Even (very) noisy LLM evaluators are useful for improving AI agentstensorzero.com·35 pts·GabrielBianconi·10
Sporks of AGI: why the Real Thing is better than the Next Best Thingsergeylevine.substack.com·3 pts·GabrielBianconi·0
We raised $7.3M to build an open-source stack for industrial-grade LLM appstensorzero.com·1 pts·GabrielBianconi·0
Fine-tuned small LLMs can beat large ones with programmatic data curationtensorzero.com·53 pts·GabrielBianconi·11
<syntax-highlight>: custom element that uses the CSS Custom Highlight APIandreruffert.github.io·2 pts·GabrielBianconi·0
From NER to Agents: Does Automated Prompt Engineering Scale to Complex Tasks?tensorzero.com·1 pts·GabrielBianconi·0
Can reinforcement learning for LLMs scale beyond math and coding tasks? Probablyarxiv.org·6 pts·GabrielBianconi·4
Case Study: Automating Code Changelogs at a Large Bank with LLMstensorzero.com·1 pts·GabrielBianconi·0
Show HN: TensorZero – open-source data and learning flywheel for LLMsgithub.com·49 pts·GabrielBianconi·2