I Tried to Make AI Writing Sound Human by Banning AI Words Through logit_bias
I tried to make AI writing sound more human with logit_bias, an API setting that changes how likely a model is to select specific…
Beitrag lesenBlog
Ich schreibe über Software, KI-gestützte Entwicklung, Laravel, SaaS, SEO, Tooling und alles, was sichtbar wird, wenn Software im Alltag genutzt wird. Meist technisch, aber nicht auf ein Thema beschränkt.
Die neuesten Beiträge aus dem Blog.
A research agent can leak a private document without uploading it. It can read a detail, turn it into a web search, and send…
Beitrag lesenOn July 22, 2026, Qualys disclosed CVE-2026-64600, a race condition in XFS, a Linux filesystem. The flaw is in XFS's copy-on-write path, where the…
Beitrag lesenGoogle’s Managed Agents, now in Public Preview, can give a Gemini agent a Google-hosted Linux sandbox. Google documents the default Antigravity agent as able…
Beitrag lesenOn July 20, 2026, OpenAI described an incident in which an unnamed internal model found many stuck find processes and every shell command hanging.…
Beitrag lesenOn July 20, 2026, OpenAI described an internal incident involving an unnamed model for long-running tasks. It saw that other systems had successful private…
Beitrag lesenI've built a lot of software, both my own side projects and client work as a freelancer. AI tools have made me much faster.…
Beitrag lesenDirekt zu den Bereichen, über die ich öfter schreibe.
Alle Themen im Blog.
Aktuelle Beiträge aus den Themen, über die ich öfter schreibe.
Alle Beiträge im Blog, neue zuerst.
I tried to make AI writing sound more human with logit_bias, an API setting that changes how likely a model is to select specific…
Beitrag lesenA research agent can leak a private document without uploading it. It can read a detail, turn it into a web search, and send…
Beitrag lesenOn July 22, 2026, Qualys disclosed CVE-2026-64600, a race condition in XFS, a Linux filesystem. The flaw is in XFS's copy-on-write path, where the…
Beitrag lesenGoogle’s Managed Agents, now in Public Preview, can give a Gemini agent a Google-hosted Linux sandbox. Google documents the default Antigravity agent as able…
Beitrag lesenOn July 20, 2026, OpenAI described an incident in which an unnamed internal model found many stuck find processes and every shell command hanging.…
Beitrag lesenOn July 20, 2026, OpenAI described an internal incident involving an unnamed model for long-running tasks. It saw that other systems had successful private…
Beitrag lesenI've built a lot of software, both my own side projects and client work as a freelancer. AI tools have made me much faster.…
Beitrag lesenIncident response is the work of reconstructing and containing a breach after it happens. Hosted AI models can act as an elastic analysis layer…
Beitrag lesenSSH access is often wider than a security policy intends. Tailscale SSH manages authentication and authorization for connections over a private Tailscale network. Its…
Beitrag lesenOn July 20, 2026, OpenAI said an unnamed internal model spent an hour finding a vulnerability in its sandbox so it could open a…
Beitrag lesenSecurity scanners already produce more credible-looking alerts than most teams can afford to investigate. On July 16, 2026, Capital One released VulnHunter, an open-source…
Beitrag lesenGoogle has put a hard expiry date on its Custom Search JSON API. It’s the server-side service behind applications that send a query to…
Beitrag lesen