When a Vision Model Turns Weeks into Months

The vision model changed weeks into months. A second prompt fixed a different duration, then repeated the unit error elsewhere in the same figure. Lowering temperature and asking for verbatim text had not made the transcription dependable.

We observed this in an October 2, 2026 spike on six figures from a licensed reference book used by a professional learning platform. The problem mattered because some facts appeared only inside images. A text-only retrieval pipeline could not find them. A generated image description could make them searchable while quietly changing the evidence.

Three passes over the same six figures

The first prompt asked for a description at temperature 0.2 using the original PDF image. It recovered much of the visible text, but it also invented visual detail and misread a duration. The second pass used temperature 0, enlarged the image to a 1568-pixel long edge and separated text transcription from a short structural description.

That revision improved several outputs. It recovered previously omitted lines and corrected one duration. In the difficult figure, however, a printed duration expressed in weeks became months. Labels were partly obscured by the illustration. Despite an instruction to mark unreadable text, the model supplied plausible wording instead.

The structural descriptions introduced their own errors. One pass reversed the orientation of a pyramid. Another described side-by-side blocks as vertically stacked. Exact words and a correct explanation of their arrangement were separate targets.

What changed across the recorded prompt passes

Pass	Output contract	Observed limitation
First	A general figure description.	A wrong duration and invented visual details.
Second	Visible text plus structure.	A corrected value alongside a new unit error. Some spatial descriptions remained wrong.
Third	TEXT, DESCRIPTION and MEANING, followed by a separate transcription call.	The numeric comparison flagged the difficult figure. Wording and spatial errors remained outside that check.

Give transcription and interpretation different fields

We made the third pass's output contract more explicit. TEXT held visible wording. DESCRIPTION described what was drawn and how it was arranged. MEANING interpreted the figure. In that spike, the instruction for MEANING prohibited introducing numbers outside TEXT.

This separation made an output easier to inspect. A reader could distinguish a copied label from a model's explanation. It did not turn the copied label into verified transcription, or the explanation into an assertion made by the source author.

A second call asked the same model to transcribe the original-sized image. We compared quantities and their units between the two readings. Treating the unit as part of the quantity was necessary: preserving a numeral while changing its time unit was precisely the failure we wanted to notice.

The disagreement detector flagged the only figure with the numeric error in that six-figure pass. It did not raise a numeric alarm on the other five. That was a useful observed result on a small selected set. It was not an estimate of general error-detection recall.

Two readings can agree on the same mistake

Both calls used the same model and the same underlying image. Their outputs were separate readings, with different instructions and image sizes. They were not independent models or independent expert judgments.

A disagreement created an inspection candidate. Agreement could still leave a shared mistake untouched. Numeric comparison also missed changes in terminology and arrangement. The recorded spike included an incorrect word that would require a lexical check, and a spatial error that would require understanding the diagram. Even normalization needs a boundary. A comparator can ignore typographic differences in a range while preserving its unit. It should not erase a meaningful distinction merely to increase agreement. The following is a fictional comparator example, not another measured output:

Illustrative quantity comparisons

Reading A	Reading B	Inspection decision
2-3 weeks	2 to 3 weeks	Equivalent formatting can normalize to the same quantity.
2-3 weeks	2-3 months	Preserve and flag the unit disagreement.
The top level	The bottom level	A numeric comparator has no verdict on this difference.

The larger book run changed what needed attention

In the October 3 live check, the corpus contained 22 figures. Two received attention flags. One was the duration figure, where obscured labels again produced conflicting readings. The other contained partly obscured lettering. The model had guessed words in its description. The recorded crop inspection confirmed both needed attention.

The remaining 20 were unflagged.

That count does not prove those figures were free of errors, because the flagger did not comprehensively evaluate their wording or geometry. Attention was a triage field, and review was optional by default. Flagged material could remain available to search.

Retrieval produced a separate result. Across ten figure questions, the intended figure appeared in the retrieved sources each time. Nine answers cited that figure. The remaining answer cited book prose containing the answer. Those observations showed that the added representations could participate in retrieval. They did not certify every generated description.

Keep the image at the end of the inspection path

The useful source card linked back to the original figure and its page. It also identified the description as model-written. That provenance matters when the representation is editable: correcting a generated description changes what retrieval sees, while the original image remains the evidence to inspect.

For a new deployment, we would evaluate numeric disagreements separately from omissions, terminology and spatial relationships. We would also measure the errors left unflagged, using human-labeled examples. The six-figure result cannot supply that missing denominator.

