gps372

This might be already happening. Competitor's market share (without details) is common to share. Scintilla onboarded by Walmart earlier this year might already be giving instore AI capabilities.

True, in-store planogram compliance and floor-plan compliance have got in focus again. It never lost the focus to be honest, just that now there is an expectation to do it while ensuring nothing fall through the cracks.

But there is a much more stringent privacy requirement here since customers walking in those stores haven't really signed up for this analysis. Hence, difficult to just setup the camera and take continuous data for analysis.

Plain and boring computer vision would have still required a team who would identify frames to sample before processing, and then annotate, generalize and classify the data.

Not an expert on this but I don't think same kind of manual effort is required anymore.

Most comments may have ignored this so far, but this is an interesting AI based research.

At the end of the article is this excerpt

>> Results from this research were generated using an AI computer vision model developed by the research team on Bristol’s Isambard-AI, the UK’s most powerful AI supercomputer. Isambard-AI powered the analysis of 172.6 hours of live match footage from all 104 games played between 11 June and 19 July 2026.

So, basically now merchandizers, auditors, compliance monitors, etc. have a tool using which they can quantify whether broadcaster complied with contractual requirements of showing their ads/merch/logos as per contract. And if they missed, then they can quantify the delta - to sue the broadcaster for the balance as well.

Also, it can enable many countries, where certain content is not allowed, then this tool can simply give them data points without having to employ someone, or have someone review the output of the AI tooling.

Hmm, in your example, temperature is fully measurable but there might be a slight challenge in measuring if "If we are at home". Since for this you need to define more variants with measurements from motion sensors, pressure or weight sensors on beds or sofas, if a device has got connected to wifi, etc.

By the time your first round of beta testing is over, you may have quite a handful of such axioms and variants, which have been humanly validated!

Have you done any such experiment in this space?

Haven't gone through full PDF as its very detailed, few things have resonated with me so far.

Basically if a Car A is performing better (be it speed, milage or in general sense) than Car B, then it is not necessarily because its engine. It could be because of better tires, better gearbox, lighter body, better usability of features, etc.

You can implement an AI feature (like AI for BI) in different ways even with the same model - via ReAct-loop, or plan-and-execute, or hybrid. You can make it stateless, stateful, RAG-based, etc. depending upon whether you want to prioritize result accuracy or depth of analysis. You can use LLM to generate either intent (requires lesser reasoning) or the queries itself (requires much more capable model).

Your harness can adapt to the underlying model's native capabilities, or can make up for its absence, e.g. query generation in above example requires your model to have MOE capabilities but intent generation wouldn't.

Approach itself looked impractical to me for any non-trivial system, like domain centric system of records systems which can have 100s if not 1000s of laws. Though it can be tried as a side parallel thread to see if system is still compliant and following right first principals after a few years from its inception.

I would rather wait to see how it gets adopted, if at all. Anyone aware of early reviews of the adopters of bend 2?

AI can definitely be a cover for someone to do something nefarious and blame it on the AI.

All that AI needs is access to all the spicy tools like nukes, unsupervised medical diagnosis/treatment, unchecked military decision making, etc. to its React loop so that humans can be completely hands-free and enjoy the fruits of AI's labor.

Maybe we need to mandate parliament (or anything equivalent in other countries) debate before giving any critical tool access to LLM? And then a UN general assembly vote to conclude the process, maybe.

Thanks for taking time to respond here. Would love to know from your experience the scale of function-points, team size, client-requirement variance, etc. different teams would have worked with and maintained over a period of time via this open-spec.

Please note that I can already see that github repo has 68k+ stars. So popularity is not in question, just the viability and consistency of adoption across different scenarios.

>> The power is that you do a lot of upfront thinking

This is the best part of this spec, but we have found from our experience that though upfront thinking changes has a lot of merits and adds clarity and alignment upfront, but it changes bit by bit in every meeting and before you know your specs are not aligned with general consensus in the team. If your team is large enough, then it gets very difficult to own the task of constructing alignment between your principal-artifacts and your evolved under-current of understanding.

If you check my submissions (https://news.ycombinator.com/submitted?id=gps372), I have written whole set of articles on the myths of how easy it is keep the understanding consistent.

I would still say that if you are working on a platform and if your engg team size if anything more than 25-30, then this spec must be adopted from top-down and not bottoms up. Bottom level engineers usually don't have the level of consistent exposures (as and when they socialize and evangelize their platform) which top level engineers have.

Looks like this will be a hard sell for many orgs who are already struggling with explosion of artifacts on JIRA, sharepoint, github, etc. Also, most of them have somewhat settled on some ways (in past 6-8 months) to produce AI first specs and work with them.

Also, this looks like something which leadership level folks need to adopt first and then somehow it needs to trickle down to PI planning and sprint planning. Would like to hear someone's experience on how this has got adopted in their org.

Fully agree. With LLM being able to solve every problem, getting deep into a problem all by yourself becomes a passion side project. Now might be a real test of how much you love programming.

Your enterprise wants the work done, done fast and reliably. Your productivity goals have increased, just like invention of motors would increased goals of carriers who were earlier doing their job via more manual efforts like pedaling. But still people love cycling, but they largely "don't have to" rely on it to do their job.

Similarly, now you simply don't have a dependency to love programming to increase your productivity.

Superset comes with a built-in MCP server now https://superset.apache.org/admin-docs/configuration/mcp-ser..., which you need to expose as another container. Any agent with proper authentication (JWT mostly) will be able to create and manage dashboards via natural language.

If it works (something they need to be convinced about), if it accelerate mathematics and solve complex problems for humanity, then why not?

Aren't they already using computers, mobiles, calculators, etc. already?

Agree! 'Problems' are getting solved and this needs to be celebrated. Wondering how this will discourage mathematicians at all, since now they have another tool to accelerate their research. Nothing is stopping them from using 'new technologies' or sticking a gun to their head to use the 'new technologies' either.

>> No matter how precisely you specify your epic, if the model will find something that contradicts your knowledge/intent, there are good chances it'll get confused and make subtle errors, and you won't realize until much later.

True! hence the need for someone to review the final spec output and own it as their own output. I have also found LLM to be better at debugging and solving 'a' specific problem, which I believe is due to output's surface area to be reviewed is lesser in comparison.

I mean then it might be difficult to get stakeholder's alignment on specs written in typescript though.