8thcross

I thought anthropic has guardrails, especially their frontier models and OpenAI has none? I cant even get it to work on pure science with Claude...how come nobody is using OpenAI for such? is FT just an another NYT and Wapo?

I woke up to this terrible news, and I’m shocked and surprised. I was listening to him just yesterday!

John, I’ve gained a lot from your talks, insights, tips on wine and food, your perspectives on technology, and your advice. Thank you, sir, wherever you are. I wish your family peace, and my deepest condolences.

Memory tags: His one page articles from back of pcmag and byte mags, his podcasts with leo, cranky geeks show, noagenda, horiwitz, heart attack, berkeley, wine, when I was a kid, california zephyr, mudflaps, tip of the day. you never finished that book!

we are running a harness outside the sandbox, inside a sandobx.

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.