XzAeRosho

I was reading the announcement and wondering the same. And don't forget, still with 3.1 Pro as the frontier model.

Same for me. DeepSeek models are incredibly good at implementation and light planning. I still default to Opus models for feature planning, but for most simple features the Pro models suffice.

Incredible good value and product they have built.

Read the article. It's about Microsoft culture messing things up, not Azure themselves (though it may be a factor).

This is just speculation, but I suppose it's because Apple is also collaborating/contributing in the EU Chat Control 2.0 legislation, so they may have some argument that completely opening the door for uncontrolled app installs may not allow them to comply with such legislation.

As I said, just speculation, but this is how most of the time these things go

This has been a lesson I learnt very early in my SWE career. This is nothing new sadly, but is a great lesson that not everything is technical expertise, but rather presentation and UI eye candy.

Tell that to recruiters requiring leet code tests for Senior/Leadership roles. Absolutely idiotic market at the moment.

Google's MO since always has been to release great products or services for free, position themselves high and then abandon them or just find uses for Enterprise sales.

I'm pretty sure they are doing it because they get some research experience by shrinking and improving these models, and because they know that by doing this they get some good PR among the dev community.

It just repopulates the context. It's absolutely infuriating the way it behaves now, since there are not many workarounds to minimize token usage unless you use caveman [1].

[1]: https://github.com/JuliusBrussee/caveman

It's not actually doing browser actions like Playwright or other browser automation tools, rather than direct API and MCP calls/actions. This is a whole new subset of API and connections that are all contained within the Agent context, no browser mocking. That's why they are creating these new protocols, so the full governance can work within the context of the Agent and its available tools.

As I said, it doesn't have to make sense, but this is being pushed on us anyway...

There's a slightly new topic called Agentic Commerce, where you say for example: "purchase for me the most energy efficient dishwasher with a budget of $600", and the agent will connect via specialized via special MCP Servers and APIs to available stores, and will do the full purchase process for you.

This MPP helps bridge the gap between the agent putting the product "in the basket", to actually completing the full purchase process.

Disclaimer: I'm not in any way advocating for this use case, but it's part of my job to understand how it works. Part of what I do is try to help Agents understand, for example, what is "an efficient dishwasher" using actual data, and not hallucinated info.

I know most of this affects only the US, but I'm wondering where this will go in the EU if the Age Verification Tech goes ahead in America. There's been lots of efforts to increase surveillance disguised as protection for kids in the EU and UK.

The Swiss implementation of eID may be hint that governments may/will take the responsibility to implement and maintain the tech, but the multiple intrusions and lobbying by Palantir and friends in the EU gives me the ick.

>2. How do you handle the semantic gap? LLMs operate in natural language/fuzzy logic space, while formal methods require precise specifications. What's the translation layer like?

From what I understood, this validates the output correctness, not that the output aligns with the user goals, so there's still room for the LLM to get the user goals wrong, and this is only to validate the mathematical consistency between the output code and the formal specification (in this paper, within the ESBMC framework for C++ code).

So it's kind of tight scoped, in this case, but I think it points in the right direction for coding assistants, which usually get some language primitives wrong.

This is the job a junior developer may deliver in their first weeks at a new job, so this is the way it should be treated as: good intentions, not really good quality.

AI coding needs someone behind to steer it to do better, and in some cases, it does. But still hasn't left the junior phase, and while that doesn't happen, there's still the need for a good developer to deliver good results.

An option trader would bet on the volatility index of the predictions, instead of the prediction itself.

The answer to most convenient solutions is money. There's no money in that.

Absolutely. Common sense and critical thinking is less common than you may think.

It really depends on the driver lottery. Do you have good driver support? Good, you'll have a mostly flawless experience. Generic drivers? You either get weird cpu usage patterns, or perfectly normal behavior. Maybe an update will break everything. Welcome to the Linux Driver Lottery.

It's really good nowadays, but the issues remain the same sadly, and it's not Linux devs fault either, it's just the manufacturer lack of support.

If things felt corrupt before, why not improve the processes? Why keep doing the same but with the companies the administration in turn likes the best?

I think the answer it's in the Blackmagic website:

>the world’s first advanced cinema camera designed to shoot for Apple Immersive Video

I think they are tapping early into an emerging "new" video format.

It says so in the article itself:

>Excluding interconnects, the SRAM and CCD should add up to less than 20µm thick. To accommodate such small and fragile components, AMD has added a bulky layer of dummy silicon at the top and the bottom for structural integrity.

yup: https://grapesjs.com/

Self-hostable too.

I've been working on some ML solutions similar to this with, and the high accuracy is the challenging part. Specially with "creative" layout documents.

I'm curious as well to see how they are handling accuracy, since I had to build an external agent to validate data.

I know this is an honest response, but it's a bit funny that most (if not all) of those features are not useful at all in daily applications. And they will be added in the future™!

Interesting!

As a fullstack developer, how did you even landed on such projects? Are you even using your SW Engineering skills in this? I really want to know more how are you able to lead an urbanism and architecture project with, supposedly, no formal backgrounds. Are you partnered with other people in this endeavour?

RLS is rock solid. That's what Supabase leverages to create access policies and more. They have a very good example of how it works and how powerful it is in their docs: https://supabase.com/docs/guides/database/postgres/row-level...

  Location: Barcelona, Spain
  Remote: Yes
  Willing to relocate: No
  Technologies: Python, Golang, C#, Docker, PHP, Linux networking, LLMs agent tuning, data science
  Résumé/CV: https://linkedin.com/in/vagonzal
  Email: victor <at> vgr.cl

Senior Software Engineer with 10+ years of experience and 5 years working remotely with stable clients from all over Europe. I have a preference for backend and networking, but I'm still proficient in frontend technologies like React, Vue, and my new favorite: Astro.

I feel confident working in most modern programming languages, and have 6+ years of experience in project/team management. I'm very flexible at working in any kind of environment.

It's on HuggingFace already: https://huggingface.co/google/gemma-2-9b

Nowadays, installing WSL is really painless procedure [1]

Also make sure to install the Windows Terminal [2] to take full advantage of wsl2.

[1]: https://learn.microsoft.com/en-us/windows/wsl/install

[2]: https://learn.microsoft.com/en-us/windows/terminal/install

>The presence of oxygen so early in the life of this galaxy is a surprise and suggests that multiple generations of very massive stars had already lived their lives before we observed the galaxy.

For some reason this quote blew me away. It's just so hard to comprehend the timescales and vastness of the universe.

It's considered an emergent phenomenon of LLMs [1]. So arithmetic reasoning seems to increase as LLMs reasoning grows too. I seem to recall a paper mentioning that LLMs that are better at numeric reasoning are better at overall conversational reasoning too, so it seems like the two come hand in hand.

However we don't know the internals of ChatGPT-4, so they may be using some agents to improve performance, or fine-tuning at training. I would assume their training has been improved IMO.

[1]: https://arxiv.org/pdf/2206.07682