#Mythos finds a #curl vulnerability
-
@bagder from my talks with people who had been given access to mythos in their org, they say it does find things which current tools miss, but also overlooks cases which current tools catch. so, yeah, to me it is "mostly marketing" combined with general FUD
@bagder but i have not asked them about exploit capabilities, though. there i cannot comment, and there it could be significantly better caps
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder hah! i was right!
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder
At least it works. It would have been quite a disaster if it found zero. -
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder Would it be a good idea to take an older version, where you already know you (as humans) found (and fixed) a certain number of vulnerabilities and see if AI can spot those correctly?
The Idee beeing to really have a quality test? ("For Science"
). Or are the all trained on your latest version already and that would invalidate that test?
-
@bagder Would it be a good idea to take an older version, where you already know you (as humans) found (and fixed) a certain number of vulnerabilities and see if AI can spot those correctly?
The Idee beeing to really have a quality test? ("For Science"
). Or are the all trained on your latest version already and that would invalidate that test?
@johnnythan I agree that would be an interesting challenge for someone with time and tokens to burn
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
"Zero memory-safety vulnerabilities found."
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder LOL!
The report concluded it found five “Confirmed security vulnerabilities”. I think using the term confirmed is a little amusing when the AI says it confidently by itself. Yes, the AI thinks they are confirmed, but the curl security team has a slightly different take.
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder yessssssssss. we guessed right on the poll
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder I suspect the question is, will it still be a worthwhile tool when the actual price to use the tool, not subsidized by anyone's war chest or VC, is revealed?
-
My personal conclusion can however not end up with anything else than that the big hype around this model so far was primarily marketing. I see no evidence that this setup finds issues to any particular higher or more advanced degree than the other tools have done before Mythos. Maybe this model is a little bit better, but even if it is, it is not better to a degree that seems to make a significant dent in code analyzing.
@bagder Yes. While I can't prove it, it tracks with A stealing the playbook of O who already said that they will likely pivot from B2C into B2B. One last fear mongering push and tons of directed compute at reputable projects and suddenly your marketing far surpasses that of any benchmark. -
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder the power of rigorous software engineering
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
@bagder not trying to buy into Anthropic's hype machine, but I wonder if curl is just a nonrepresentative code base. The average closed source / internal code base is probably worse in orders of magnitude when it comes to static checks, engineering principles, you name it.
I suspect Mythos will be useful in making poor software a bit more secure. That could have been done without AI of course.
-
@bagder not trying to buy into Anthropic's hype machine, but I wonder if curl is just a nonrepresentative code base. The average closed source / internal code base is probably worse in orders of magnitude when it comes to static checks, engineering principles, you name it.
I suspect Mythos will be useful in making poor software a bit more secure. That could have been done without AI of course.
@eskett I do emphasize that it is good at finding flaws. And so are many other models. So yes, they will certainly find many flaws in source code going forward. Mythos and the others.
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
AI powered code analyzers are significantly better at finding security flaws and mistakes in source code than any traditional code analyzers did in the past
I’m not sure this follows from what you’ve said in the rest of the post. Static analysers and fuzzers also made it very easy for people to find vulnerabilities and typically found a lot when they were deployed for the first time. And both were a lot cheaper to run than something like Mythos.
They aren’t finding as many vulnerabilities now because projects that are critical for security are integrating them into their CI flows.
And this is what always happens with some new technique: valgrind, Coverity, sanitisers, fuzzers, and so on: they’re released, they find a load of bugs that existing techniques failed to find, people fix them, they get integrated into regular CI runs, and the kinds of bugs that those tools find never make it into the tree.
Syskaller, for example, has found a lot more bugs in the Linux kernel than any Anthropic tools. And that’s just one fuzzing tool.
-
AI powered code analyzers are significantly better at finding security flaws and mistakes in source code than any traditional code analyzers did in the past
I’m not sure this follows from what you’ve said in the rest of the post. Static analysers and fuzzers also made it very easy for people to find vulnerabilities and typically found a lot when they were deployed for the first time. And both were a lot cheaper to run than something like Mythos.
They aren’t finding as many vulnerabilities now because projects that are critical for security are integrating them into their CI flows.
And this is what always happens with some new technique: valgrind, Coverity, sanitisers, fuzzers, and so on: they’re released, they find a load of bugs that existing techniques failed to find, people fix them, they get integrated into regular CI runs, and the kinds of bugs that those tools find never make it into the tree.
Syskaller, for example, has found a lot more bugs in the Linux kernel than any Anthropic tools. And that’s just one fuzzing tool.
@david_chisnall i think it makes sense for everyone to run the "easy" and cheap tools first, and once they all find no more problems, then you bring out the bigger canons like AI analyzers. So yeah, which is "best" ? It probably depends.
-
@david_chisnall i think it makes sense for everyone to run the "easy" and cheap tools first, and once they all find no more problems, then you bring out the bigger canons like AI analyzers. So yeah, which is "best" ? It probably depends.
@bagder @david_chisnall I'm not going to advocate actually doing this because it's expensive and I'm not a fan of the environmental impacts, but I am curious what it would find if you pointed it at the codebase from a time before the other precursor tools like fuzzers were in use. How many bugs can it find that you know with hindsight are there to be found?
-
@bagder @david_chisnall I'm not going to advocate actually doing this because it's expensive and I'm not a fan of the environmental impacts, but I am curious what it would find if you pointed it at the codebase from a time before the other precursor tools like fuzzers were in use. How many bugs can it find that you know with hindsight are there to be found?
@http_error_418 I agree, this would be a very interesting experiment - and potentially informative for other teams deciding where to spend limited developer time. @bagder @david_chisnall
-
My personal conclusion can however not end up with anything else than that the big hype around this model so far was primarily marketing. I see no evidence that this setup finds issues to any particular higher or more advanced degree than the other tools have done before Mythos. Maybe this model is a little bit better, but even if it is, it is not better to a degree that seems to make a significant dent in code analyzing.
@bagder
In terms of evidence to the contrary:
Check out
https://social.security.plumbing/@freddy/116549451049357174 / the blog post:
https://hacks.mozilla.org/2026/05/behind-the-scenes-hardening-firefox/>270 vulnerabilities found by Mythos fixed in a single Firefox release.
That's just one data point, but interestingly far off from yours.
-
#Mythos finds a #curl vulnerability
yes, as in singular one.
Mythos finds a curl vulnerability
yes, as in singular one. Back in April 2026 Anthropic caused a lot of media noise when they concluded that their new AI model Mythos is dangerously good at finding security flaws in source code. Apparently Mythos was so good at this that Anthropic would not release this model to the public yet but instead … Continue reading Mythos finds a curl vulnerability →
daniel.haxx.se (daniel.haxx.se)
I love it :
"The AI reviews are used in addition to the human reviews. They help us, they don’t replace us."
-
My personal conclusion can however not end up with anything else than that the big hype around this model so far was primarily marketing. I see no evidence that this setup finds issues to any particular higher or more advanced degree than the other tools have done before Mythos. Maybe this model is a little bit better, but even if it is, it is not better to a degree that seems to make a significant dent in code analyzing.
@bagder How do you explain that Mythos found 271 bugs in Firefox, and counting, and only 1 in cURL. Is the Firefox code base 271 times larger?
