bredren
I suspect both old codebases and new ones that have a very intentional architecture are both dangerous to let loose.
The agent doing the fixing must have not only an incredible map of the project and how it is put together, but the ability to reach into annotated examples in the past and refer to them as it goes about a fix.
I’m seeing that frontier models will not follow intended patterns or know when to deviate if their primary charge is “fix this bug.”
It is perhaps a better idea to have agents’ primary job be “maintain this codebase” and one way that they do it is to fix bugs, and “oh by the way here is a bug.”
Growing up in the 80s everything is white folks or animals but almost always it is about a boy or boys.
I think the baby books are still board books. Cordoroy’s Shapes is part of what I remember about our first’s earliest years. Reading it over and over. We even did a first birthday theme for it. My mom made triangle tarts.
After that they are floppy picture books. I suppose at this scale is is probably both economical and reflects some of the material involved.
That is just fine, though it’s just not the same as holding a hardcover.
Our kids don’t care about that, though. It’s more about the time and talking about the pictures and how well we ham it up.
The evidence of hack is the feature.
I wonder if this would turn even the most stalwart opponents around.
I could see discussion about such an announcement focusing on exactly what qualifies as an "alien."
Your use case here is beyond mine, but I have used custom tooling to handle contractor bid process workflows for projects at our home.
AI applied to products will allow people to not only consider but actively move on changes that did not seem reasonably possible before.
PHP2SHELL, in particular, made me expand my weekly security review to include my external network resources.
The natural conclusion for this seems to be realtime monitoring CVE and pre-CVE vulnerability indications in exposed stacks.
The Foundation models keep a surprisingly decent set of data available for fast filtering by a local LLM.
I’ve found a slower, second pass, is needed by Qwen to clean it up. (I am running on the new Mac Mini m5 pro 64gb.)
I’ve run my own tests using a date range, a short description of a red cedar planter box build I did last year, and a set of known correct photos.
There is some cool stuff you can do without sending your family’s pics up to any of the frontier model providers.
Because the scrapes become more interesting once combined with such information.
It has all the expected controls.
It can be an acceleration when wielded by someone who can keep the model focused.
I was wondering how he has adapted to using LLMs. If they might have significantly advanced his work.
These companies see the interfaces with the customer moving into domains they lack the taste and capability to compete.
They want to own that channel even if it is to spam them with ads like BMW did with the Spider-Man “special feature.”
Or Chamberlain has (reportedly) playing with the location of buttons and ads in their “app.”
Rivian, BMW, Chamberlain have the market dominance to ignore what customers want.
Jetbrains does not but had / has to try.
Bill would attend both events in support of Tim and Adam. I had a great experience with both the Drapers as a founder.
One time, while living with my cofounder in the hotel Tim was restoring in downtown San Mateo, I broke the hotel elevator.
The laundry was on the basement level and ~everyone used this brick to prop open the door so could dash to the laundry move it to the dryer and dash back without loosing the car.
Well, the brick was not well propped and somehow the door pushed it to a point where it could close but also somehow carry it up the shaft.
Watching the door close it was just like, uh oh.
Up goes the elevator idk a few stories and then the sound of a brick tumbling down the shaft hitting who knows what.
Ya, the elevator stopped working immediately. I owned up to it the next day, writing Tim and offering to pay for what probably would have consumed all of our accelerator funds of damage I had caused.
He thanked me for my honesty and said not to worry about it.
Tim (and Adam) went on to invest in not one but two of my ventures.
Anyway, I realize this is about Bill but I think a person can be reflected in not only themselves but those that they raise and wanted to share this.
Oh and Bill, at least back then, did not think much of Bitcoin. :)
Sibling comment gets at the detail better, but it seems museums have dual roles: display some works for the public and preserve a much greater archive of work for progeny (?).
The public interest in viewing stuff doesn’t sound like it gets nearly the cachet as being ones who get to actually be close to the works.
FWIW, this sounds somewhat similar to ROM or many other digital “rarity” communities online.
I remember this happening in the Dave Matthews Band online community in the aughts (oddly specific but yes people with recordings that led to say the full leak of what became Busted Stuff) or to be one of the few who had heard a copy of “Build you a house.”
More recently I saw evidence of hoarding / gatekeeping in leaks of clean (master?) individual tracks from studio recordings of major artists.
I seem to remember celerity photo leak scandals that began as some kind of insiders only type thing.
I mention these examples because the human condition to hoard or derive power over the control of content is not unique to museum administrators.
That said, physical copies of rare human art are undoubtedly worth protecting.
However, I find the protection of digital descriptions of the works, especially given comment that they are likely not even unique, galling and not dissimilar to all the gate keeping examples I provided above.
This is site meta though, see footer for contact methods to get direct answers on stuff like this.
Wasn’t there a dive on Freddy Pharkus up on FP recently?
These kind of folks still exist and still create. There is a lot more noise to sort through these days.
Except they were not for past few years as they misfired on the attempt to compete with vscode. That had a big impact on pycharm, which seemed starved for resources for so long. The company eventually declared a year of Django, but even that failed to really make an impact.
Arguably, Jetbrains had first insight into AI based code completion via rapid rise of the TabNine plugin but missed that opportunity also.
"Early testers found its writing clearer and easier to follow, which addresses some of the common feedback we heard about Opus 5"
and
"We’ve made major improvements to the way Opus 5.5 writes and communicates, one of the most common areas of feedback we heard about Opus 5."
and
"In our own use, this has made Opus 5.5’s work easier to follow and check—which is a safety benefit as well as a practical one."
I realize it is corporate communications but "most common areas of feedback" and is a bit sterile. If the company wants authenticity and trust its easy to say that they found it hard to follow. And that it did not meet a quality bar they generally expect from their releases.
If this is not true, that it Opus 5 output was generally acceptable and we might see something like that again, that is an important consideration for potential customers or investors.
I don't remember seeing any RW content, but there was some John Lennon stuff. He was mostly in good taste, but I remember seeing something and being, uncomfortable with it.
I don't really see why Bob Barker should be any less protected, then John Lennon or Robin Williams. None of these people were saints.
But there is or at least used to be deference provided to certain people or establishments.
I haven't seen this video that was so upsetting, but perhaps it's not the reanimation so much as the content. Some of it is so obviously satire it's not to be taken seriously.
But, I remember somebody used Bruce Lee as a vessel to spread the gospel on Sora. I had to frown at that, as it was not how he would have behaved.
Contextify (https://contextify.sh)
It is an application for Linux, macOS and Windows that files your AI chats into a database your AI can read using a skill or MCP.
It backs up the valuable content of your Claude Code and Codex conversations (JSONL transcripts) and turns them into a complete history you don’t have to manage.
Use Contextify during normal flow of CLI AI conversations:
1. Resume unfinished work → "where did we leave off on that?"
2. Recover the intent/scope → "what was the actual goal of this whole effort?"
3. Verify it got done → "did we ever finish that, and which session proves it?"
4. Recall a fix → "how did we fix this the last time it broke?"
You can self-host and keep all data local or use the source available Contextify Cloud sync server so your history on all machines in your cluster or desktop and laptop are always backed up and immediately available for use.
I have not been a Windows user since the days of the Hackintosh. But urging here and from users to cover the platform pushed me into it and I ended up really enjoying the challenge.
Right now I’m working on an expanded version of the windows app and support for integrating a 3rd party local LLM.