George Balston
@GeorgeBalston
Co-Founder at @AVERIorg. Prev: founded CETaS, led & scaled national security @TuringInst, HMG. AI Safety, Governance, (National) Security. 2xDad
270 Following 575 Followers
It seems a bit premature to declare that AI hasn’t changed the nature of cyberrisk when amateurs are (apparently) successfully and single-handedly hacking into large banks
i’m delighted to see several ideas we’ve been pushing at @AVERIorg in Sen. Cantwell’s new AI framework:
continuous stress testing of covered ai systems, ongoing government + independent oversight, meaningful access for independent researchers.
this is a strong step forward.
Show more
Frontier AI companies have committed to giving outside evaluators employee-like access to training, evaluation and deployment. We're very excited about this. But its impact depends heavily on implementation.
Today we're sharing our principles for embedded evaluations. 🧵
Show more
Confirmation of what was expected: GLM 5.3's safeguards as an open weight model are extremely weak.
Interesting bits:
- Abliteration (removing safeguards) cost only $4,400.
- Abliteration took GLM 5.3's refusal rate from above 90% to about 3% and 2% on two benchmarks and to 12% on the third.
- Abliteration barely reduced model capabilities. Same scores on GPQA and only 4% reduction in cybergym.
- Even with no abliteration, jailbreak methods were still very effective.
- None of the techniques to bypass safeguards that worked on GLM 5.3 worked on Claude models.
Show more
Claude Opus 5.5 writes a fugue in the style of Bach. I called Astra’s fugue the most impressive musical feat I’d ever seen from an LLM, and this is just as good. The circle-of-fifths sequence beginning at 1:13 is beautiful. The interplay of voices is natural and satisfying. LLMs are getting to the point where their music is good enough to listen to for pure enjoyment.
Show more
Swarm Scaling
Just how powerful are large swarms of AI agents?
And how do their powers scale as more and more agents are added to the swarm?
🧵
Our latest #RUSICommentary# by @GeorgeBalston examines the risks Open-weight AI models pose for criminal misuse, and asks whether UK surveillance law is keeping pace with a shifting AI landscape.
Show more
After leaving OpenAI, I decided to go all in on making frontier AI auditing a thing.
So I'm very glad many people seem to agree that's a good goal + even worth doing voluntarily!
But it's not the only thing that matters, and it's also easy to do badly. 🧵
Show more
Calling it now - someone will launch the Middle Power Open Weights Alliance. MPOWA is too good an acronym to waste.
The AI Office has endorsed parts of the AEF-1 standard relating to the independence provisions of the GPAI Code of Practice. Great work from @aievalforum !
This is a first, and (we think) is super important.
Confidentiality concerns wrt both proprietary models and sensitive benchmarks are legitimate. Having the ability to run both in secure enclaves gives privacy guarantees which are stronger than contractual obligations, and will hopefully create greater opportunities for external evaluations and subsequently safer AI.
A pleasure working with @GoogleDeepMind @openminedorg and @MLCommons on this.
Show more
