General Analysis
@gen_analysis
Followers
54
Following
70
Statuses
11
Automated AI Safety and Red Teaming Tools— Backed by @ycombinator
San Francisco
Joined January 2025
Read our recent blogpost on how our team found vulnerabilities in GPT-4o, o1, and o3 guardrails. The consistent success of our method highlights the need for developing robust, automated testing frameworks to safeguard AI systems.
0
1
3
This is why we need stress testing for LLMs. Finding subtle ways where these models fail requires careful analysis and engineering. Pulse is doing a great job at this.
Document ingestion & Gemini 2.0 caused a lot of buzz this week. As builders in this space, here's our take: Data ingestion is a multistep pipeline, and maintaining confidence from LLM nondeterministic outputs over millions of pages is a problem. (1/7)
0
0
3
LLM-powered search is fast, but is it resilient? We’re digging into systems like Perplexity and Deep Research to find where they break—and why. Stay tuned.
Deep Research Live from Tokyo 4pm PT / 9am JST Stay tuned for link to livestream.
0
0
0
RT @gen_analysis: Latest Update: ⛓️ Uncovering Hallucinations in GPT-4o for Legal AI We've recently completed an extensive red-teaming stud…
0
41
0
RT @founderjournals: 🚀 @gen_analysis launched! Finding Failure Modes for AI Models "Acquiring software products and replacing human teams…
0
1
0
Jailbroken: Read our latest report on how GPT 4 hallucinates on legal questions!
0
5
12
General Analysis just launched on @ycombinator's Launch YC! General Analysis: Finding Failure Modes for AI Models. Check them out:
0
1
6