lebovic's submissions

1.		How do frontier AI agents perform in multi-step cyber-attack scenarios? (aisi.gov.uk)
		3 points by lebovic 15 days ago \| past
2.		Hacking Claude Code remote: escaping YOLO-mode sandboxing (noahlebovic.com)
		4 points by lebovic 35 days ago \| past
3.		Evaluating and mitigating the growing risk of LLM-discovered 0-days (anthropic.com)
		62 points by lebovic 55 days ago \| past \| 18 comments
4.		Show HN: An agent sandboxing quickstart based on Claude Code (github.com/lebovic)
		2 points by lebovic 68 days ago \| past
5.		Delay-Line Memory (wikipedia.org)
		2 points by lebovic 3 months ago \| past \| 1 comment
6.		Claude Advanced Tool Use (anthropic.com)
		673 points by lebovic 4 months ago \| past \| 266 comments
7.		Fixing a Milli-q purifier for 99% off (bsiranosian.com)
		4 points by lebovic 6 months ago \| past
8.		Infrastructure from mining makes sense for scientific computing (noahlebovic.com)
		5 points by lebovic on May 12, 2023 \| past
9.		Barnstorming (wikipedia.org)
		1 point by lebovic on Feb 14, 2023 \| past
10.		Show HN: Swap between local and cloud execution with a Python decorator (github.com/trytoolchest)
		4 points by lebovic on Feb 3, 2023 \| past \| 1 comment
11.		AWS has a low elasticity ceiling for big servers (noahlebovic.com)
		15 points by lebovic on Dec 9, 2022 \| past \| 7 comments
12.		AWS doesn't make sense for scientific computing (noahlebovic.com)
		295 points by lebovic on Oct 7, 2022 \| past \| 270 comments
13.		Show HN: Lug – run Python locally or in the cloud, paired with a container (lug.dev)
		5 points by lebovic on Sept 8, 2022 \| past \| 1 comment
14.		Show HN: An API for running computationally intensive tools (trytoolchest.com)
		6 points by lebovic on June 9, 2021 \| past \| 3 comments