Fer 🇦🇺🧉
10.8K posts

Fer 🇦🇺🧉
@ferparra
Growth, Data, Product 🚀 Formerly @pollenizer EstimateOne @Accenture @Microstrategy; @ITBA alumni.

We’re introducing HALO 😇 Hierarchal Agent Loop Optimizer HALO is an RLM-based agent optimization technique capable of recursively self-improving agents by analyzing their execution traces and suggesting changes. This work is inspired by the Mismanaged Genius Hypothesis proposed by @a1zhang and @lateinteraction earlier this month. tldr; we improved performance on AppWorld (Sonnet 4.6) from 73.7 --> 89.5 (+15.8) by giving HALO-RLM access to harness trace data and asking it to identify issues. The feedback from HALO surfaced failures in the harness such as hallucinated tool calls, redundant arguments in tools, refusal loops, and semantic correctness issues. Each issue mapped cleanly to a direct prompt update. We then fed these finding into Cursor (Opus 4.6), and asked the coding agent to update the underlying harness. We repeated this trace -> HALO-RLM analysis -> code update loop until the score plateaued. Today we’re open-sourcing the core HALO-RLM framework, evals, and data for further review.



JUST IN: Microsoft commits to A$25,000,000,000.00 investment in Australia to build AI infrastructure & train workers.


TREN FRIENDS. The one about the pump. Ok, this one goes out to my coach and all the gym-bros who hit the church of iron at 7 AM. 💪 via Ai-NDREY Can we make a whole actual episode of this pls? 🤣






Waiting for the EU and China to get in on the blockade action



















