4
points
gyre007
Joined 2,778 karma
Hacker
Personal blog: https://cybernetist.com/
[ my public key: https://keybase.io/milosgajdos; my proof: https://keybase.io/milosgajdos/sigs/8qF4glD8qAvHdQ9rB6-hlEMv9xmyIvD4bj4SkGshR8g ]
- gyre007 parentFrom my experience Zed agents oftn just goes and edits your files without your asking it to. Even if you ask questions about codebase, it assumes you want it to be changed. For it to be useful it must be better at understanding prompts; I would also like it to generate diffs like it does but prompt me if I want to apply them first
- Not having the leader really annoys me but I’ve found myself using Zed more and more recently regardless. I think their LLM integration is just right for me unlike the neovim plugins I’ve tried. It’s really annoying because Ive been using vim for well over a decade so Id prefer to stick at home, but Zed is really reaching the level Im starting to like
- 1 point
- Yep, this is the right take. Somehow entrepreneurs are perceived in the EU as tich freeloaders and not as job and innovation creators who tend to take a lot of risk and go through tremendous pressure while running their companies. I feel the influx of VC money skewed the vision of what it entails to start a company: it is true that the investment slightly "de-risks" founders (emphasis on double quotes!) but that's often an illusion - I don't think people who never ran a company understand the pressure of a founder's responsibility towards their employees, investors, etc... most of the generally very risk-averse Europeans will never grasp this
- > They coddle rather than manage
At one of the gigs I had, the VP of Engineering was running the engineering department like your good uncle rather than actually managing it so it becomes a well oiled high performing department. And it showed. And not in a good way. It set the company back badly.
- This is true, but as I learnt [1] recently, adversarial attacks on LLMs can get incredibly sophisticated, so this is kinda apples and oranges ¯\_(ツ)_/¯
[1] https://cybernetist.com/2024/09/23/some-notes-on-adversarial...
- This is awesome! Over the summer I wrote API clients for both Go [1] and Rust [2] as we were using Play in my job at the time but there was only Python and Node SDK.
[1] https://github.com/milosgajdos/go-playht [2] https://github.com/milosgajdos/playht_rs
- I didn't say it was bs. I was alluding to the timing of this essay being published but, clearly, I didn't articulate it in my message well. I also don't think everything he says is bs. Some of it I find a bit naive -- but maybe that's ok -- some other things seem a bit like sci-fi, but who are we to say this is impossible? I'm optimistic but also learnt in life that things improve, sometimes drastically given the right ingredients.
- This reminded me of my Hopfield networks implementation in Go [1]. The algorithm is rather simple but fascinating nevertheless and works surprisingly well for reconstructing noisy images. I actually blogged about it as well [2]. But as many are discussing here Deep Memory networks based on Boltzmann networks are more powerful yet they don't seem to have found much use case either
[1] https://github.com/milosgajdos/gopfield [2] https://cybernetist.com/2017/03/12/hopfield-networks-in-go/
- I finally read it recently (few months back or so) and I thoroughly enjoyed it. One of the many takeaways for me was how similar the SW world is to the HW one when it comes to actual human being behind engineering -- I guess I shouldn't be surprised but for some reason, the book reinforced that notion in my head. I'm sure I will read it again at some point.
- 5 points