Viewing profile — hakanderyal

It’s optimized to death. Every word, every comma. I have a rule file for writing rule files. Problem stems from using my own abstractions instead of common frameworks. For a full s…

I have rule files that guides the agent towards my coding standards, code style, house rules etc. They alone cost 60-80k tokens, and they are the backbone of my system that prevent…

UK, USA and Singapore are the popular choices for this. UK is simple and cheaper, Singapore is a bit more expensive. I don’t see a reason to go USA route unless you are seeking inv…

I think this is a common sentiment among heavy users of AI that also still cares about code quality. I've built up a skill harness and review flow that makes Opus generate slop-fre…

CC can explain it clearly, which how I learned about how the inference stack works.

This is also the reason why we have two polar opposite views on AI. “Slop generator” vs “Next best thing since sliced bread”. With SOTA models it all depends on how you drive them.…

Even that would be more meaningful test. They basically coated the ball with a strong smell, then they prepped the dog with that smell, then set it loose in a 5x5 meter area. "Our …

And it's very valid. Because otherwise you would ask Claude to trim a tree and it would go raze the whole forest and plant new seeds. This was the primary pain point last year, esp…

Similar usage here. But I encountered this moments, and I chalk it up to the random nature of LLMs. Back in Sonnet 3.5 days, it would happen every other day. I even build an 'you a…

https://x.com/elder_plinius jailbreaks all the frontier models when they get released. They were jailbroken for a long time, like all the others.

One added benefit is it allows you to throw more tokens to the problem. It’s the most impactful benefit even. Context & how LLMs work requires this. From my experience no frontier …

We are not there yet. While there are teams applying dark factory models to specific domains with self-reported success, it's yet to be proven, or generalizable enough to apply eve…

I created a system which I call 'devlog'. Agent summarizes what it did & how it did in a concise file, and its gets committed along with first prompt and the plan file if any. Late…

It has Claude all over it. When you spend enough time with them it becomes obvious. In this case “it’s not x, it’s y” pattern and its placement is a dead giveaway.

If you are not going all in with agents, yes, it would. On the other hand, the documentation & workflows need to be created only once. You need to invest a bit upfront to get posit…

Anyone that have spent serious time with agents know that you cannot expect out-of-the-box success without good context management, despite what the hyping crowd would claim. Have …

I've been increasingly removing myself from the typing part since August. For the last few months, I haven't written a single line of code, despite producing a lot more. I'm using …

What you are describing is the most basic form of prompt injection. Current LLMs acts like 5 years old when it comes to cuddling them to write what you want. If you ask it for meth…

You are describing the HN that I want it to be. Current comments here demonstrates my version sadly. And, Solving this vulnerabilities requires human intervention at this point, al…

Solving this probably requires a new breakthrough or maybe even a new architecture. All the billions of dollars haven't solved it yet. Lethal trifecta [0] should be a required read…

This was apparent from the beginning. And until prompt injection is solved, this will happen, again and again. Also, I'll break my own rule and make a "meta" comment here. Imagine …

It's mostly based on feelings/"vibes", and hugely dependent on the workflow you use. I'm so happy with Claude Code, Opus and plan mode that I don't feel any need to check the other…

Try plan mode if you haven't already. Stay in plan mode until it is to your satisfaction. With Opus 4.5, when you approve the plan it'll implement the exact spec without getting of…

He is pretty popular in the AI/vibe coding niche on X and amassed a good following with his posts. Clearly the user is in the same bubble as him.

If this helps to keep the $200 around longer, I’m happy. The thing I most fear is them banning multiple accounts. That would be very expensive for a lot of folks.