News for hackers. Stuff that matters.

rinkash

Show HN: Tool to measure log TCO savings without losing or migrating any data

I work on Chiron. We provide a “lossless consolidation” solution for log savings on high-fidelity stores like Splunk, where you don’t lose any data, your query results stay intact, and you still meet your compliance needs. On a Palo Alto firewall log sample we published, the lossless merge came to about 40%. Method and numbers: https://medium.com/@chironvision_inc/keeping-palo-alto-logs-...We...

( Read More... | no comments | on HN )
Some of the benchmarks, like SREGym, are gaining popularity for evaluating the effectiveness of various agentic investigation tools. Vendor-promoted tools take most of the top spots, ahead of DIY systems based on generic frontier models. Vendors can improve their offerings through better models and better data quality. With Chiron providing the context data, we see a huge jump in model accuracy (46.2% compared with the paper’s 30.9% baseline) and about 9× fewer tokens on ORCA-bench. This suggests that DIY projects with the right context are a viable option.
Does the gateway give you token accounting you can trust across providers? You mention Groq putting usage in its own field, and that’s the kind of quirk that quietly breaks cost attribution. Once you’re routing across providers, cost per request is the number most teams actually want out of a gateway, and it’s only as good as the worst provider’s usage reporting.