skatanski

You could have a dedicated lightweight-agent running a cheap model in parallel to any workload, analysing the workload (like the prompt) and creating "memories" in a vector DB. These could be according to some guidelines. Alternatively, if there's safety risk - storing and approving could be decoupled and split into 2.

Really good to hear that. We've had AWS reps trying to push RedShift on multiple occasions after we've done our research and selected Clickhouse for our analytical workloads. Every time we have a meeting with them for some other reason - the topic of RedShift returns, they always want to discuss it again.

Are they using headers for identification? If so, it could be skewed by orgs masking some/all. I’m quite curious myself.

I agree. I wonder if it's a mix of fully remote work being popular some time ago and the amount of tech one has to know now increasing (DBs, backend, frontend, cloud, observability, security, etc.). When hiring remotely, people naturally try to find candidates who are very communicative, have a high level of ownership, and can work with or without clear requirements and without oversight. That latter set of traits is often associated with senior developers rather than juniors.

I don’t really understand, if replacing developers is right around the corner, why throw money into so many IDEs. Or perhaps it’s really cheap to produce something like this?

Inside of buildings was quite confusing, cause you couldn’t see inside, but some targets/items were totally in there. Syndicate Wars was similar about it + destructible buildings. Both were really great my hands down favorite Bullfrog game.

I’ve tried finding similar game, the remake was an FPP, heard it was ok. And an indie game called Satelite rain was the supposed spiritual successor, never got to play it. Any recommendations?

This to me vibes with the world of manga Blame by Tsutomu Nihei. In it large automata, have been building the mega structure long after biological humans are gone. The structure already encompasses the moon, and they are still building. Cool concept, which goes well together with the architecture background of the author.

Really cool article. Personally I think the really cool bit about MCP is that you can very easily write your own server which can talk to the db or call various APIs. That server can run locally and be used by GitHub Copilot for answering questions and executing tasks. I also find it useful in a tight corporate environment where it’s more difficult to get a dedicated LLM API key. You can easily do POCa with what every dev has access to.

How does it work from the privacy standpoint? Can they use recorded samples for training?

I’m curious about other aspects of this: - leverage of countries who can host such AI over countries who can’t, will there be a point when countries can’t allow themselves not to have access to „emergency” talent in case they can’t use AI? Recent „choose european”, tariffs show that much of the high end stuff is concentrated in US and China. - outages happen, does the company stop because the cloud is not working? - highly regulated companies still can’t use copilot to its fullest because of „can’t show answer because it’s matching public code” - is replacing all talent safe - in terms of operational or national safety?

Similar here, there are gotchas though. Some versions ago they've changed their query optimization engine - some of our "slow aggregations" become "unresponsive aggregations" because suboptimal indexes were suddenly used. We had to use hints to force proper indexing. Their columnar db offering is quite bad - I'd say if there's need for analytical functionality, its better to go with a different db. Oplog changes format - and although its expected, it still hurts me every now and then when I need to check something. Similarly at some point they've changed how nested arrays are updated in changestream, which has broken our auditing (its not recommended to use changestream for auditing, we still did ;) ). We've started using NVM instances for some of our more heavily used clusters. Well it turned out recovery of an NVM cluster is much much slower than a standard cluster. But all in all I really like mongodb, if there are no relations - its a good choice. Its also good for prototyping.

Precisely, and if you are enterprise, you want to have an option to request priority support and have a lot of features out of the box. Also some of the search features are only available in Atlas unfortunately.

Could it be the top comments even though most voted are also most commented and more divisive and controversial? And the most boring comments are somewhere at the back? Hence big amount of failed predictions at the top.

I think at this moment, this sounds more like "quarter of the company's new code is created using stackoverflow and other forums. Many many people use all these tools to find information, as they did using stackoverflow a month ago, but now suddenly we can call it "created by AI". It'd be nice to have a distinction. I'm saying this, while being very excited about using LLMs as a developer.

This sounds so good. My father is using windows. He has teamviewer installed - and half the time when I wanna connect with him it turns into a nightmare of new version update. I only have most recent version. He doesn’t know, which version he has. I can’t connect to him, then I need to guide him how to update his version. It’d probably be easier for me to run older version in a VM, but then I don’t want him to run potentially insecure old version of screensharing app.