Subscribe

Search

Results for “AI inference”

22 stories found

Security

Cursor's breach post-mortem: a key leaked at Fireworks led to old agent traces, stolen credentials and a fake Claude Code extension

Cursor says the October 29 poisoning of its extension marketplace started with an access key exposed at its inference vendor Fireworks, which let an attacker copy 2025 coding-agent traces that held unredacted credentials. Anyone who installed Claude Code 2.1.312 or 2.1.313 from Cursor's marketplace, or got a notice from Cursor, still has work to do.

· 4 min read

Security

Fireworks AI's breach widens: billing data, some datasets and unfinished model weights taken. What customers should do

Fireworks AI now says a second intrusion on October 24, through a cloud provider hosting its R&D machines, reached billing records for customers and, for some accounts, secrets, datasets and incomplete model weights. Its inference service shows no impact, but anyone who trained or evaluated models there should check their notice and rotate keys.

· 6 min read

Repos

Microsoft's ONNX Runtime repo went 404 on GitHub and broke CI builds. PyPI and NuGet still work: what to do

Since about 22:20 UTC on November 17, github.com/microsoft/onnxruntime and its release downloads have returned 404, breaking builds that fetch the inference engine from GitHub. Microsoft hasn't explained the ONNX outage, but told The Register it made "some repositories private" while investigating malicious content. The PyPI and NuGet packages are unaffected. Switch downloads to them and pin hashes.

· 3 min read

Repos

llama.cpp and ggml hit v1.0.0: what the semantic-versioning promise covers, what was removed and who must check

After about three and a half years of fast-moving build tags and 0.x releases, the local-inference engine behind a large share of on-device AI tools now promises that breaking C API changes will only arrive with a major version bump. The 1.0 release also deletes a batch of deprecated functions, so anyone linking libllama directly should check their build before upgrading.

· 3 min read

Repos

Yogurt is a free, MIT-licensed Granola alternative that records and summarizes meetings entirely on your computer

Frigade's Yogurt records your mic and system audio without a meeting bot, transcribes with whisper.cpp and writes summaries with a local open-weight model through llama.cpp. It runs on Mac, Windows and Linux, needs no account and passed 950 GitHub stars within three days. Expect multi-gigabyte model downloads, and note that some features are Mac-only.

· 3 min read

AI

OpenAI says its models rewrote parts of AMD's flagship GPU for up to 14% PPA gains, and some went to the fab. What's proven

OpenAI said on November 18 that its models rewrote circuit code in AMD's flagship GPU design for up to 14% power-performance-area gains, and that some of those changes are in a design already sent for manufacturing. It's the first claim of OpenAI-written RTL shipping in an AMD part. But AMD hasn't named the chip, and every number so far comes from OpenAI.

· 1 min read