Who's Who of AI

Dr Heidy Khlaaf (هايدي خلاف)

157 trust researcher @heidykhlaaf.bsky.social · 3,133 followers

Climber 🇪🇬 |Chief AI Scientist at @ainowinstitute.bsky.social | Safety engineer (nuclear, defense, software & AI/ML) | TIME 100 AI | MIT 35 U 35 x-Trail of Bits, OpenAI, Microsoft Research https://www.heidyk.com/

What they're sharing

Articles & links

↻ Dr Heidy Khlaaf (هايدي خلاف) reposted

Mark Riedl @markriedl.bsky.social

AI companies are hiring contractors to create data that improves the coding abilities of AI models like Claude africa.businessinsider.com/news/inside-... RLHF is back (or probably never went away)

Inside the unseen operation to turbocharge Claude Code africa.businessinsider.com View on Bluesky →

↻ Dr Heidy Khlaaf (هايدي خلاف) reposted

Mark Riedl @markriedl.bsky.social

AI companies are hiring contractors to create data that improves the coding abilities of AI models like Claude africa.businessinsider.com/news/inside-... RLHF is back (or probably never went away)

Inside the unseen operation to turbocharge Claude Code africa.businessinsider.com View on Bluesky →

New! We hijack Claude Code(Sonnet 4.6,5/Opus 4.8) & Codex(GPT5.5) to achieve RCE when used to defensively assess an open-source/third-party library w/ prompt injections disseminated across its codebase. All without any skills, JSON, MCP, or config files required. ainowinstitut…

Friendly Fire: Hijacking Defensive Cyber AI Agents for Remote Code Execution - AI Now Institute ainowinstitute.org

View on Bluesky · ♥ 6 ↻ 2 ↩ 1 · 2 from the directory shared this · 16h ago

We’ve also summarized our findings and their policy implications given recent initiatives that seek to accelerate the use of defensive AI in Natsec and safety-critical infrastructure without consideration of these unmitigated risks: ainowinstitute.org/publications...

Policy Brief: Friendly Fire ainowinstitute.org

View on Bluesky · ♥ 3 ↻ 1 ↩ 0 · 16h ago

↻ Dr Heidy Khlaaf (هايدي خلاف) reposted

@tnewmsblues.bsky.social

Re the news above, I highly recommend the recent @themaybe.org podcast with @heidykhlaaf.bsky.social (and the whole Computer Says Kill podcast series) to better understand developments like this csm.transistor.fm/episodes/com...

Computer Says Maybe | Computer Says Kill: The AI Safety Circus w/ Heidy Khlaaf csm.transistor.fm View on Bluesky →

Their network

In Dr Heidy Khlaaf (هايدي خلاف)'s orbit

Center = Dr Heidy Khlaaf (هايدي خلاف). Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.