3. A recent experience with ChatGPT 5.5 Pro (gowers.wordpress.com)

We are all having to keep revising upwards our assessments of the mathematical capabilities of large language models. I have just made a fairly large revision as a result of ChatGPT 5.5 Pro, to whi…

8. LLMs Corrupt Your Documents When You Delegate (arxiv.org)

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT 5.4) corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction.

10. The Intolerable Hypocrisy of Cyberlibertarianism (matduggan.com)

I like the Internet. I am old enough to remember the pre-Internet era and despite the younger generations pining for those simpler days, I was there. Paper maps were absolutely horrible, just you and a compass in your car on the side of the road in the middle of the

19. Rust but Lisp (github.com)

Rust but LISP. Contribute to ThatXliner/rust-but-lisp development by creating an account on GitHub.

25. CPanel's Black Week: 3 New Vulnerabilities Patched After Attack on 44k Servers (www.copahost.com)

If you run a server with cPanel or WHM, you need to read this carefully. On May 8, 2026 β€” just ten days after the cPanel CVE-2026-41940 authentication bypass was used to compromise 44,000 web hosting servers and deploy ransomware β€” cPanel quietly released a second emergency security patch. This one covers three new vulnerabilities: […]

30. Can LLMs model real-world systems in TLA+? (www.sigops.org)

Editors’ note: AI has been actively pushing the frontier of applied formal methods for computing systems. In this article, the Specula team wrote about their experience of evaluating LLMs on modeling system code, the basic capability for agentic model checking, using TLA+, a specification language f

Article Details

Browse by Date

Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open