behat's submissions | Hacker News

1.		A look at coding agent benchmarks, and what may be interesting next (tuneloop.io)
		3 points by behat 11 days ago \| past \| discuss
2.		What would it take to match model intelligence to the task? (tuneloop.io)
		1 point by behat 13 days ago \| past \| discuss
3.		Benchmarking – Frontier models go out of their way to cheat (tuneloop.io)
		2 points by behat 17 days ago \| past
4.		Show HN: Tuneloop – a local CLI for analyzing coding agent session transcripts (github.com/tuneloop)
		5 points by behat 46 days ago \| past
5.		Launch HN: Relvy (YC F24) – On-call runbooks, automated (relvy.ai)
		48 points by behat 5 months ago \| past \| 25 comments
6.		Ramp: How we made Ramp sheets self-maintaining (twitter.com/ramplabs)
		3 points by behat 5 months ago \| past
7.		LLM Costs of AI investigating production alerts (relvy.ai)
		6 points by behat 6 months ago \| past \| 1 comment
8.		OpenRCA benchmark – Improving Claude's root cause analysis accuracy by 12 pp (relvy.ai)
		12 points by behat 6 months ago \| past
9.		Can AI debug problem scenarios in the OpenTelemetry demo application? (relvy.ai)
		2 points by behat on April 30, 2025 \| past
10.		How GitHub Copilot is getting better at understanding your code (github.blog)
		24 points by behat on May 23, 2023 \| past
11.		Tech stack for fine-tuning LLMs
		25 points by behat on May 17, 2023 \| past \| 4 comments
12.		Show HN: A macOS app that suggests fixes to error messages on screen (getessential.app)
		4 points by behat on May 7, 2023 \| past