Jason Axley
@jason.axley.net
I do appsec, skeptical & geeky stuff, biking, guitar, travel & stay young goofing around with my kids. Open to mentoring infosec. DM me.
@axleyjc.federate.social
@axleyjc.federate.social
Reposted by Jason Axley
Reposted by Jason Axley
Fascinating thread!
You might enjoy my recent Science piece on AI "gaslighting":
www.science.org/doi/10.1126/...
You might enjoy my recent Science piece on AI "gaslighting":
www.science.org/doi/10.1126/...
Why AI chatbots lie to us
A few weeks ago, a colleague of mine needed to collect and format some data from a website, and he asked the latest version of Anthropic’s generative AI system, Claude, for help. Claude cheerfully agr...
www.science.org
August 12, 2025 at 2:31 PM
Fascinating thread!
You might enjoy my recent Science piece on AI "gaslighting":
www.science.org/doi/10.1126/...
You might enjoy my recent Science piece on AI "gaslighting":
www.science.org/doi/10.1126/...
Reposted by Jason Axley
MCP specification, section 3. Security and Trust & Safety:
Every security principle is OPTIONAL.
#whatmeworry #whatcouldpossiblygowrong #mcp
Every security principle is OPTIONAL.
#whatmeworry #whatcouldpossiblygowrong #mcp
August 6, 2025 at 3:18 AM
MCP specification, section 3. Security and Trust & Safety:
Every security principle is OPTIONAL.
#whatmeworry #whatcouldpossiblygowrong #mcp
Every security principle is OPTIONAL.
#whatmeworry #whatcouldpossiblygowrong #mcp