@yebuseth No. TheAgentCompany has no official account.

@0xRiver8 @YufanSong98 @TomerLevinboim @gneubig @frankxu2004 @_AgentCompany That account is NOT an official account of TheAgentCompany.

@YufanSong98 @TomerLevinboim @gneubig @frankxu2004 Caveat: OpenHands’ system prompts for LLMs that support function calling and those that don’t, are, as one could imagine, different.

@TomerLevinboim @YufanSong98 @gneubig @frankxu2004 OpenHands’ system prompt might have been engineered for Claude unintentionally, since it was the primary LLM developers of OpenHands used for dev and benchmarking.

@TomerLevinboim @YufanSong98 @gneubig @frankxu2004 The prompt we used was an one liner:

@TomerLevinboim @YufanSong98 @gneubig @frankxu2004 For example, all LLMs had trouble closing the popup window on ownCloud. Claude (and maybe others), sometimes could figure out that using “escape” keystroke would close the popup. If we add this trick to the system prompt I believe the score would be boosted.

@TomerLevinboim @YufanSong98 @gneubig @frankxu2004 During our evaluation, we didn’t add any specific prompts that could potentially boost the score. I believe the score could be boosted if you inspect all the failed trajectories and add specific prompts to work around common errors.

RT @gneubig: How far are we from having competent AI co-workers that can perform tasks as varied as software development, project managemen…

Just deployed latest JanusGraph to looking great! #Graph #graphdatabase #DataAnalytics

RT @JanusGraph: The JanusGraph Technical Steering Committee is excited to announce the release of JanusGraph 1.0.0 🎉 The release artifacts…

Check out how to use Spark to calculate PageRanks for massive citation networks using JanusGraph (or any other TinkerPop-enabled graph database): #PageRank #Spark #TinkerPop #JanusGraph

RT @JanusGraph: JanusGraph 0.6.4 has been released recently. This is a maintenance release that includes a lot of dependency updates, but a…