… For some models, dropping prior thinking on turns without tool calls is an established behavior and part of the model’s fine-tuning DeepSeek-R1 is the clearest example . But that same behavior is wrong for interleaved agentic turns, where the prior reasoning explains the tool sequence. …
… This looks to be the common theme across tasks from a look at the company’s data, with agentic coding seeing an increase in power because of that better reasoning. …
… An inability to stem horrendous hallucinations and outright bad behavior might set the timeline to never. The lack of sufficient tools to check an agent’s work will continue to be an impediment. But if a widespread rollout does take place, agents could put plenty of human beings out of a job. …
… Those are then evaluated relative to each other in a “tournament,” the results of which are evaluated by a Reflection agent. An Evolution agent can then make improvements to any surviving ideas, which can be sent back through the process. …
… Having a bunch of AI agents write a bunch of software seems to be a real market for these tools. …
… Having an AI software stack means being able to deploy AI agents into that data to better organize it — with fewer concerns about leakage than there would be with general-purpose third-party LLMs. “Training AI models on public data is the largest, fastest-growing business in history,” Ellison said … …
… "OpenAI unveils AgentKit that lets developers drag and drop to build AI agents" . …