731–740 of 1001 posts
The agentic spam is exhausting. I just wanted to code. Too early in my career to not give a shit and retire, but too late be excited about these things and eager to learn. What a time...
Earlier quoted context omitted.
They have a capacity to "learn", it's just WAY MORE INVOLVED than how humans learn. With a human, you give them feedback or advice and generally by the 2nd or 3rd time the same kind of thing happens they can figure it out and improve. With an LLM, you have to specifically setup a convoluted (and potentially financially and electrical power expensive) system in order to provide MANY MORE examples of how to improve via…
> With an LLM, you have to specifically setup a convoluted (and potentially financially and electrical power expensive) system in order to provide MANY MORE examples of how to improve via fine tuning or other training actions. The only way that an AI model can "learn" is during model creation, which is then fixed. Any "instructions" or other data or "correcting" you give the model is just part of the context window.
Earlier quoted context omitted.
I wouldn't bet on an Electron app winning anything long-term in the dev-oriented space.
I strongly disagree. Firstly, the barrier to entry lower for people to take web experience and create extensions, furthering the ecosystem moat for Electron-based IDEs. Even more importantly, though, the more we move towards "I'm supervising a fleet of 50+ concurrent AI agents developing code on separate branches" the more the notion of the IDE starts to look like something you want to be able to launch in an unconfi…
Earlier quoted context omitted.
Same here - completely relate. One thing I’ve noticed though that actually coding (without the use of AI; maybe a bit of tab auto-complete) is that I’m actually way faster when working in my domain than I am when using AI tools. Everytime I use AI tools in my domain-expertise area, I find it ends up slowing me down. Introducing subtle bugs, me having to provide insane amount of context and details (at which point it…
it is absolutely poor skill, or disengenuous at best, for any coder to claim AI tools slow them down lol.
Cue: "the tools are so much better now", "the people in the study didn't know how to use Cursor", etc. Regardless if one takes issue with this study, there are enough others of its kind to suggest skepticism regarding how much these tools really create speed benefits when employed at scale. The maintenance cliff is always nigh...
There are definitely ways in which LLMs, and agentic coding tools scaffolded in top, help with aspects of development. But to say anyone who claims otherwise is either being disingenuous or doesn't know what they are doing, is not an informed take.
Earlier quoted context omitted.
- don't learn from what you tell them Whenever I have a model fix something new I ask it to update the markdown implementation guides I have in the docs folder in my projects. I add these files to context as needed. I have one for implementing routes and one for implementing backend tests and so on. They then know how to do stuff in the future in my projects.
They still aren't learning. You're learning and then telling them to incorporate your learnings. They aren't able to remember this so you need to remind them each day. That sounds a lot like '50 First Dates' but for programming.
Earlier quoted context omitted.
- don't learn from what you tell them Whenever I have a model fix something new I ask it to update the markdown implementation guides I have in the docs folder in my projects. I add these files to context as needed. I have one for implementing routes and one for implementing backend tests and so on. They then know how to do stuff in the future in my projects.
> I add these files to context as needed. Key words are these. > They then know how to do stuff in the future in my projects. No. No, they don't. Every new session is a blank slate, and you have to feed those markdown files manually to their context.
I went ahead and downloaded it, it looks to be a VSCode fork very similar to Cursor, with support for the following models: - Gemini 3 Pro (High) - Gemini 3 Pro (Low) - Claude Sonnet 4.5 - Claude Sonnet 4.5 (Thinking) - GPT-OSS 120B (Medium)
Thank you for saying what this entire blog post doesn't. It's actually disrespectful of Google to launch this without even a mention of the fact that it is based on VSCode.
Earlier quoted context omitted.
15 years ago, every company had its own "BlahBlah Studio" IDE built on top of Eclipse. Now it's VSCode. Meanwhile, JetBrains IDEs are still the best, but remain unpopular outside of Android Studio.
And IntelliJ PyCharm’s lack of popularity surprises me. Maybe it’s not good enough at venvs
If there’s a workflow I’m missing please let me know because I want to love it!