Running Autonomous Research Experiments with Agents
samsja19 · x · 2026-07-13
The post mentions that @eliebakouch is running experiments with Fable in a nearly automated fashion to investigate several questions about JLens.
These questions include:
- At what stage of training the structure forms
- Whether it can be transferred across different models
- How the patterns change with scale
- How far a "nudge" propagates
- What the K2 JLens looks like
This content serves as a case study of "agent-driven autonomous research" rather than a simple chat demonstration.
More from coding & agent
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- Morgan Stanley and US banks block third-party AI agents over credentials — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26
- 250 Builders Hack With Codex at Berlin Community Hackathon Ahead of OpenAI DevDay — paw_lean · 2026-10-26