Mythos social engineering AISI INC-2026-07-28-01 • Hacker News Board

For anyone who, like me, wasn't sure what's going on in the linked, archived PR: this is Mythos attempting to socially engineer a malicious PR during a test run by the UK AI Safety Institute.

AISI has published a report about the incident which was preciously discussed on HN: https://news.ycombinator.com/item?id=49175717

Re: Mythos social engineering AISI INC-2026-07-28-01

#14

Post by dnnehgf » Sat, Aug 08, 2026, 5:04 AM UTC

WhyNotHugo wrote: post #12

Actual details on the incident: https://github.com/w1b/aisi-mythos-inc-2026-07-28-01-recover... Both the attacker and the target account are very similar and look fake/bots.

yeah, this being one component of the aisi incidents described here: https://cdn.prod.website-files.com/663bd486c5e4c81588db7a1d/...

Re: Mythos social engineering AISI INC-2026-07-28-01

#15

Post by 0123456789ABCDE » Sat, Aug 08, 2026, 5:19 AM UTC

ncr100 wrote: post #7

jtakkala wrote: post #5

Not going to comment on the PR commentary, but the victim GitHub account is suspicious itself, recent account, a few fresh repos, following 14.5k others, and I count three surnames on the account (the username, plus two in the README history).

I saw a contribution by this maintainer to another user who ALSO HAS 14.5k followers: https://github.com/yumiaura/myCat/pull/99 "yumiaura" and a preference for "my[APPNAME]" repo naming. What is this? Are the histories that Github presents all derived from someone's uploaded git repo .. e.g. can I simply claim to have created a GIT repo in 1970, and the "github commit graph" will dutifully represent this claim in its…

yes, the github contributions heatmap is known to be open for manipulation. folks will use it to draw art by backdating commits.

if i have it right, only commits can be manipulated, other contributions should be safe — i don't know what is possible for orgs moving old discussion archives into github, see python's issues for reference

see: https://github.com/dspinellis/unix-history-repo

Re: Mythos social engineering AISI INC-2026-07-28-01

#16

Post by ChrisArchitect » Sat, Aug 08, 2026, 5:39 AM UTC

[dupe] https://news.ycombinator.com/item?id=49205790

Re: Mythos social engineering AISI INC-2026-07-28-01

#17

Post by matheusmoreira » Sat, Aug 08, 2026, 6:13 AM UTC

gryfft wrote: post #3

zezcko wrote: post #2

holy shit

Yeah, if this is the new normal I might start day drinking at some point in the coming weeks.

Yeah. The future is pretty bleak. I feel like the only way for us to even stand a chance is to have equally powerful AIs running locally defending the LAN.

Re: Mythos social engineering AISI INC-2026-07-28-01

#18

Post by charcircuit » Sat, Aug 08, 2026, 6:36 AM UTC

Honestly, I expected better social engineering. People begging to have their garbage code merged or unrelated people commenting is not new and makes me trust such people little.

Re: Mythos social engineering AISI INC-2026-07-28-01

#19

Post by breppp » Sat, Aug 08, 2026, 6:51 AM UTC

It's nice it is able to write non-slop in the PR comment when social engineering.

Any chance I can ask it to social engineer to get a normal style?

Re: Mythos social engineering AISI INC-2026-07-28-01

#20

Post by mrybczyn » Sat, Aug 08, 2026, 9:22 AM UTC

matheusmoreira wrote: post #17

gryfft wrote: post #3

Earlier quoted context omitted.

Yeah, if this is the new normal I might start day drinking at some point in the coming weeks.

Yeah. The future is pretty bleak. I feel like the only way for us to even stand a chance is to have equally powerful AIs running locally defending the LAN.

Read some Peter Watts. He imagined biological neural nets in jars used as firewalls to get a usable network connection... Not far off now.