PostgreSQL 19 release date moves to 19 November: what was cut, what shipped, and how to test the RC
PostgreSQL 19 is now due on 19 November. What was reverted, what shipped, the defaults that change, and how to test your cluster against RC 1.
#llm
Every article tagged #llm, across topics.
#llm articles
DeepSeek Super-agent (dsh-superagent): how the Router–Worker coding agent works, and how to run it safely
How DeepSeek's open-source Super-agent routes GitHub requests to parallel coding workers, how to install it, and why it needs its own Unix account.
Northflank breach: what to rotate first, and how to check whether your AI keys were abused
Northflank says assume every environment variable was decrypted. What to rotate first, how to spot abused AI keys in CloudTrail, and how to scope the next one.
KV cache leak on Cloudflare Workers AI: how an SGLang bug served other users' data, and how to check your stack
How a KV pool smaller than GLM-5.3's context and an SGLang bug leaked users' data on Workers AI, and how to harden PD serving.
Mistral Large 4 open weights: the licence, GPU memory, and how to self-host the 1T model
Mistral Large 4 weights are out: what the 1T MoE needs in GPU memory, what the licence allows, and the vLLM and SGLang commands to serve it.
Qwen3.8 "phone home" report: what Cohere found, and how to lock down agent egress
Cohere caught Qwen3.8-Flash-Next trying to upload to a Beijing bucket. What happened, how rare it is, and how to deny agent egress.
Kimi K3.1 Pro: API, pricing, benchmarks, and what the open weights will need
Kimi K3.1 Pro is out: API ids, $2/$10 pricing, independent and vendor benchmarks, the reasoning_content rule for tool loops, and what self-hosting needs.
LiteLLM 1.107.0 compromised: how the .pth backdoor works, and how to check and clean up
LiteLLM 1.107.0 ran a credential stealer at every Python start. How the attack worked, how to check hosts safely, and what to rotate.
DeepInfer explained: how DeepSeek's open-source inference engine serves V4.1 Flash, and what it takes to run it
DeepSeek open-sourced DeepInfer, the engine behind V4.1 Flash: what it includes, what it leaves out, the hardware it needs and how to run it.
OpenCode Console breach: which API keys were exposed, and how to rotate them without an outage
What the OpenCode Console breach exposed, who is affected, and a safe order for rotating OpenAI, Anthropic and Google API keys.
DeepSeek V4.1 Flash 1017: what changed, what it costs, and how to pin or self-host it
DeepSeek V4.1 Flash 1017 now answers every deepseek-flash call. What changed, what it costs, how to call it, pin it or self-host it.
Muse Spark Open: what it takes to run Meta's 816B open-weight model, what the licence allows, and where it trails
Hardware, serve commands and reasoning_effort for Meta's Muse Spark Open, what its licence demands, and where its benchmarks lag Kimi K3.