What shipped and what it changes
Model releases and capability changes, pricing and access shifts, developer tooling and infrastructure, and adoption patterns across industries.
Tobias LundIndustry & Models Writer
AI Industry & Models
Direct PDF input is now practical for many multimodal models. A test packet shows why tables, footnotes, diagrams, and cross-page references still need a parsing pipeline.
Tobias Lund · October 5, 2026 · 7 min
AI Industry & Models
A router can send routine support work to a cheaper model. The savings disappear when a short refund request hides a policy exception, so routing and model quality need separate tests.
Tobias Lund · 7 min read
AI Industry & Models
Automatic routing makes cheaper models practical for routine work. The hard part is detecting when the router, rather than the selected model, caused the failure.
Tobias Lund · 8 min read
AI Industry & Models
OpenAI, Anthropic and Google accept PDFs, but their ingestion paths preserve different evidence. A four-page test shows when direct upload works and when preprocessing is the safer choice.
Tobias Lund · 7 min read
AI Industry & Models
OpenAI can now retain a model run’s messages and tool context. That reduces orchestration code, but it makes deletion, storage duration and provider portability part of the API design.
Tobias Lund · 8 min read
AI Industry & Models
A cheaper model can handle routine requests, but one bad routing decision may create retries and manual review. Logging the decision makes the real savings measurable.
Tobias Lund · 7 min read
AI Industry & Models
Routers can send routine prompts to cheaper models and reserve stronger models for difficult cases. The savings disappear if quality misses and second calls stay outside the ledger.
Tobias Lund · 7 min read
AI Industry & Models
Real-time voice models can remove transcription from the application path. For support calls that need moderation and audit logs, developers may still need to generate text beside the conversation.
Tobias Lund · 8 min read
AI Industry & Models
Sending routine requests to cheaper models can lower inference costs. The savings survive only when the router detects mixed, unfamiliar, or high-risk requests before a bad answer triggers another call.
Tobias Lund · 8 min read
AI Industry & Models
One AI request can have different boundaries for inference, logs, abuse review, and support. The deployment setting and access controls matter more than the API hostname.
Tobias Lund · 8 min read
AI Industry & Models
Native PDF support removes a conversion step, but it does not guarantee correct rows, footnotes, or chart labels. Use a structured parser when those relationships determine the answer.
Tobias Lund · 7 min read
AI Industry & Models
Changing the model name proves that an API call still runs. A five-gate rehearsal shows whether refusals, truncation, images, token counts, and failures still fit the application.
Tobias Lund · 8 min read
AI Industry & Models
Mirror sampled production requests to a candidate model, hide its outputs, and compare each run. The method exposes task-specific regressions before a model swap reaches users.
Tobias Lund · 8 min read
AI Industry & Models
Native PDF input removes a preprocessing step, but it does not remove layout errors. The right input format depends on whether the document contains tables, columns, scans or citation-sensitive text.
Tobias Lund · 8 min read
AI Industry & Models
Moving model names remove upgrade work, but they also weaken regression evidence and incident replay. Here is when to pin a snapshot and how to stage the next one.
Tobias Lund · 8 min read
AI Industry & Models
Commercial use can be allowed while attribution, use restrictions, redistribution rules, or scale thresholds still apply. Run this four-part check before release.
Tobias Lund · 8 min read
AI Industry & Models
A two-tier model pipeline can lower inference spend, but only when escalation works before the cheap model produces a plausible mistake. The real comparison is total cost per accepted answer.
Tobias Lund · 8 min read
AI Industry & Models
A provider can update a model alias without changing your API request. Pin a snapshot where possible, then test the workflow’s outputs, latency, safety behavior, and tool calls.
Tobias Lund · 8 min read
AI Industry & Models
Page images preserve visual layout but erase many document-level relationships. A hybrid parser handles tables and scans without losing footnotes, headers, or cross-page references.
Tobias Lund · 7 min read
AI Industry & Models
OpenAI’s Responses API unifies model input and tool use, but it does not turn every Assistant, Thread, or Run into an equivalent object. Here is the migration map.
Tobias Lund · 8 min read
AI Industry & Models
Regional endpoints make in-region model inference practical, but they do not govern every log, review queue, support session, or connected search tool.
Tobias Lund · 8 min read
AI Industry & Models
Routing routine requests to a cheaper model can lower inference costs. The test is whether the router catches difficult cases without hiding errors or adding intolerable delay.
Tobias Lund · 8 min read
AI Industry & Models
A code sandbox can turn a plausible answer into a reproducible calculation. It also needs strict limits on network access, files, packages, runtime, and output.
Tobias Lund · 8 min read
AI Industry & Models
Basic chat requests transferred unchanged in our test. Parallel tools, strict argument schemas, streamed calls and tool results exposed differences that require an adapter.
Tobias Lund · 7 min read
AI Industry & Models
A replacement model can change tool calls, refusals, latency, and tone. Test it against customer-visible outcomes before a provider’s deprecation deadline forces the switch.
Tobias Lund · 7 min read
AI Industry & Models
Computer-use APIs automate software with screenshots instead of dedicated integrations. That broad reach comes with slower loops and less certainty than browser tools that read page structure.
Tobias Lund · 7 min read
AI Industry & Models
A vendor-designated successor can change refusals, token use, latency and tool calls. Shadow-test the workflow before moving production traffic, with rollback thresholds set in advance.
Tobias Lund · 7 min read
AI Industry & Models
A retirement date tells you when an endpoint closes, not whether its replacement behaves the same. Shadow traffic exposes changes in refusals, tool calls, latency, and length before cutover.
Tobias Lund · 8 min read
AI Industry & Models
Smaller models can classify, extract and route routine work with less delay and expense. The useful boundary appears only when each task is tested separately.
Tobias Lund · 7 min read
AI Industry & Models
Reasoning models help when spreadsheet cleanup requires judgment across several cells. Straight category rewrites and formula templates rarely justify the wait.
Tobias Lund · 7 min read
AI Industry & Models
A shared request format gets code talking to a second model. A 60-case replay test shows whether instructions, JSON, tools, refusals, and retries still behave.
Tobias Lund · 8 min read
AI Industry & Models
A support assistant can reuse the computation behind a static policy manual instead of processing it from scratch. The savings depend on keeping that manual at the start of every request, unchanged.
Tobias Lund · 7 min read
AI Industry & Models
A benchmark win does not make a model usable. This same-day checklist separates releases that can enter a production test from those worth watching only.
Tobias Lund · 8 min read
AI Industry & Models
Sending every file can turn one coding task into millions of repeated input tokens. Prefix caching helps, but a code map and selective loading usually cut cost, delay, and distraction further.
Tobias Lund · 8 min read
AI Industry & Models
Valid JSON is only the first gate. Production systems must also catch truncated responses, schema drift, unsupported fields, and values that look valid but trigger the wrong action.
Tobias Lund · 8 min read
One story a day
One real story about AI each morning — no hype, no alarm, just company for the road.