy.” Why? Based on what?

Other criticisms of the design require more in-depth analysis with a thermodynamics software that predicts carbide types and alloy in solution. ChatGPT claims an improvement in corrosion resistance because of the higher chromium, but in fact the chromium in solution is reduced in the “MagnaCut+” alloy because of the other elements. There is also  3-5% chromium carbide in the heat treated structure which reduces corrosion resistance. The improvement in corrosion resistance with MagnaCut came from reducing chromium carbide content to near-zero and this steel dropped that innovation for no reason because ChatGPT doesn’t know what it is doing.

The carbide content of MagnaCut+ and MagnaCut would be similar but MagnaCut+ would have half of its carbide be the larger chromium-rich type, reducing toughness. It also claims that cobalt improves toughness, which it doesn’t.

My Grade: C

The steel can be hardened and would be nearly stainless. But calling it MagnaCut+ while reducing corrosion resistance, wear resistance, and toughness from MagnaCut is bad so it gets a C.

Some General Thoughts

In none of the proposals that ChatGPT gave did it ever say that it would make these steels by powder metallurgy. The very high alloy content of these steels means they would not be very good if made with conventional steelmaking. Or at the very least these would not be an improvement on existing steels if they were not made with powder metallurgy. So to not state explicitly that the steel should be made with powder metallurgy is a big omission.

ChatGPT provided no heat treating information. In one case ChatGPT claimed its new alloy would require “more precise heat treatment” but it did not provide any information on temperature ranges the steel might heat treat from. I very much doubt it could give accurate ranges even if asked. Of course in the one case the steel wouldn’t be able to be hardened at all so it wouldn’t be able to give a temperature that would work.

As I have stated several times, the approach ChatGPT takes is to add a lot of every element. It seems to think that elements only improve steel, so add some of all of them and you have a new super steel. It has no real concept of balancing different elements together or what the drawbacks are for adding different elements. It is basically what happens when “internet experts” try to design their own steel. So maybe this is a win for AI because it is now as smart as “internet experts”?

Could a Different AI Design Knife Steel?

ChatGPT is a “large language model,” meaning it was trained on huge amounts of written text from humans. It uses the statistical information about how humans put words together to generate coherent text. However, the model is not good at collecting data about different things, analyzing and comparing that data to find unique insights and solutions, and then to turn that into information. The other problem is that information about how to design tool steels is not really available on the internet, especially not in a form that ChatGPT could use. To really develop a good model we would need a database of information specific to knife steel design. So not a “general AI” but a “narrow AI” for our specific task. This would still be challenging, because the exact data we want does not really exist. The more data we can feed into an AI model the better the results can be. This is the classic example of “garbage in, garbage out.” A lot of information on tool steels and stainless steels are locked within specific steel companies, or even inside the heads of different metallurgists. The scientific literature, including publicly available journal articles and reported experiments, are not usually in a format that would easily be usable in a large database for an AI. Each study is done with different conditions: they hot rolled the steel with a different amount of reduction, they tested different sized coupons, they reported microstructure values but not mechanical properties, they tested Izod toughness instead of charpy toughness, etc.

For my own development of steel I use several different things, including:

1. Journal articles and books which collect different studies to find trends with different variables. Changes to composition, heat treatment, etc.
2. My own data which I have collected the last several years on Knife Steel Nerds – toughness, corrosion resistance, hardness, edge retention, etc.
3. Thermodynamics software – this software does not use machine learning or AI but uses databases to come up with expected microstructure at different temperatures. When it works perfectly you can know what carbides you have and which elements are “in solution” and how much.
4. Simple models for different properties – I have created simple equations which predict properties and there are some that are reported in journal articles and books. Some that I have created have been reported on this website such as this study on corrosion resistance or this study on edge wear.

With those pieces of information I can come up with approximate property targets and balance elements together. A similar process could be used for a “narrow AI.” Existing thermodynamics software could also be plugged into this AI, which is already happening. I think to do much better than humans would likely require a bigger database of experimental data than we currently have. For example, small tweaks could be made to existing steels such as the content of Mo, Si, Mn, N, etc. Currently, without experimentation by making these variations, we don’t know which changes could potentially lead to improvements. If our database was big enough, perhaps an AI could make predictions about which changes to try and thus reduce the number of experiments. But we are not there yet.