Good catch on CTOs part. That scenario is one that keeps me awake at night -- that some large PR of mine has come functionality or feature that I didn't ask for and didn't notice.
How did the CTO respond to "Claude did it and I didn't catch it"? Did the AI PR summary mention it? Or did the CTO just read the code?
I am fighting against people doing this every day, and we've made it extremely clear that your computer and processes running on it are an extension of you, a human, who is responsible for the actions on your computer.
Won't that slow you down a lot? I get it in principle, but in practice if you have to review everything your coding agent does the productivity gains diminish significantly
Whether or not he's serious, as someone who's grudgingly using Claude at work due to mandates, the productivity gains do shrink massively (and sometimes go negative) if you actually attempt to gain the level of understanding you'd have of the system had you written it yourself.
Does it matter if the developers understand the system they maintain?
I guess that depends whether the genAI maximalists turn out to be right.
CTO responded well to it - frankly because we're all using some coding agent and it's just the natural process of code review for them to sniff things out. No mention of it in any PR summary - CTO found it in the migration that would mutate the User record to accept `null` email.
So, we tried feeding the logs back to the LLM, and it mostly produced slop. Lots of decisions nobody cared about. The biggest things that moved the needle were:
- Baseline it. We mine previous logs, github comments, etc. for "what you care about." That helps pull out decisions that you actually care to read.
- Anchor to code. "The code enshrines this decision" is more interesting than "the agent self-talked this." Agents don't always self-talk decisions, and the thing that ultimately matters is the behavior in code.
For me this is basically the opposite of how it would need to be, the decisions are all in my messages to the agent, almost never directly in the agent's replies, sometimes indirectly though I suppose.
Interesting to see that apparently some people use these tools and are the ones listening and doing what the LLM decide and says, rather than the opposite.
> Ran a blind eval before shipping, published it including the misses (REPORT.md). Agents with Grepathy answered the "why" questions right. Baseline agents made up confident wrong answers.
Is this eval public anywhere? The whole ecosystem severely lacks transparency, and people continue making strong claims without any sort of data or results that backs these up. Is there any public somewhere backing up the idea that it's more accurate that just using whatever agent harness?
> Claude made a decision nobody approved
It irks me a tiny bit that this is essentially clickbait, you don't know for sure Claude "made a decision nobody approved" as you've lost the data because you never thought sufficiently about storing these things in the first place. Most likely it misunderstood you at one point, you didn't carefully read the reply and approved it all, so most surely what you've done lead to that being done. These big models hardly ever just randomly do whatever, you can more often than not trace it to something you did wrong.
I recently took a small contract to help a vibe-founder de-vibe his project a bit. One hour with him has done more for my confidence as a developer than all the good work I’ve done this year. When probing for answers about the app and system he (lovable and Claude) had created he legitimately could not answer a single question and has almost no idea how anything works, even though there is a public web app that is capable of taking subscription payments from authenticated users. We’re living in strange times, and a giant pile of shit is coming at us like floods and tsunamis. If you’re patient and nice to talk to I imagine there will be good work available with which to flex your “I know what I’m doing”
> The reasoning was in a transcript on my laptop. Claude Code deletes those after 30 days by default. Two of my projects lost their whole history that way.
Wait what? Claude Code (and Codex) transcripts are auto-deleted??
That's a treasure trove of information for all my projects and I had built some tooling and workflows tahat deal with extracting insights from them -- withut ever realizing I mightbe losing old chats. Thanks for this -- I may need to include an archival step for retention.
Can we get the transcript of the session where you had Claude write this post? I want to understand the "why" behind this project, and whether a human being was at any point involved in the "blind, pre-registered evaluation of Grepathy against an honest baseline".
Good catch on CTOs part. That scenario is one that keeps me awake at night -- that some large PR of mine has come functionality or feature that I didn't ask for and didn't notice.
How did the CTO respond to "Claude did it and I didn't catch it"? Did the AI PR summary mention it? Or did the CTO just read the code?
I am fighting against people doing this every day, and we've made it extremely clear that your computer and processes running on it are an extension of you, a human, who is responsible for the actions on your computer.
Won't that slow you down a lot? I get it in principle, but in practice if you have to review everything your coding agent does the productivity gains diminish significantly
I guess you get to choose between reviewing it yourself or wasting someone else’s time
I can’t tell if you are serious. Are you serious?
Whether or not he's serious, as someone who's grudgingly using Claude at work due to mandates, the productivity gains do shrink massively (and sometimes go negative) if you actually attempt to gain the level of understanding you'd have of the system had you written it yourself.
Does it matter if the developers understand the system they maintain?
