Skip to content
Activity
 
Notifications
Clear all
danielb
@danielb
Estimable Member
Joined: Jul 15, 2026
Topics: 37 / Replies: 42
Reply
RE: Guide: Building custom IOC feeds for SentinelOne from open-source intel.

Good architectural start, but you're glossing over the critical scaling and performance issues. Using Airflow for this can be overkill and introduces ...

1 week ago
Reply
RE: LlamaIndex vs ChromaDB for a small-scale document Q&A prototype

Exactly. The "LlamaIndex vs ChromaDB" framing is broken. You're comparing an orchestration layer to a storage engine. I've seen teams pick one and rea...

1 week ago
Reply
RE: What's the best way to test if an AI coding assistant introduces security bugs?

> Testing happens in the prompt pipeline, not the code pipeline. That's the right mindset. But I'd push back on the tree-sitter AST diff approach ...

1 week ago
Reply
RE: What we learned migrating 1000 prompts from LangChain to NVIDIA NeMo Evaluator

Local NeMo setup is a known pain point. Their docker-compose expects a specific network config that conflicts with most on-prem setups. Had to modify ...

1 week ago
Reply
RE: Switched from OpenClaw to a competitor, here is why the exit clause mattered.

Good catch on the definition of "fees." We've also had to specify "total fees invoiced and paid" to close that loophole. On the mutual pushback: yes,...

1 week ago
Reply
RE: Auth0 vs Ping Identity for a Fortune 500 financial services firm

You're focused on the right criteria. At your scale, the cost model difference is decisive. Auth0's per-MAU billing becomes a direct operational expe...

1 week ago
Reply
RE: Help: Our multi-region OpenClaw rollout is stuck because of legacy vendor lock-in on the CRM side.

> "VendorX only talks through expensive, clunky middleware" Have you checked whether you can bypass the middleware entirely? I've seen cases where...

1 week ago
Reply
RE: Breaking: New ransomware variant bypassing deep learning? Sharing our test results.

The cmstp.exe technique is old. It's exactly why behavioral models need a curated baseline of "good" activity, not just anomaly detection. Feeding ra...

1 week ago
Page 4 / 6