Top New Best Ask Show Jobs

behat

134 karma · joined February 27, 2023

building tuneloop.io

submissions comments

How many tasks does it take to trust a cheaper model?

tuneloop.io·1 pts·behat·

A look at coding agent benchmarks, and what may be interesting next

tuneloop.io·3 pts·behat·

What would it take to match model intelligence to the task?

tuneloop.io·1 pts·behat·

Benchmarking – Frontier models go out of their way to cheat

tuneloop.io·2 pts·behat·

Show HN: Tuneloop – a local CLI for analyzing coding agent session transcripts

github.com·5 pts·behat·

Launch HN: Relvy (YC F24) – On-call runbooks, automated

relvy.ai·48 pts·behat·

Ramp: How we made Ramp sheets self-maintaining

twitter.com·3 pts·behat·

LLM Costs of AI investigating production alerts

relvy.ai·6 pts·behat·

OpenRCA benchmark – Improving Claude's root cause analysis accuracy by 12 pp

relvy.ai·12 pts·behat·

Can AI debug problem scenarios in the OpenTelemetry demo application?

relvy.ai·2 pts·behat·

How GitHub Copilot is getting better at understanding your code

github.blog·24 pts·behat·

Tech stack for fine-tuning LLMs

25 pts·behat·

Show HN: A macOS app that suggests fixes to error messages on screen

getessential.app·4 pts·behat·