Our OCR table experiment reached a related boundary from another direction: correct characters could still support a wrong association. Here, the first necessary inspection was simpler. Open the image, locate the obscured label and compare the time unit with the searchable text.

Evidence: the six-figure spike of October 2 and 22-figure live check of October 3, 2026. The project and book are described anonymously. Licensed crops and raw model responses are not redistributed. The comparator table is an invented illustration. These engineering checks do not establish medical accuracy or mandatory human approval of all indexed material.

FAQ

Last updated: October 15, 2026

Quick answers to common questions about custom software development, pricing, process and technology.

Expand all Collapse all

Search FAQs

Type to filter questions and answers. Use Topic to narrow the list.

Showing all 14

• How long have you been in business?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production has been in business since 2013, with over 13 years of experience in custom software development. During this time, we have delivered over 110 applications for 200+ clients across 28 industries, including FinTech, healthcare, crypto and e-commerce. We are rated 5/5 on Clutch based on 107 verified reviews (2026).

• What services do you provide?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production provides six core service categories: AI Development (LLM applications, AI agents, machine learning and computer vision), Blockchain and Web3 (smart contracts, DeFi, tokenization on Ethereum, Solana, TON and other chains), FinTech Development (payment platforms, digital banking, KYC and AML integration), Software Development (mobile apps, web platforms, database design, UI/UX), Security and QA (code audits, penetration testing, smart contract audits, manual and automated testing) and Consulting (architecture design, MVP validation, startup consulting).

• Where is Pharos Production located?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production is headquartered in Las Vegas, Nevada, USA (5348 Vegas Dr, Las Vegas, NV 89108), with an engineering office in Kyiv, Ukraine (44-B Eugene Konovalets Str. Suite 201, Kyiv 01133). We work with clients worldwide and provide remote collaboration across all time zones. Visit our contact page for directions and scheduling options.

• How big is your team?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production has a team of 90+ engineers, including software developers, blockchain specialists, QA engineers, DevOps experts, UI/UX designers, project managers and solution architects. Our founder, Dr. Dmytro Nasyrov, holds a PhD in Artificial Intelligence and leads the technical direction of all projects.

• What types of customers do you serve?

  Copy link Copies a direct link to this answer to your clipboard.

  We serve a wide range of clients, from startups and product companies to mid-sized enterprises and large institutions. Our clients include crypto exchanges, FinTech providers (like Pleenk), healthcare organizations, sportsbook operators (like Pro Gambling), e-commerce platforms and SaaS companies. Pharos Production has worked with 200+ clients across 28 industries since 2013, adapting engagement models to match each client's stage, whether it is MVP validation for a startup or enterprise-scale development for an established business.

• How is a custom software development company different from an agency?

  Copy link Copies a direct link to this answer to your clipboard.

  A custom software development company like Pharos Production assigns one dedicated engineering team that owns your product across multiple release cycles, instead of handing it off once a contract ends. Agencies more often rotate staff between clients and optimize for fast delivery over long-term product ownership.

  Pharos Production keeps the same team on your codebase through 2-week sprints, so there is no re-onboarding cost each time you request a new feature.

• How much does custom software development cost?

  Copy link Copies a direct link to this answer to your clipboard.

  Custom software development costs vary based on project scope and complexity. At Pharos Production, typical project ranges are: MVP development ($10,000-$25,000), suitable for startups validating a product idea; full-fledged production ($25,000-$50,000), for established businesses scaling a proven concept; and full-cycle development ($50,000-$80,000+), for complex enterprise-grade systems. These ranges include architecture design, development, QA testing and deployment. Hourly rates range from $50 to $99 depending on role and seniority. Final pricing depends on technology stack, number of integrations and engagement model (staff augmentation, dedicated team or project outsourcing).

• How long does it take to develop a custom software application?

  Copy link Copies a direct link to this answer to your clipboard.

  Development timelines depend on scope and complexity. At Pharos Production, a typical MVP takes 2-4 months, a production-ready application takes 4-8 months and a complex enterprise system can take 8-12+ months. We use an agile methodology with 2-week sprints, delivering working increments after each sprint. Every sprint includes a retrospective, progress report and planning session for the next iteration. This approach ensures transparency and allows businesses to launch faster by prioritizing high-impact features first. Get a timeline estimate for your project.

• What industries does Pharos Production serve?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production serves 28 industries: FinTech, MiCA Compliance, Banking, Insurance, Crypto, Healthcare, Fitness, E-Commerce, Food & Restaurant, On-Demand, Manufacturing, Automotive, Energy, Oil & Gas, Supply Chain, Construction, Real Estate, Gaming, Streaming, Media, Telecom, Education, Aviation, Travel, Logistics, Marketing, Agriculture and Recommender Systems. Our deepest expertise is in FinTech, blockchain and healthcare, where we have delivered compliance-ready platforms (HIPAA, PCI DSS, GDPR) and high-load systems handling thousands of concurrent users. For the latest industry insights, read our guides on FinTech trends in 2026 and the Web3 technology stack.

