we are running a harness outside the sandbox, inside a sandobx.
HN user
8thcross
didnt prove anything. prompt engineering still works with GPT-5. dont know what your experience is about...
I tried it with cursor-agent, their cli - and it generated better code than expected. YMMV. It was more thoughtful and strategic than the other frontier models.
Once you on it, you are hooked bru.
a little too late i think.
interesting but i have thought about it. rarely is ours as well. All my code is original but based on my past experiences from learning, thinking about it, and improving it based on new knowledge i know. my 2cents.
This is from their claude-code guide: "Claude Code is intentionally low-level and unopinionated, providing close to raw model access without forcing specific workflows. This design philosophy creates a flexible, customizable, scriptable, and safe power tool. While powerful, this flexibility presents a learning curve for engineers new to agentic coding tools—at least until they develop their own best practices". The agent is what makes the claud-code as good as it is. By not using it, you are using the model that is a hit or miss on several aspects a programmer would need.
I fear your definition of "success", needs some rethinking. What are you really happy about, for whom, why?
Been using it for a couple days - The integration fixed the gap that required me to open the files for viewing updates, and changes made in real-time as compared to the terminal mode, which did things behind the scenes, and you had no idea what its doing. the series of nonsensical (but funny) names (Pondering, Twerking, Juggling, etc.) it gives are not useful after its initial fancy wears off..
Hmm...It seems that humans should be less interested in such things? Making Makefiles readable by human is less needed in the context of LLMs needs to know about it more than us no?
I think we are just discovering as engineers, on how our brain works.
building knowledge graphs (GrahRAGs) are obsolete from a acamedic and technical point of view. LLMs are getting better with built in graph networks capable algorithms like SONAR and knowledge embeddings. like someone said - just use Notebook LM instead. But, they are useful in corporate setup when the infrastructure,teams and skills are lagging by years.
agreed. depends on how competent a manager is or the org is in recognizing their employee's skills.
I realized, being a manager overseeing people, chasing after career progression was a wrong path. I should have stuck to what I like more, engineering, not bullshitting.
was it based on India's UPI? If so, this is the basis for SWIFT for BRICS?
so you are saying i can feed my last 10 years of exam question papers and get predictions on what we will get this year?
I think the Indians started this trend...Infosys, L&T etc.
got it. plan B for skynet. one baby transformer at a time.
ah, Thanks! but what can a distributed system like this do? is this a fun to do, for the sake of doing it project or does it have practical applications? just curious about applicability thats all.
whats the point of this? serious question - can someone provide usecases for this?
Thanks for reminding us that vision (in the vision models) is not the same as having a pair of eyes.
I do see the trend in corporates to push this agenda, not sure if it will survive though...becoming a developer again may sound like downsizing your career progression in many cultures.
About the diverging roles, i agree its likely go down that path, based on my own career experience as well. The fact that I enjoy the freedom to be as innovative with quick turnaround, i could be in terms of directly able to solve business issues, rather than process entanglements set forth for managing developers.
people have been doing this for a while now? cost is one factor obviously, but privacy, security, and offline use comes to mind.
Cline or Roo Cline allows for local LLMs to be used. OpenRouter.ai - has made both Google Gemini 2.0 flash and thinking free!
This was my finding as well - I now use Roo Cline tho....
"This means the code being released contains all the build system files (using the waf build system), but it will not compile or link as released."
What do we do with this POS?
"This means the code being released contains all the build system files (using the waf build system), but it will not compile or link as released."
But what can you do with this?
many of the indian tech leaders have been saying just that...70-90 hrs a week!
i like sony WH-XM1000 series. I have 3, but it works great. turn off NR is easy, it even comes with a cord to use when it runs out of power. if you like audiophile quality - 300 is not going to cut it.