Home Speakers Chip Huyen Quote Compound mistakes: an agent often needs to perform multiple steps to accomplish a task, and the overall accuracy decreases as the number of steps increases. If the model’s accuracy is 95% per step, over 10 steps, the accuracy will drop to 60%, and over 100 steps, the accuracy will be only 0.6%.
Words found on the source page on Nov 6, 2026.
More from Chip Huyen Blog Common pitfalls when building generative AI applications Jan 16, 2025
The teams with the best products I’ve seen all have human evaluation to supplement their automated evaluation. Blog Common pitfalls when building generative AI applications Jan 16, 2025
These annotation guidelines can help improve the model’s instructions (if a human has a hard time following the instructions, the model will, too). Blog Agents Jan 7, 2025
A common complaint is that agents are only good for burning through your API credits. However, if agents can be autonomous, they can save human time, making their costs worthwhile. Blog Agents Jan 7, 2025
Higher stakes: with access to tools, agents are capable of performing more impactful tasks, but any failure could have more severe consequences.
On the same topics Blog Will agents have network effects? Oct 6, 2026
If the content creation loop works for agentic virality, I think it means there’s a big incentive for every agent to volunteer to make visually-appealing, shareable content, do this often. Blog Thinking in Systems, Shipping in Loops Sep 24, 2026
This is the new software engineering: designing the systems that let AI write code correctly at scale. Talk Speech at the UN Security Council Sep 23, 2026
I address you today at a moment of global awakening: in recent months, AI agents developed by leading companies have acted in unacceptably dangerous ways, against instructions. Blog Frontier Overhangs Sep 21, 2026
Once you have put all of your information into a personal agent and actually incorporated it into your day-to-day life, it is much more of a challenge to change to something else. Blog Frontier Overhangs Sep 21, 2026
Truly effective defense will mean truly trusting agents to act autonomously, but most companies won’t do that until they are forced to by regular and unremitting hacks by fully autonomous attackers. Blog Frontier Overhangs Sep 21, 2026
What this means is that model performance isn’t the only thing that matters: the integration between model and harness is where true agent differentiation is found. About this quote 
Quotesby Glyph