More on Colossal’s futile efforts to “de-extinct” ancient giant birds

After announcing that it would “de-extinct’ the Woolly Mammoth, and that it had in fact “de-extincted” the Dire Wolf, the company Colossal Biosciences is now making big noises about its effort to bring back extinct big birds: the giant moas of New Zealand (driven extinct by humans around 1300 AD) and the dodo of Mauritius (also killed off by humans in 1662). These are big birds (dodos weighed from 20-40 pounds, moas, of which there were nine species, from 55 to 600 pounds), and this fact alone makes it hard to de-extinct them.

But, as with the “woolly mammoth”, the concept of bringing back extinct species is impossible given our current technology, and saying that you can is grossly misleading.  And that’s for several reasons (the indented bits below are mine):

1.) You need the DNA of the extinct species if you’re going to create a simulacrum of it by injecting bits of the extinct animal’s DNA into the genome of a modern relative.

2.) You need to know what the DNA segments you have actually do in the animal, and how sequences differing between it and the donor genome can produce an animal with some traits of the original species. Where are the “big genes” in a mammoth, for example?

3.) Species are not “de-extincted”: what happens is that a living relative is genetically engineered by putting in a few bits of ancient DNA to create a “partial hybrid” that superficially resembles the ancient species. This involves finding and inserting a few bits of ancient DNA that you think will make the donor species look more like the extinct one. For example, I think fewer than 20 genes were engineered into a gray wolf genome to make the “dire wolf”. These included both dire wolf genes and mutant genes of modern dogs inserted into a gray wolf genome. The tweaked embryo was then implanted in a domestic dog. It’s important that you (and the press) realize that the ancient species is not brought back; what we get is a modern species that looks a bit like the ancient species. (See my post on the “dire-ish wolf” here.)

4.) There are problems with rearing the “tweaked” (I won’t call it “de-extincted”) species.  We cannot artificially inseminate elephants with elephant genomes that have been engineered for hairiness and bigger tuskx. We don’t have the ability to do this (though we might in the future), the embryos might not develop properly, and the mother is unlikely to take care of them. This is why Colossal has spoken of using “artificial uteruses” to rear the tweaked “mammothy” elephant.

5.) For giant birds like the dodo and moa, you need to be able to rear the tweaked species—presumably adjusted to be larger than its surrogate relative—in big eggs. Because those eggs don’t exist, they have to be made somehow. This week Colossal announced the creation of 3-D printed eggshells that could be used to contain a chicken embryo that develops to term.  But of course hatching is one thing, and rearing is another. What mother will rear a tweaked “dodolike” bird.  The closest relative of the dodo is the Nicobar pigeon, a bird considerably smaller than the dodo (the pigeon weighs about a pound). The closest living relative of the moas is the tinamou, which weighs about as much as a big chicken: five pounds max.  Rearing such birds to maturity is a serious problem, even if they were full dodos or moas rather than tweaked pigeons or tinamous.

4.) Colossal has announced that a crucial part of “de-extinction” is “rewilding”: releasing the tweaked animals back into nature to restore their niche.  This is one of the most questionable parts of the whole enterprise.  The tweaked hairy elephant, for example, should be released on the tundra (and in groups of individuals, which is yet another problem, as you need to engineer more than one hybrid). That tundra doesn’t exist in the form it did in the past, and, of course, the tweaked hairy elephant has to have all genes necessary to seek out and use the food that a real woolly mammoth would have, including genes for preferring as a mate others of its kind. It has to be able to survive extreme cold. We don’t know what genes these are! All we have are DNA sequences.

An example of the problems is Colossal’s announcement that it had “de-extincted” the Dire Wolf. It hadn’t: it engineered a gray wolf with about 20 genes taken from both wolves and domestic dogs, producing a whitish wolf that seems a bit larger than gray wolves.  Three of these creatures were made. Not only were they not released in the wild, but they are sequestered in a secret and tightly-controlled fenced area that is off limits to all but selected journalists.

All the brouhaha, then, is misleading. We don’t get extinct species back, we may not even get “tweaked” species back, and they are very unlikely to ever see the wild again. I discussed many of these problem in an op-ed last year in The Boston Globe (archived here). See also the New Scientist article below.

Because Colossal has misled the public—they originally said they’d de-extincted the dire wolf, then retracted that claim, then reinstated it, saying that if it looks like a dire wolf, it is a dire wolf—each time they accomplish something they tout it as a huge advance towards real de-extinction. After all, they have to keep their rich investors and the public happy.

The latest Colossal announcement, which came through the mail, is that of their developing an artificial chicken eggshell. The problem is (see below the fold) that this has already been done by others some time ago. A further problem, of course, is that this is only a minor issue in the problem of putting dodo-like or moa-like embryo in an artificial egg. Here’s Colossal’s announcement, and note the emphasis on “de-extinction”:

Here’s a breathy, chest-thumping video, accompanied by triumphant music, making it seem that the problem of de-extinction is on the way to being licked:

This is an achievement, of course, but to me it’s not a substantial step towards getting back moas and dodos. as it’s not that new.

