221–230 of 268 posts
Did anyone have equal results with the „unofficial“ fork „Anon Kode“? Or with Roo Code with Gemini Pro 2.5?
Earlier quoted context omitted.
Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.
At this point should we get our first knob/slider on a language model... THINK ..as if we're operating this machine as analog synth
The consumer-facing chatbot interfaces just hide all that because they're aiming for a non-technical audience.
I've developed a new mental model of the LLM codebase automation solutions. These are effectively identical to outsourcing your product to someone like Infosys. From an information theory perspective, you need to communicate approximately the same amount of things in either case. Tweaking claude.md files until the desired result is achieved is similar to a back and forth email chain with the contractor. The differenc…
> These are effectively identical to outsourcing your product to someone like Infosys. But in my experience, the user has to be better than an Infosys employee to know how to convey the task to the LLM and then verify iteratively. So more like an experienced engg outsourcing work to a service company engg.
I've developed a new mental model of the LLM codebase automation solutions. These are effectively identical to outsourcing your product to someone like Infosys. From an information theory perspective, you need to communicate approximately the same amount of things in either case. Tweaking claude.md files until the desired result is achieved is similar to a back and forth email chain with the contractor. The differenc…
Earlier quoted context omitted.
Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.
At this point should we get our first knob/slider on a language model... THINK ..as if we're operating this machine as analog synth
Surprised that "controlling cost" isn't a section in this post. Here's my attempt. --- If you get a hang of controlling costs, it's much cheaper. If you're exhausting the context window, I would not be surprised if you're seeing high cost. Be aware of the "cache". Tell it to read specific files (and only those!), if you don't, it'll read unnecessary files, or repeatedly read sections of files or even search through f…
The productivity boost can be so massive that this amount of fiddling to control costs is counterproductive. Developers tend to seriously underestimate the opportunity cost of their own time. Hint - it’s many multiples of your total compensation broken down to 40 hour work weeks.
The "ultrathink" thing is pretty funny: > We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" I had a poke around and it's not a feature of the Claude model, it's specific to Claude Code. There's a "megathi…
Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.
Earlier quoted context omitted.
Not gonna lie: the "ultrathink" keyword that Sonnet 3.7 with thinking tokens watches for gives me "doubleplusgood" vibes in a hilarious but horrifying way.
A little bit of the old ultrathink with the boys
Earlier quoted context omitted.
Oh wow. Reading your comment guarantees I'll never use Claude Code. I use Aider. It's awesome. You explicitly specify the files. You don't have to do work to limit context.
Not having to specify files is a humongous feature for me. Having to remember which file code is in is half the work once you pass a certain codebase size.
Earlier quoted context omitted.
What is in the file?
An overview of the project and the features implemented. Edit: Here's the actual file if you want to see it. https://gist.github.com/Wowfunhappy/e7e178136c47c2589cfa7e5a...
It doesn't seem to have included any points on style or workflow in the context. Most of my context documents end up including the following information:
1. I want the agent to treat git commits as checkpoints so that we can revert really silly changes it makes.
2. I want it to keep on running build/tests on the code to be sure it isn't just going completely off the rails.
3. I want it to refrain from adding low signal comments to the code. And not use emojis.
4. I want it to be honest in its dealings with me.
It goes on a bit from there. I suspect the reason that the models end up including that information in the context documents they dump in our sessions is that I give them such strong (and strongly worded) feedback on these topics.
As an alternative, I wonder what would happen if you just told it what was missing from the context and asked it to re-dump the context to file.