polskibus

I find it interesting why this article dropped so quickly from the front page. Is there a way for privileged users to actively push an article away from it?

I assure you, it’s similar in many EU countries. Teachers are usually paid very little, governments are not doing much to keep them, due to really bad demographics forecasts in most countries.

Why do you think it’s different in other countries? It’s the same all over Europe too. More and more kids have ADHD or other mental issues, social networking affects social norms etc.

This is your brain trying conserve your energy/time by recollecting/brute-forcing/following known patterns, instead of diving into unknown. Otherwise known as „being lazy” / procrastinating.

What is the model architecture? I'm assuming it's far away from LLMs, but I'm curious about knowing more. Can anyone provide links that describe architectures for VLA?

So explicit model description (kind of repeating the schema into explicit model definition) provides better results when used with LLM because it’s closer to the business domain(or maybe the extra step from DDL to business model is what confuses the LLM?). I think I’m failing to grasp why does this approach work better than straight schema fed to Llm.

are you saying that a current gen LLM can answer such queries with EnrichMCP directly? or does it need guidance via prompts (for example tell it which tables to look at, etc. ) ? I did expose a db schema to LLM before, and it was ok-ish, however often times the devil was in the details (one join wrong, etc.), causing the whole thing to deliver junk answers.

what is your experience with non trivial db schemas?

This looks very interesting but I’m not sure how to use it well. Would you mind sharing some prompts that use it and solve a real problem that you encountered ?

It’s also an excellent example on how lack of forced machine-readable format for gov publishing is a PITA.

My experiments with copilot and Claude desktop via mcp on the same codebase suggest that copilot is trimming the context much more than desktop. Using the same model the outputs are just less informed.

I guess it’s too late now, please consider EU next time. Whether I would buy it would depend on total cost. I joined the waitlist.

How can I order it to Europe?

Is this a reaction to Apple paper showing that reasoning models don’t really reason?

How does it work for outsourcing? Do you get full tax deduction if f you just pay offshore company to do dev?

What is your team’s take on the copyright for commits generated by ai agent ? Would the copyright protect it?

Current US stance seems to be: https://www.copyright.gov/newsnet/2025/1060.html “It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements”.

If entire commit is generated by AI then it is obvious what created it - it’s AI. Such commit might not be covered by the law. Is this something your team has already analysed?

Thanks for the additional information, a few hours sounds great, I was expecting multiple days to narrow it down, given a lengthy feedback loop.

I wonder how long did it take to bisect such issue. Build image every time and reboot a vm?

Still it means it does really heavy lift. I’d like to understand how to extract bigger efficiency gains from Claude etc , because currently often times I just waste time with it and give up after several attempts

Question for those who burn through Max limits- what type of tasks do you do that burn so much of the limit? I’d imagine it has to be a lot of code being produced? Or is it large inputs that burn through it quickly? If you run Claude so often during the day - what is it doing for you all the time?

Shouldn’t this be a launch HN/ shown HN?

It has Research , works well with Web Search. Saves a lot of time compared to googling and trying to synthesise knowledge yourself.

What would be the copyright status for clips generated with such service? Would the copyright protect it?

Current stance:

https://www.copyright.gov/newsnet/2025/1060.html

“It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements”.

If it isn’t covered (after all it’s the AI that drew all the pictures) then anyone using such service to produce a movie would be screwed - anyone could copy it or its characters).

I’m leaving out the problem of whether the service was trained on copyright material or not.

I think the bigger problem, that started around 2022 is much lower volume of jobs in software development. Projects were shutdown, funding was retracted, even the big wave of migrations to the cloud died down.

Today startups mostly wrap LLMs as this is what VCs expect. Larger companies have smaller IT budgets than before (adjusted for inflation). This is the real problem that causes the jobs shortage.

Is this similar to what google does with sheets and Microsoft with excel these days?

Jetbrains tools have MCP plugin and can work with Claude.

Can you share an example of such real world win where fine tuning was less effective ? I’m curious about sample business cases.

I’m interested in this and it seems you have done your homework. Would you mind sharing some references?

They are higher than South Korea. One big factor remains which are very high property prices and rents. People have a choice and want their kids to have space. If they cannot afford it then often they choose not to have kids (or have 1 less).

Do iOS apps also take screenshots of activity in other apps without consent? Does the platform allow it to, if yes then is there a way to block it?

I got Claude Desktop to perform code review using mcp in Jetbrains IDE. I don’t know why would you prefer a cloud based pipeline with separate CR tool to it. This way I can extend the review process the way I want for example adding feature specs etc. There are other issues with llm based CR but I think mcp (or similar protocol) is the way to go.