AIQB
PerspectivesOrdinary

why are models bad at harness engineering！？

Source: X：Dex Horthy（HumanLayer）(@dexhorthy)·

Summary

This record preserves its title, category and source. Open the original source for full details.
CategoryAI Perspectives & Methods
TierOrdinary
Published
Indexed by AIQB
SourceX：Dex Horthy（HumanLayer）(@dexhorthy)
AIQB record IDintel-2e63c76d54bff3d4491b91fb
Read original source ↗More Perspectives

Related stories

Matched by category, entity tags and source

PerspectivesOrdinary
Milestone - /show-me has over 11k installs and 2.5k github stars！
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesOrdinary
many are asking - what's your take？
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesOrdinary
SlopCodeBench Update： Fable 5.1 Medium - 11% - I think we need to re-run this at higher effort G…
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesOrdinary
thats…promising. also crazy that SOL xhigh was cheaper and WAYYY better than SOL medium
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesOrdinary
SlopCodeBench Update - Astra has entered the chat
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesOrdinary
kicking off the biggest SlopCodeBench run to date tonight - we're testing the FULL benchmark on Fabl…
Source: X：Dex Horthy（HumanLayer）(@dexhorthy)
PerspectivesSelected
Sir Demis Hassabis vs Sir Demis Hassabis
Source: Gary Marcus：The Road to AI We Can Trust（RSS）
PerspectivesSelected
i'm joining forces with @ylecun and an incredible group of people to start AMI Labs @amilabs. AMI …
我与 @ylecun 和一群杰出人士联手创立 AMI Labs @amilabs。
Source: X：谢赛宁 (@sainingxie)
PerspectivesOrdinary
Say an AI remembers that you prefer short emails. Useful when you ask it to draft a reply. Now say …
Source: X：Rohan Paul (@rohanpaul_ai)
PerspectivesOrdinary
Agree with @JensenHuang： we're entering the AGI era. The AGI era must also be the alignment era. We…
Source: X：Mark Chen（OpenAI 首席研究官，@markchen90） · OpenAI