Rich Harang @rich.harang.org · 17/09/2026[redacted] year old me, actually in an AI security role: 140
Rich Harang @rich.harang.org · 17/09/2026an AI security role, as maybe imagined by my recollection of a younger, more foolish me: 120
Rich Harang @rich.harang.org · 03/09/2026ICYMI: x.com/nvidianewsro... www.linkedin.com/feed/update/... Selfishly really happy to see NVIDIA throw its resources behind open weight models and public datasets via the HF platform. 041
Rich Harang @rich.harang.org · 02/09/2026"But everyone knows AI models don't do anything useful" openai.com/index/path-t... The bracing thing here is that a) this is on new/unknown exploits (though a fairly small number), and b) just look at how steep that Astra line is w/r/t token count. We need frontier-grade models for defenders ASAP. 120
Rich Harang @rich.harang.org · 26/08/2026Haven't been getting the pens out as much as I want to, but got a short sketch done a few days ago. Nose is a bit wonky but still enjoying exploring the block-printing-adjacent aesthetic, and slowly improving on getting portraits to look like the people I'm drawing. 000
Rich Harang @rich.harang.org · 06/08/2026As foretold by prophecy. www.reuters.com/technology/m... 011
Rich Harang @rich.harang.org · 02/08/2026I usually resist dunking on/amplifying these terrible takes, but holy shit. I know some day, probably not too far off, my kid's gonna start having too much going on to want to sit and shoot the shit with me all that often, and I'll be sad when it finally happens. Why would you ever give that up? 150
Rich Harang @rich.harang.org · 05/07/2026Air quality at 6:00 today, after the 5th of July fireworks that didn't start until the 4th had been over for 30 minutes. At least the incessant fucking fighter jet flyovers stopped early for weather. 000
Rich Harang @rich.harang.org · 13/06/2026Since recent events seem to have dragged AI powered biosafety back into the chat, thought I'd take the excuse to repost this. IYKYK. 060
Rich Harang @rich.harang.org · 04/06/2026Trying to get quicker and looser and less fussy at hatching -- quick sketch from imagination 120
Rich Harang @rich.harang.org · 02/03/2026I've used this 'seed' a few times now (code in alt text), with multiple models and every time I get something useful out. Tell it to "improve this script" once, then bootstrap to taste. It does need an Opus-4.6 level model to one-shot it, but cheaper models can get you there eventually. 240
Rich Harang @rich.harang.org · 27/05/2025Meanwhile, on Twitter (not "X"; their words not mine).... (From quick inspection: mostly crypto + telegram scams -- this is about a week's worth) 010
Rich Harang @rich.harang.org · 30/04/2025Tapping the "Models give you what you ask for, not what you want" sign yet again. 020
Rich Harang @rich.harang.org · 26/02/2025I am begging AI Red Teams to stop killing themselves trying to prevent attacks that can be just as easily accomplished by editing client-side HTML. For example: 100
Rich Harang @rich.harang.org · 23/01/2025Without downloading new pictures/videos where are you mentally? 780
Rich Harang @rich.harang.org · 08/01/2025An arcane tome filled with occult knowledge about the true workings of the world, that causes madness and despair in all who pursue its dark secrets? Yeah we've got one in the back. 091
Rich Harang @rich.harang.org · 07/12/2024Apropos of the "models pretending to escape from their server" thing: (from transformer-circuits.pub/2024/scaling...) 130
Rich Harang @rich.harang.org · 29/10/2024The team's response to _every_ LLM security finding this week: 020
Rich Harang @rich.harang.org · 27/11/2023Bucket list item complete: finally saw the northern lights in person. Had about ten minutes when you could see the green ribbons with the naked eye, no long exposure photo needed. 030
Rich Harang @rich.harang.org · 03/07/2023So remember the "mango pudding" LLM backdooring attack? How safe do you feel using these models now? 121
Rich Harang @rich.harang.org · 03/05/2023So, uh, that langchain vuln is pretty bad. (nvd.nist.gov/vuln/detail/CVE-2023-2…) 010