• Why hire a software development company instead of building in-house?

  Copy link Copies a direct link to this answer to your clipboard.

  Hiring a software development company offers faster time-to-market, lower upfront costs and access to specialized expertise without long-term employment commitments. According to Deloitte's 2024 Global Outsourcing Survey, 57% of companies outsource software development to access skills they cannot hire internally.

  Factor	In-house team	Software development company
  Time to assemble	3-6 months (recruiting + onboarding)	1-2 weeks
  Upfront cost	High (salaries, benefits, equipment)	Lower (project-based pricing)
  Specialized expertise	Limited to who you can hire locally	Access to 90+ engineers across blockchain, AI, FinTech
  Scalability	Slow (each new hire takes months)	Fast (scale up or down per sprint)
  Long-term commitment	Full-time employment contracts	Flexible engagement models
  Risk	High if key engineers leave	Company ensures continuity and knowledge transfer

  For businesses that need blockchain, AI or high-load architecture expertise, outsourcing to a specialized firm like Pharos Production reduces risk and accelerates delivery.

• What projects does Pharos Production not take on?

  Copy link Copies a direct link to this answer to your clipboard.

  Pharos Production focuses on mid-to-large custom software projects with budgets starting at $10,000. We do not take on template-based websites, WordPress theme customization or short-term contracts under one month. We also do not provide non-technical staffing (marketing, sales or design-only roles). Our strongest fit is blockchain, FinTech and healthcare projects where security, compliance and high-load architecture are critical. For smaller projects or MVPs under $10,000, we recommend exploring freelance platforms or no-code tools as a more cost-effective starting point.

• Why does Pharos Production use agile methodology?

  Copy link Copies a direct link to this answer to your clipboard.

  We use agile with 2-week sprints because it reduces the risk of building features that miss the mark. Each sprint ends with a working demo, a retrospective and a plan for the next iteration.

  This means clients see progress every 14 days and can adjust priorities based on real results, not assumptions. We chose this approach after years of experience showing that rigid, fixed-scope contracts lead to scope creep, missed deadlines and products that do not match market needs by launch day.

• When should you NOT hire a custom software development company?

  Copy link Copies a direct link to this answer to your clipboard.

  Custom development is not the right choice in every situation. You should not hire a custom software company if: your problem is fully solved by an existing SaaS product (e.g. Shopify for e-commerce, Salesforce for CRM); your budget is under $10,000 and timeline is under 4 weeks; you need a simple landing page or marketing website (WordPress or Webflow is faster and cheaper); or you are still validating the idea and have not spoken to potential users yet.

  In these cases, off-the-shelf tools or no-code platforms offer better ROI. Custom development makes sense when you need unique workflows, regulatory compliance, high-load architecture or competitive differentiation that packaged software cannot provide.

• What kind of projects has Pharos Production delivered?

  Copy link Copies a direct link to this answer to your clipboard.

  Here are three anonymized examples from our recent delivery history:

  FinTech startup - payment platform (MVP)
  Scope: mobile app + backend API with bank-grade encryption. Team: 4 engineers, 1 QA. Timeline: 10 weeks. Budget: $38,000. Result: launched on schedule, processed $2M+ in transactions within the first quarter.

  Healthcare provider - patient portal (Full product)
  Scope: HIPAA-aligned web platform with EHR integration, appointment scheduling and telemedicine. Team: 6 engineers, 1 DevOps, 2 QA. Timeline: 6 months. Budget: $120,000. Result: 15,000+ active patients, zero compliance violations in two annual audits.

  Crypto exchange - trading engine (Complex)
  Scope: high-load matching engine handling 50,000+ orders per second, multi-chain wallet infrastructure on Ethereum and Solana. Team: 8 engineers, 2 QA, 1 security auditor. Timeline: 11 months. Budget: $340,000. Result: 99.97% uptime, passed three independent security audits.

  See more projects: NoMoreBets, Pulse, Sagas, Gambit Stream and Pleenk. For the full portfolio, visit our case studies. Learn more about the technology behind these projects in our guide to stablecoins and crypto infrastructure.

Dmytro Ihnatov is the Lead Backend Developer at Pharos Production. He documents backend architecture and research experiments from the team's work on a professional learning platform for aesthetic medicine.