broast

The way frontier models work, that loop will get compressed to a one-shot within a version or two

Most ai output is meant for other ai's to read, in my experience. The humans job is to compress it for humans

I prefer to have the LLM ask me the questions

many of us work with swarms of cheap off-shore contractors and have to rewrite or finish their code already as it is. The llm is much lower friction

Don't they eventually become managers and tech leads anyway and outsource to their staff?

On the discussion of the right or wrong tool, I find it possible that the ability to reason towards a goal is more valuable in the long run than an intrinsic ability to achieve the same result. Or maybe a mix of both is the ideal.

It's essentially the same as an engineering lead writing a good jira ticket

Prompt engineering is just good transfer notes and ticket writing, which is something a majority of the devs I've worked with don't enjoy or excel at

But what about their two year head start? If everyone is executing at the speed of light, there will still be winners and losers

So cool, I think all kids would love this

Hey! Cool! I've been making this too: https://github.com/broast/aipageeditor

Looking forward to trying it and see how far it takes the vision. Tweaks looks capable of very cool and useful things :)

Good work. I've been thinking about this for awhile and also experimenting with letting the LLM do all the work, backend logic plus generating the front-end and handle all front-end events. With tool use and agentic loops, I don't see any reason this can't work where it meets the latency needs (which hopefully could be improved over time).

I think every single Windows release has necessitated some registry hacks to bring back useful features from the previous version

I've had a flip 3 and flip 5 which both had screen and hinge problems within a year. I love the form factor but just don't take it to the beach.

My flip 5 inner screen is currently unusable so I'm stuck using the small square cover screen which I'm enjoying quite a bit too. I don't know if my next phone should be a flip phone or a small phone, but nothing gets as small or as good hardware as the front cover of these flip phones, vs other small phones

It's the cover screen of my zflip 5 with the inner screen being broken. It's surprisingly usable and I find myself wishing more phones were purposefully built at this size and shape.

My mobile device is a square aspect ratio and thus there is no portrait mode to check this out :(

So basically what an engineering manager or product manager enjoys doing

> it will be harder to find someone to talk to understand what they were trying to do at the time.

These are my favorite types of code bases to work on. The source of truth is the code. You have to read it and debug it to figure it out, and reconcile the actual behaviors with the desired or expected behaviors through your own product oriented thinking

Uploaded my own sci-fi art and was amazed by the result

I definitely have

I'm a bot

The only feature I need that would accelerate my workflow that text file editors don't currently have is a column with the last modified timestamp of that particular line, and maybe some color indication to show which lines were modified the most recently compared to others. And this would be based on change, not based on save or commit.

Reading code is just as fun as writing it, to be honest

It's taken Cisco 25 years to recover

This tool just made me realize I've been vibe coding at years for work as a manager. Great job, this is a game changer so far for me!

I wonder how effective it would be to finetune a model to remove jailbreaks from prompts, and then use that as part of the pipeline into whatever agent

If they waited to know the outcome then it wouldn't be a probability

Chatgpt itself has gotten much better at producing and reading code since a year ago, in my experience

As I understand, anki's use of spaced repetition comes from how it presents you cards in increasing or decreasing frequency based on how you have answered it previously. In this way, I prompt chatgpt to ask me questions, and it revisits previous questions or topics for me based on how I've answered previously. I continue the same conversation periodically prompting it for questions to ask me.

I just let chatgpt quiz me anki style on topics I'm learning