Chip Huyen quote, Jan 7, 2025

Author, AI Engineering · Jan 7, 2025 · Post, Agents

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%.

Primary source

Words found on the source page on Sep 25, 2026.

More from Chip Huyen

Date	Quote	Context	Source
Jan 16, 2025	The teams with the best products I’ve seen all have human evaluation to supplement their automated evaluation.Jan 16, 2025· Post	PostCommon pitfalls when building generative AI applications	Source
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).Jan 16, 2025· Post	PostCommon pitfalls when building generative AI applications	Source
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.Jan 7, 2025· Post	PostAgents	Source
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.Jan 7, 2025· Post	PostAgents	Source

Date	Quote	Context	Source
Sep 24, 2026	This is the new software engineering: designing the systems that let AI write code correctly at scale.Tomasz TunguzSep 24, 2026· Post	PostThinking in Systems, Shipping in Loops	Source
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.Yoshua BengioSep 23, 2026· Keynote	KeynoteSpeech at the UN Security Council	Source
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.Ben ThompsonSep 21, 2026· Post	PostFrontier Overhangs	Source
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.Ben ThompsonSep 21, 2026· Post	PostFrontier Overhangs	Source
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.Ben ThompsonSep 21, 2026· Post	PostFrontier Overhangs	Source
Sep 21, 2026	They also highlight the bifurcating economics of AI: state of the art models for discovery & optimized models for production. We use the largest frontier models to train new models, & the most capable models to architect systems. But once a system is engineered & hardened, running it thousands or millions of times through a workflow benefits from narrower AI.Tomasz TunguzSep 21, 2026· Post	PostAI Comes for the If Statement	Source

About this quote

Said by: Chip Huyen, Author, AI Engineering
Where: Agents
Topics: Agents
Source: huyenchip.com/2025/01/07/agents.html

A quote is one moment, not the whole argument. Read it in context at the source.

Sources: the primary source linked on each quote, checked weekly. A quote is one moment; read the source. Logos via logo.dev; trademarks belong to their owners.

More from Chip Huyen

On the same topics

New quotes by email