It is really good at grep and will make multiple grep calls in parallel.
And when I open it in the parent directory of a bunch of repos in our codebase, it can very quickly trace data flow through a bunch of different services. It will tell me all the files the data goes through.
It's context window is "only" 200k tokens. When it gets near 200k, it compresses the conversation and starts a new conversation..... which mostly works but sometimes it has a bit of amnesia if you have a really long running conversation on something.
> My bet is their model doesn't realistically compare to any of the frontier models.
I've been using composer-1 in Cursor for a few weeks and also switching back and forth between it, Gemini Flash 3, Claude Opus 4.5, Claude Sonnet 4.5 and GPT 5.2.
And you're right it's not comparable. It's about the same quality of code output of the aforementioned models but about 4x as fast. Which enables a qualitatively different workflow for me where instead of me spending a bunch of time waiting on the model, the model is waiting on me to catch up with its outputs. After using composer-1, it feels painful to switch back to other models.
I work in a larg(ish) enterprise codebase. I spend a lot of time asking it questions about the codebase and then making small incremental changes. So it works very well for my particular workflow.
Other people use CLI and remote agents and that sort of thing and that's not really my workflow so other models might work better for other people.
In my experience the software engineers that often get promoted crank out as many features as possible with almost no regard to the defect rate. If you do things at a more deliberate pace, you can be regarded by product or management as slow and unproductive. Real incentives exist in software development that push for quantity over quality.
This is not analogous to the failure of an anesthesiologist to properly sedate a patient. This is a process failure. Clearly the proper amount of QA was not in place for whatever reason and they need to re-examine their approach. Of course their process needs extra diligence given the cost of failure.
It would be a real shame if an individual is punished for this instead of examining the process and system of incentives that led to this failure.
Complete extinction of humans is a high bar. Also I would expect that the reaction to such a disease would be extreme. It could certainly be much worse than the current crisis we are facing.
I would agree with you that there hasn't been a genuine hit since MOO 2. I would say, however, that one game, Distant Worlds: Universe, was a huge leap forward in redefining what's possible in the 4x genre (i.e. deep and immersive gameplay in a real-time context). Most of the other 4x games since 1996 have been a variation on the gameplay mechanics of MOO 2.
DW:U is the only 4x game that I would unequivocally say is as good as the original MOO2.
Why are there so many interviews per Scala developer? I love Scala but I have a hard time finding very many companies who actually use it (I'm in Austin, TX). It seems like its usage is dwarfed by folks using Ruby, Node.js, PHP, Python, C#, Java etc.
I really hope this book has some discussion regarding Pulumi in addition to the normal Terraform discussion. My team switched over to Pulumi recently after using Terraform for a couple of years and it's so much easier to work with. It would be a shame if it is not at least included in the discussion.
Sure, but the author should have relied on those examples instead of creating some sort of bizarre hypothetical narrative to argue his point. I find it's always telling when an argument is based on hypotheticals or "thought experiments". It generally means that the author had to literally make stuff out of thin air to argue their point. It's antiscientific at best and disingenuous at worst.
Also, take home assignments are often time intensive for the candidates but not for the company giving out the assignment. I’ve done remote coding assignments but then had my candidacy dismissed for such silly reasons as “you live in the wrong time zone” AFTER I had completed the assignment. I would have felt a lot better about that sort of nonsense (it’s unavoidable if you have done more than a few interviews) if I knew that the company had invested as many hours in my interview process as I had.
I have the Nokia 3310 and like it. Aside from not being great at receiving multimedia texts, it works pretty well. Also it has Snake, but sadly not the original version.
BMC Group K.K. Japan | Senior Full Stack Web Developer | Remote Worldwide | Contract | $ Hourly | Flexible schedule
We are looking for a senior full stack web developer to help us build a collaborative data science platform. The platform will provide a cloud workspace where data scientists can develop and share Jupyter Notebooks. We are looking for someone with experience in web developent, Python, and Kubernetes. Some experience with Jupyter Notebooks and/or data science is also helpful.
We enjoy a friendly and collaborative work environment. We all have families and understand the value of life outside of work. Although we expect you to work full-time, we have an accommodating and flexible schedule.
Strong communication skills in English is also a requirement.
Knowledge of Japanese is NOT in any way a requirement.
The engagement starts with a three month duration, with a subsequent longer term opportunity based on performance.
I would agree with him that the last couple of questions are BS, but perhaps the point of it is to evaluate how good you are at convincingly BSing your way through a situation?
Most people don't have the luxury of being brilliant or well-known enough to be able to be unapologetically blunt all of the time.
Especially when dealing with customers and/or investors.
And when I open it in the parent directory of a bunch of repos in our codebase, it can very quickly trace data flow through a bunch of different services. It will tell me all the files the data goes through.
It's context window is "only" 200k tokens. When it gets near 200k, it compresses the conversation and starts a new conversation..... which mostly works but sometimes it has a bit of amnesia if you have a really long running conversation on something.