I don’t support this endeavour but “you are at 123 Fake Street at 9:47am on Thurs May 7” vs “you are in the area of Fake Street/Sham Town on a Weekday Morning”.
Can you link to a changelog that shows the 5-10x feature increases? I keep hearing this, but I don’t see anything I use ever actually shipping like this, or people backing this up with any sort of proof.
That reminds me of a chart I saw posted in HN comments recently that someone created tracking bullet points in Claude Code release notes per day that was cited as "proof of a step change" in AI development over the last year. It showed like a dozen or so on average that jumped to to like over 50 one month and stayed around that number.
So I looked at the most recent CC release notes on Github and the majority look like this:
Fixed /clear not resetting the terminal tab title after a conversation
Fixed session title chip from /rename disappearing while a permission or other dialog is active
Fixed agent panel below the prompt being hidden when subagents are running (regression in 2.1.122)
Fixed external-editor handoff (Ctrl+G) blanking the conversation history above the prompt
Fixed /context dumping its rendered ASCII visualization grid into the conversation, wasting ~1.6k tokens per call
Fixed OAuth refresh race after wake-from-sleep that could log out all running sessions
Fixed 1-hour prompt cache TTL being silently downgraded to 5 minutes
Fixed cache-miss warning appearing spuriously after /clear or compaction when changing /effort or /model
I'd be extremely interested to know what percentage of these were just fixing last week's Claude Code written PR that no human ever set eyes on.
But hey, all that churn looks great on charts being circulated on social media as free advertising for their flagship product (and consequently the company's valuation) so never mind, LGTM!
I don’t think we will though. Because the “short game” is match the requirements of the agent operator. If we don’t care about the finer details that we let the LLMs infer, then we shouldn’t care if a human infers them (but yet we do).
I think LLMs are great, and I think people who can use them to get to the green in one and take it from there will soar, just like people who could identify a problem and solve it themselves did in the past.
> which is expected if the models are in fact getting better at agentic coding
Is it? Or is it also explainable that the models are not getting better but people are still adopting it.
If the models were getting we’d be seeing mobile apps with new features at 10x the rate previously, or websites with 4 times the number of features. But we’re not.
Honeastly though, I get it. If you have headcount for two people, do you want one of those people to be a DBA and another to be a platform architect? Whos going to actually make the app.
I genuinely think the problem is that frameworks don't do this for you. Why should you need a DBA and platform architect to make a multi tenant CRUD app, pretty much every one does the same thing..
Security minded generalists exist. They might move slower than you expect of a MFBS (move fast break shit) engineer, but you might also end up with fewer issues later.
there’s always some senior-ish person in the interview pool who is interested in security. hire them, let them figure things out and then give them permission to call bullshit on what you’ve done so far.
avoid hiring the “fanatics” tho. you don’t need E2EE everywhere.
The thing about an SLA is that once you’ve broken it you’ve lost the trust. It doesn’t _really_ matter what the cost is for breaking it, nobody chooses their platform based on the refund they’ll get if they’re down. But they absolutely do choose based on reliability and uptime. The enterprise SLA refund credit will show as a (big) metering blip, but the problem is the people who signed the contracts are going to be speaking to Gitlab now
reply