And of course the press has picked it up, but this time they are careful to quote Colossal’s many critics as well as its chief propagandist, Ben Lamm. The Times of London talks about the eggshell as a step in resurrecting moas, using emus as surrogate moms. Click headline below to read:

Excerpts from The Times piece:

Colossal Biosciences, a Texan biotechnology firm, has developed a shell-less system it says is capable of supporting a bird embryo from early development through to the point of hatching.

So far the device has been used to produce baby chickens. The end goal, the company says, is to deploy a much larger version to resurrect the moa, whose eggs were about 80 times the volume of a farmyard hen’s.

. . . . So far the device has been used to produce baby chickens. The end goal, the company says, is to deploy a much larger version to resurrect the moa, whose eggs were about 80 times the volume of a farmyard hen’s.

. . .Eventually, the hope is that emu cells can be edited, introducing genetic changes that would make any resulting animal more moa-like. The hurdle then would be where to grow an embryo. According to Colossal, the eggs of the South Island giant moa were roughly eight times the volume of an emu’s. No living bird would be large enough to play mother to it.

This is where the artificial egg would come in. Colossal says the device could be scaled up, allowing embryos of much larger birds to develop in a controlled chamber. It claims this could remove the need for a living surrogate mother and make it possible to incubate embryos at sizes no modern bird can manage.

But they quote critics!

. . .Critics say such claims need careful handling. To recreate a mammoth, for instance, Colossal plans to alter the genetic code of an Asian elephant.

Even if that succeeds, sceptics argue the result would not truly be a mammoth, but an elephant engineered to have some mammoth-like traits, such as shaggy hair and extra fat reserves.

The same issues apply to the moa. The project, which is being backed by Sir Peter Jackson, the film director behind the Lord of the Rings trilogy, plans to compare ancient DNA from the extinct species with living relatives such as emus and tinamous to work out which genetic features helped make a moa a moa.

Well, there’s the rub! But Ben Lamm is always around to give the necessary donation-promoting optimism:

Ben Lamm, chief executive of Colossal, said: “Restoring species like the South Island giant moa isn’t just about reconstructing ancient genomes and editing [primordial germ cells, which eventually become sperm or eggs] — it requires building an entirely new incubation system where no surrogate exists.”

He added: “It’s a major milestone for Colossal and a foundational technology for our de-extinction toolkit.”

Again, I’m not saying that the artificial egg is not of any value. I’m just saying that insuperable problems remain with bringing back moas (or dodos).

Here’s a tweet that Matthew sent me, which called my attention to a New Scientist article that, mirabile dictu, strongly criticizes the de-extinction program as a whole:

Colossal says its "artificial egg" will help it bring back the moa, which had larger eggs than any living birds 🧪But it's really just an artificial eggshell, and even clingfilm will work – sort of – as an artificial eggshell. Plus there's the yolk problem…www.newscientist.com/article/2527…

— Michael Le Page (@mjflepage.bsky.social) 2026-05-19T12:19:10.242Z

The article at New Scientist can be found by clicking on the screenshot below, or finding it archived here:

A few Q&As from the piece:

Is this the first-ever artificial bird egg?

Colossal does use the term “artificial egg” in its press release, but it is really just an artificial eggshell. Either way, it isn’t a first – in fact, it’s possible to remove chicken eggs from their shells and hatch them from anything from plastic cups to cling film. However, the survival rate is usually low because, without an eggshell, the developing chicks may not get enough oxygen. A number of teams around the world have been working on more sophisticated so-called ex-ovo approaches.

How much better is it than cling film?

Colossal claims its silicone membrane is better than existing ex-ovo methods because it allows oxygen through at the same rate as a chicken eggshell and doesn’t require additional oxygen. However, it hasn’t released any experimental results to back this up. “I would love to see what the numbers are on efficiency,” says Ben Novak of non-profit wildlife conservation group Revive & Restore. “How many of these chicks hatch versus how many don’t?”

Colossal doesn’t publish much of the data that would enable scientists to see exactly what it did, which genes it used, and what the results are. Three more issues:

Does this mean we could create a giant artificial moa egg?

Even if Colossal’s approach does work well for chicken eggs, it won’t necessarily work for larger eggs. Larger eggs might need shells with different properties because of their lower surface-area-to-volume ratio, but this could probably be solved by tweaking the permeability of the membrane. Making a big egg also requires more than just a big eggshell. Moa eggs were up to 24 centimetres long and 18 cm wide, so they contained a lot more egg white and yolk than the eggs of living birds. Adding more egg white should be relatively straightforward. Chickens have been successfully hatched in the egg white from turkeys, says Novak, which suggests it won’t matter much what animal’s egg white is used.

