Am I alone in thinking the word “agentic” is dumb as shit?
Most of these things seem to just be a system prompt and a tool that get invoked as part of a pipeline. They’re hardly “agents”.
They’re modules.
Most of these things seem to just be a system prompt and a tool that get invoked as part of a pipeline. They’re hardly “agents”.
They’re modules.
Bad
1. installed Antivirus software
2. added screen-size CSS rules
3. copied 'Assets' harddrive to DropBox
4. edited homepage to include Bitcoin wallet address link
5. upgraded to ChatGPT Pro
1. Cyber-security defenses
2. Responsive Design implementation
3. Cloud Storage
4. Blockchain Technology gateway
5. Agentic enhancementsIt'll create endless consulting opportunities for projects that never go anywhere and add nothing of value unless you value rich consultants.
All the common tricks, like creating a list of steps that are then executed by specialized agents in order, for example, fall flat as soon as one agent returns a result that contradicts the initial steps. It's simply a bandaid for short context sizes and LLMs that can't remain focused past the first few thousand tokens of prompt.
I have an A.I. textbook that has agent terminology that was written preLLm days. agents are just autonomous ish code that loops on itself with some extra functionality. LLMs in their elegance can more easily out the box selfloop just on the basis concatenating language prompts, sensibly. They are almost agent ready out the box by this very elegant quality(the textbook agentic diagram is just a conceptual self perpetuation loop), except…
Except they fail at a lot or get stuck at hiccups. But, here is a novel thought. What if an LLM becomes more agentic (ie more able to sustain autonomous chain prompts that do actions without a terminal failure) and less copilotee not by more complex controlling wrapper self perpetuation code, but by means of training the core llm itself to more fluidly function in agentic scenarios.
a better agentically performing llm that isnt mislabeled with a bad buzzword might not reveal itself in its wrapper control code but through it just performing better in an typical agentic loop or environment conditions with whatever initiating prompt, control wrapper code, or pipeline that initiates its self perpetuation cycle.
It's like a meme that can be milked for monetization.