Finding Security Bugs in OSS with LLMs on a Budget
Nicholas Carlini discussed a method for automating the search for security vulnerabilities in code repositories using language models. He proposed a costly brute-force approach that, while effective, is not feasible for most open-source projects. An alternative, heuristic-based method was tested on the Umbraco-CMS project, yielding significant results at a fraction of the cost.
- ▪Nicholas Carlini presented a technique for finding security vulnerabilities using Anthropic's Claude models.
- ▪His brute-force method could cost around $40,000 for a large codebase like the Linux Kernel.
- ▪A heuristic-based approach was tested on Umbraco-CMS, costing less than $20 and identifying 20 potential vulnerabilities.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Etive-mor |
| Canonical URL | https://www.etive-mor.com/blog/carlini-style-vulnerability-hunting-on-a-budget/ |
| Publication time | Mon, 25 May 2026 08:14:04 +0000 |
| Retrieval time | 2026-05-25T08:37:36.531Z |
| Last seen | 2026-05-25T08:37:36.531Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | GCwN488IX--N |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Carlini-style software vulnerability hunting, on a budget Finding Security Bugs in Umbraco-CMS with LLMs for 1% of the Cost Nicholas Carlini did a talk a few weeks ago at [un]prompted 2026. In it, he describes how Anthropic have been using their Claude 4.5 & 4.6 series models to automate searching for security issues in repositories. He’s had some success, and managed to get a few new CVEs to his name with the technique. While novel, Carlini’s approach, as described, is an expensive way to search for bugs. I think that using a heuristics based approach to pre-search the codebase for interesting files before hunting, we can reduce the cost of his technique by 99% or more, while retaining most of the benefits.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Etive-mor.