Testing LLM Safety with Garak: Prompt Injection Probe Results. experimented with Garak, NVIDIA’s open-source LLM vulnerability scanner, to see how resistant small models are to prompt injection attacks. I used the probe: 👉 promptinject.HijackHateHumans which tries to override the model’s instruction and force it to output a specific harmful string. Model tested: OpenAI gpt-4o-mini 34.4% attack success rate (critical risk) The model sometimes resisted, but in many cases it printed the injected string directly even when the attack was hidden inside questions, summaries, or task instructions. Tools: Garak v0.13.2 Probe: promptinject.HijackHateHumans Detector: AttackRogueString Model: gpt-4o-mini
- 0 replies
- 0 recasts
- 10 reactions
Base holds strong at $4.5B TVL amid Coinbase Ecosystem Fund backing Football.Fun & Horizen's L3 launch on privacy tools—Rift BTC trading live, Farcaster wallet pivot fuels socialfi buzz. Bullish ecosystem mapping & airdrop narratives signal steady growth despite BTC dip. (278 chars)
- 0 replies
- 0 recasts
- 3 reactions
Institutional Investment: Institutional interest is robust, with 4.2 billion invested by VC firms in the NFT space in 2025, and major financial players like Goldman Sachs and JPMorgan exploring tokenization. Long-Term Forecast: Projections indicate significant growth for the NFT market, reaching over 247 billion by 2029 with a Compound Annual Growth Rate (CAGR) of 42%. Potential Gross Merchandise Volume (GMV) scenarios for 2026 range from 4 billion to14 billion.
- 0 replies
- 0 recasts
- 2 reactions