How much better is it than cling film?

Colossal claims its silicone membrane is better than existing ex-ovo methods because it allows oxygen through at the same rate as a chicken eggshell and doesn’t require additional oxygen. However, it hasn’t released any experimental results to back this up. “I would love to see what the numbers are on efficiency,” says Ben Novak of non-profit wildlife conservation group Revive & Restore. “How many of these chicks hatch versus how many don’t?”

What about the extra yolk required?

That’s more of a problem. Each egg yolk is a single cell, meaning ostrich yolks are the largest single cells found on the planet. To make a yolk larger would require penetrating the cell membrane and injecting more yolk, says Novak, which would likely cause the cell to burst. So it might be necessary to somehow enlarge the cell membrane so it can hold the extra yolk. Which is probably doable, given enough time, effort and money.

And the $64,000 question (and answer):

If all the problems with making really big eggs are solved, could we then bring back the moa?

Absolutely not. The big problem is that DNA breaks up into smaller and smaller pieces over time, and all nine species of moa went extinct around 600 years ago. It’s never going to be possible to get a complete, working copy of a moa genome and produce a living animal genetically identical to any of the extinct species. Even the human genome wasn’t completed until 2023.

. . . . Is this what Colossal aims to do with the moa?  [i.e., tweaking existing species with a few gene edits]

Colossal hasn’t revealed its plans, but based on what it did with grey wolves and “woolly mice”, its aim will likely be to tweak a few genes in the emu to create something a bit like the moa in appearance, even if that means making genetic changes not present in the moa genome. Five of the 20 gene edits made to the grey wolves were changes not found in the dire wolf genome, for instance. Nic Rawlence at the University of Otago in New Zealand doesn’t think Colossal is close to achieving even this for the moa. “The development of a genetically engineered emu and calling it a moa for no good conservation or ecological reason, but rather an ecotourism venture, is still a long way off,” says Rawlence. Nor is the idea of bringing back the moa universally welcomed, he says. “There is widespread Māori and public opposition in Aotearoa New Zealand.”

Grok agrees with all this when I asked it the question below:

From Grok:

There’s more at New Scientist, but you can read it at the link or the archived link. I hope I’ve shown that Colossal is engaged in misleading the public (and I can’t help but think it knows this, since it de-emphasizes the “tweaking” part), and that you’ve learned some of the problems with its “de-extinction” claims.

Below the fold I’ve put Grok’s answer to my question about whether previous workers had reared chicken eggs using artificial “shells” previously. The answer is “yes,” though Colossal’s expensive shell is more sophisticated. I cannot vouch for the accuracy of Grok’s answers, but of course it tells you how to investigate them.

h/t Pyers.

Click below to read more:

From Grok:

Shell-less Culture in Artificial Containers (Research Since the 1970s–1980s)Scientists remove the contents of a fertilized chicken egg (yolk, albumen, and embryo) and transfer them to artificial vessels such as:

• Plastic cups (“chick-in-a-cup”)
• Plastic films or wraps (e.g., polymethylpentene)
• Hammocks or tripods
• Surrogate eggshells (sometimes from other birds)

These setups provide containment, gas exchange (via permeable membranes or films), humidity control, and sometimes supplemental calcium or oxygen. They allow direct observation of development and are used for embryology research, teratology studies, education, and techniques like transgenesis.Key milestones and results:

• M.M. Perry (1988) achieved the first full-term development and hatching from early stages (even near single-cell) using a multi-stage surrogate shell system. Initial hatch rates were low (~7%) but improved in later refinements (up to ~50% in optimized versions by others).
• Tahara & Obara (2014) developed a simple, effective system using plastic film vessels. Embryos transferred after ~55–56 hours of natural incubation, with calcium lactate and distilled water added, plus pure oxygen aeration late in development, achieved ~57% hatchability (8 out of 14 in one trial). The hatched chicks were healthy, reached sexual maturity, and produced normal offspring.
• Other methods (e.g., rotating plastic wrap hammocks in tripods with calcium injections) have yielded hatch rates around 40% or higher in optimized conditions, with viable chicks.

These chicks develop normally overall, though success rates are generally lower than natural incubation (~70%+ in good conditions) due to challenges like desiccation, calcium deficiency, or oxygen supply. The methods have been refined over time and remain valuable tools in developmental biology.

Recent Breakthrough: Artificial Eggshells (May 2026)On May 19, 2026, Colossal Biosciences announced the hatching of 26 live, healthy chicks from fully artificial eggshells. These are 3D-printed titanium lattice structures (with hundreds of hexagonal pores) lined with ultra-thin silicone membranes (~20 microns thick) that precisely mimic natural eggshell functions for gas exchange (O₂ in, CO₂ out) and controlled evaporation. A transparent lid allows monitoring.