I guess that depends whether the genAI maximalists turn out to be right.
What happens when there’s an outage though? Just hope the LLM can fix it? Who is on the hook if it can’t?
Do you have people frantically trying to reverse engineer a basically unfamiliar-to-them code base at 2am while bleeding cash?
> Does it matter if the developers understand the system they maintain?
Are they maintaining it if all they do is type prompts into Claude?
Would you rather have one cookie now or two cookies later?
CTO responded well to it - frankly because we're all using some coding agent and it's just the natural process of code review for them to sniff things out. No mention of it in any PR summary - CTO found it in the migration that would mutate the User record to accept `null` email.
100% important. But what decisions do you care about seeing?
The whole point of the agent is to make decisions for you. If you want to make every little detailed decision, just write the code.
The whole art of this problem is figuring out which decisions matter to you, and how to surface them.
(Disclosure: we're working on this too. https://tern.sh)
How does your solution differ from OPs?
edit:
To me it looks like yours has the following negative qualities:
- closed source
- requires signup for some service
- says code doesnt leave my machine but this connects to your servers
- requires Goose AI as a dependency
So, we tried feeding the logs back to the LLM, and it mostly produced slop. Lots of decisions nobody cared about. The biggest things that moved the needle were:
- Baseline it. We mine previous logs, github comments, etc. for "what you care about." That helps pull out decisions that you actually care to read.
- Anchor to code. "The code enshrines this decision" is more interesting than "the agent self-talked this." Agents don't always self-talk decisions, and the thing that ultimately matters is the behavior in code.
Your .ai/why/main.md is at 97KB and 148 entries. Does anything prune that, or does a long-lived branch keep growing?
Well done.
This is not just Claude’s behaviour :)
It could be used for every agentic coding as well, because I have experienced such mess so many times in last three years.
One issue repaired, another one touched and changed…
thank you so much! started with a Claude Code adapter, but you think Codex would be a good next one?
This is what commit messages are for.
> Decisions only, never your messages
For me this is basically the opposite of how it would need to be, the decisions are all in my messages to the agent, almost never directly in the agent's replies, sometimes indirectly though I suppose.
Interesting to see that apparently some people use these tools and are the ones listening and doing what the LLM decide and says, rather than the opposite.
> Ran a blind eval before shipping, published it including the misses (REPORT.md). Agents with Grepathy answered the "why" questions right. Baseline agents made up confident wrong answers.
Is this eval public anywhere? The whole ecosystem severely lacks transparency, and people continue making strong claims without any sort of data or results that backs these up. Is there any public somewhere backing up the idea that it's more accurate that just using whatever agent harness?
> Claude made a decision nobody approved
It irks me a tiny bit that this is essentially clickbait, you don't know for sure Claude "made a decision nobody approved" as you've lost the data because you never thought sufficiently about storing these things in the first place. Most likely it misunderstood you at one point, you didn't carefully read the reply and approved it all, so most surely what you've done lead to that being done. These big models hardly ever just randomly do whatever, you can more often than not trace it to something you did wrong.
> I didn't know! I didn't make that decision!
Thanks for today's dose of impostor syndrome cure.
I recently took a small contract to help a vibe-founder de-vibe his project a bit. One hour with him has done more for my confidence as a developer than all the good work I’ve done this year. When probing for answers about the app and system he (lovable and Claude) had created he legitimately could not answer a single question and has almost no idea how anything works, even though there is a public web app that is capable of taking subscription payments from authenticated users. We’re living in strange times, and a giant pile of shit is coming at us like floods and tsunamis. If you’re patient and nice to talk to I imagine there will be good work available with which to flex your “I know what I’m doing”
Couldn't this just be in git commits and give the a skill to look there?
> The reasoning was in a transcript on my laptop. Claude Code deletes those after 30 days by default. Two of my projects lost their whole history that way.
Wait what? Claude Code (and Codex) transcripts are auto-deleted??
That's a treasure trove of information for all my projects and I had built some tooling and workflows tahat deal with extracting insights from them -- withut ever realizing I mightbe losing old chats. Thanks for this -- I may need to include an archival step for retention.
Horrifying, isn't it?
Amazing to me how little these companies respect the historic value of the transcripts. Most of my work is captured in them now.
> "cleanupPeriodDays": 99999
Throw that in ~/.claude/settings.json
Yes but it's just a setting you can change I don't think you really need an archival step
I use https://usegitai.com/ and https://ctx.rs/ to preserve and search them.
Can we get the transcript of the session where you had Claude write this post? I want to understand the "why" behind this project, and whether a human being was at any point involved in the "blind, pre-registered evaluation of Grepathy against an honest baseline".
[flagged]