From hallucinations to {hardware}: Classes from a real-world laptop imaginative and prescient venture gone sideways

Laptop imaginative and prescient initiatives not often go precisely as deliberate, and this one was no exception. The concept was easy: Construct a mannequin that might have a look at a photograph of a laptop computer and establish any bodily injury — issues like cracked screens, lacking keys or damaged hinges. It appeared like a simple use case for picture fashions and enormous language fashions (LLMs), nevertheless it shortly became one thing extra sophisticated.

Alongside the best way, we bumped into points with hallucinations, unreliable outputs and pictures that weren’t even laptops. To unravel these, we ended up making use of an agentic framework in an atypical means — not for activity automation, however to enhance the mannequin’s efficiency.

On this publish, we are going to stroll by way of what we tried, what didn’t work and the way a mixture of approaches finally helped us construct one thing dependable.

The place we began: Monolithic prompting

Our preliminary method was pretty normal for a multimodal mannequin. We used a single, giant immediate to cross a picture into an image-capable LLM and requested it to establish seen injury. This monolithic prompting technique is straightforward to implement and works decently for clear, well-defined duties. However real-world information not often performs alongside.

We bumped into three main points early on:

• Hallucinations: The mannequin would typically invent injury that didn’t exist or mislabel what it was seeing.
• Junk picture detection: It had no dependable method to flag pictures that weren’t even laptops, like footage of desks, partitions or individuals sometimes slipped by way of and obtained nonsensical injury stories.
• Inconsistent accuracy: The mix of those issues made the mannequin too unreliable for operational use.

This was the purpose when it grew to become clear we would want to iterate.

First repair: Mixing picture resolutions

One factor we observed was how a lot picture high quality affected the mannequin’s output. Customers uploaded every kind of pictures starting from sharp and high-resolution to blurry. This led us to discuss with analysis highlighting how picture decision impacts deep studying fashions.

We skilled and examined the mannequin utilizing a mixture of high-and low-resolution pictures. The concept was to make the mannequin extra resilient to the wide selection of picture qualities it will encounter in apply. This helped enhance consistency, however the core problems with hallucination and junk picture dealing with endured.

The multimodal detour: Textual content-only LLM goes multimodal

Inspired by latest experiments in combining picture captioning with text-only LLMs — just like the method lined in The Batch, the place captions are generated from pictures after which interpreted by a language mannequin, we determined to present it a strive.

Right here’s the way it works:

• The LLM begins by producing a number of attainable captions for a picture. 
• One other mannequin, referred to as a multimodal embedding mannequin, checks how effectively every caption suits the picture. On this case, we used SigLIP to attain the similarity between the picture and the textual content.
• The system retains the highest few captions primarily based on these scores.
• The LLM makes use of these high captions to put in writing new ones, attempting to get nearer to what the picture really exhibits.
• It repeats this course of till the captions cease enhancing, or it hits a set restrict.

Whereas intelligent in principle, this method launched new issues for our use case:

• Persistent hallucinations: The captions themselves typically included imaginary injury, which the LLM then confidently reported.
• Incomplete protection: Even with a number of captions, some points had been missed fully.
• Elevated complexity, little profit: The added steps made the system extra sophisticated with out reliably outperforming the earlier setup.

It was an attention-grabbing experiment, however finally not an answer.

A artistic use of agentic frameworks

This was the turning level. Whereas agentic frameworks are often used for orchestrating activity flows (assume brokers coordinating calendar invitations or customer support actions), we puzzled if breaking down the picture interpretation activity into smaller, specialised brokers would possibly assist.

We constructed an agentic framework structured like this:

• Orchestrator agent: It checked the picture and recognized which laptop computer elements had been seen (display screen, keyboard, chassis, ports).
• Part brokers: Devoted brokers inspected every part for particular injury varieties; for instance, one for cracked screens, one other for lacking keys.
• Junk detection agent: A separate agent flagged whether or not the picture was even a laptop computer within the first place.

This modular, task-driven method produced rather more exact and explainable outcomes. Hallucinations dropped dramatically, junk pictures had been reliably flagged and every agent’s activity was easy and targeted sufficient to manage high quality effectively.

The blind spots: Commerce-offs of an agentic method

As efficient as this was, it was not excellent. Two fundamental limitations confirmed up:

• Elevated latency: Operating a number of sequential brokers added to the full inference time.
• Protection gaps: Brokers might solely detect points they had been explicitly programmed to search for. If a picture confirmed one thing surprising that no agent was tasked with figuring out, it will go unnoticed.

We wanted a method to stability precision with protection.

The hybrid answer: Combining agentic and monolithic approaches

To bridge the gaps, we created a hybrid system:

1. The agentic framework ran first, dealing with exact detection of recognized injury varieties and junk pictures. We restricted the variety of brokers to essentially the most important ones to enhance latency.
2. Then, a monolithic picture LLM immediate scanned the picture for anything the brokers may need missed.
3. Lastly, we fine-tuned the mannequin utilizing a curated set of pictures for high-priority use instances, like ceaselessly reported injury situations, to additional enhance accuracy and reliability.

This mixture gave us the precision and explainability of the agentic setup, the broad protection of monolithic prompting and the arrogance increase of focused fine-tuning.

What we realized

A number of issues grew to become clear by the point we wrapped up this venture:

• Agentic frameworks are extra versatile than they get credit score for: Whereas they’re often related to workflow administration, we discovered they might meaningfully increase mannequin efficiency when utilized in a structured, modular means.
• Mixing totally different approaches beats counting on only one: The mix of exact, agent-based detection alongside the broad protection of LLMs, plus a little bit of fine-tuning the place it mattered most, gave us much more dependable outcomes than any single technique by itself.
• Visible fashions are vulnerable to hallucinations: Even the extra superior setups can bounce to conclusions or see issues that aren’t there. It takes a considerate system design to maintain these errors in test.
• Picture high quality selection makes a distinction: Coaching and testing with each clear, high-resolution pictures and on a regular basis, lower-quality ones helped the mannequin keep resilient when confronted with unpredictable, real-world photographs.
• You want a method to catch junk pictures: A devoted test for junk or unrelated footage was one of many easiest adjustments we made, and it had an outsized affect on general system reliability.

Last ideas

What began as a easy concept, utilizing an LLM immediate to detect bodily injury in laptop computer pictures, shortly became a a lot deeper experiment in combining totally different AI methods to deal with unpredictable, real-world issues. Alongside the best way, we realized that a few of the most helpful instruments had been ones not initially designed for this kind of work.

Agentic frameworks, typically seen as workflow utilities, proved surprisingly efficient when repurposed for duties like structured injury detection and picture filtering. With a little bit of creativity, they helped us construct a system that was not simply extra correct, however simpler to know and handle in apply.

Shruti Tiwari is an AI product supervisor at Dell Applied sciences.

Vadiraj Kulkarni is a knowledge scientist at Dell Applied sciences.