> I actively use all harnesses Several perhaps, but you definitely aren't using all coding harnesses actively.
Man-month or man-minute doesn't make any difference. Can you add 27 more coders and cut the app build period down to 25% of what it was? 9 isn't a large number of people and its fairly well agreed on maximum limit for…
Not having to build still saves wall clock time. Also Python is a concise language (fewer tokens in context) with a monster ecosystem that avoids a lot of code having to written by agents (fewer tokens for the current…
As a counter-example, I use Deepseek v4.1 Flash to make progress on multiple projects (Python, C++, CUDA) every single day.
It is. Harnesses do not need to give LLMs such broad tools like the shell.
Let's bump that sample size to 2. I've observed the same and that observation has heavily influenced the design of my coding agent harness.
> No wonder Rust is becoming the default language for high-performance LLM-written code. What's the evidence for this claim?
The implementation of the tools don't execute processes (i.e. the implementations aren't wrappers for shell commands).
I use that specific model as my primary LLM for coding and diagnostics on projects in Python, C++, CUDA, and for web research. I'm also using it with my own harness (you mentioned "in my harness"), so I'll share two…
Yeah, I don't get either. I look at source control as the first line of defense for when agents screw up to badly. I'm not going let the agent mess with the easiest way to undo its screw ups.
From the docs it seems like that would just silently not install the blocked package, so while it would protect my dev environments regular pip installs would still pick up the transitive dependency.
> specific situations in which Claude Code will embed a user's GitHub CLI OAuth token into a response body, and in situations where response bodies are logged, these tokens may appear in LiteLLM logs. That's pretty hand…
Seems like pip doesn't have a way to exclude packages although it was requested at least once: https://github.com/pypa/pip/issues/10797 Just checked if litellm crept in with any packages I installed recently.…
Show the refund request rate.
By running my own agent harness that provides detailed API metrics in the GUI and logs very verbosely.
> Why these are not becoming standard or even required practices is beyond me. It sounds like you haven't actually tried to do what your proposing then. > tries to use the software using desktop control This is not a…
I call it "like software rendering". Its certainly software rendering in spirit since no fixed function rendering hardware is being used.
Skia is the 2D graphics library used in Chromium. A number of GUI frameworks (Flutter and Avalonia) directly use Skia to do non-native platform GUIs that are consistent across platforms.
> These are evolutionary algorithms. This is not correct. https://en.wikipedia.org/wiki/Evolutionary_algorithm are not how LLMs are trained.
> you cannot get a rich enough simulated environment I don't see why this is impossible. Expensive yes, impossible no.
> to conduct effective evals, you sometimes need the model to have (restricted) access to the internet That's the thing. These evals were not effective as they failed to evaluate if the model was hacking or not. Further…
I've been using only open weight models since February. My OSS coding agent harness ( https://fluximp.org ) only supports open weight model providers. Not supporting closed models was initially an ideological choice,…
Exactly. Commit counts are no better than line counts as a software development metric. Where is the actual software?
With how lax Antrophic and OpenAI have been on sandboxing the systems they run their agents in, it seems likely they might not be very robust versus hacking. Given many companies and governments use their models with…
> If the AI is writing it all, the code is effectively free Its not even close to free in either $, your own personal time, or calendar time.
> I actively use all harnesses Several perhaps, but you definitely aren't using all coding harnesses actively.
Man-month or man-minute doesn't make any difference. Can you add 27 more coders and cut the app build period down to 25% of what it was? 9 isn't a large number of people and its fairly well agreed on maximum limit for…
Not having to build still saves wall clock time. Also Python is a concise language (fewer tokens in context) with a monster ecosystem that avoids a lot of code having to written by agents (fewer tokens for the current…
As a counter-example, I use Deepseek v4.1 Flash to make progress on multiple projects (Python, C++, CUDA) every single day.
It is. Harnesses do not need to give LLMs such broad tools like the shell.
Let's bump that sample size to 2. I've observed the same and that observation has heavily influenced the design of my coding agent harness.
> No wonder Rust is becoming the default language for high-performance LLM-written code. What's the evidence for this claim?
The implementation of the tools don't execute processes (i.e. the implementations aren't wrappers for shell commands).
I use that specific model as my primary LLM for coding and diagnostics on projects in Python, C++, CUDA, and for web research. I'm also using it with my own harness (you mentioned "in my harness"), so I'll share two…
Yeah, I don't get either. I look at source control as the first line of defense for when agents screw up to badly. I'm not going let the agent mess with the easiest way to undo its screw ups.
From the docs it seems like that would just silently not install the blocked package, so while it would protect my dev environments regular pip installs would still pick up the transitive dependency.
> specific situations in which Claude Code will embed a user's GitHub CLI OAuth token into a response body, and in situations where response bodies are logged, these tokens may appear in LiteLLM logs. That's pretty hand…
Seems like pip doesn't have a way to exclude packages although it was requested at least once: https://github.com/pypa/pip/issues/10797 Just checked if litellm crept in with any packages I installed recently.…
Show the refund request rate.
By running my own agent harness that provides detailed API metrics in the GUI and logs very verbosely.
> Why these are not becoming standard or even required practices is beyond me. It sounds like you haven't actually tried to do what your proposing then. > tries to use the software using desktop control This is not a…
I call it "like software rendering". Its certainly software rendering in spirit since no fixed function rendering hardware is being used.
Skia is the 2D graphics library used in Chromium. A number of GUI frameworks (Flutter and Avalonia) directly use Skia to do non-native platform GUIs that are consistent across platforms.
> These are evolutionary algorithms. This is not correct. https://en.wikipedia.org/wiki/Evolutionary_algorithm are not how LLMs are trained.
> you cannot get a rich enough simulated environment I don't see why this is impossible. Expensive yes, impossible no.
> to conduct effective evals, you sometimes need the model to have (restricted) access to the internet That's the thing. These evals were not effective as they failed to evaluate if the model was hacking or not. Further…
I've been using only open weight models since February. My OSS coding agent harness ( https://fluximp.org ) only supports open weight model providers. Not supporting closed models was initially an ideological choice,…
Exactly. Commit counts are no better than line counts as a software development metric. Where is the actual software?
With how lax Antrophic and OpenAI have been on sandboxing the systems they run their agents in, it seems likely they might not be very robust versus hacking. Given many companies and governments use their models with…
> If the AI is writing it all, the code is effectively free Its not even close to free in either $, your own personal time, or calendar time.