Freelance Software Developer. Digital Content Creator šØš¾āš»
Joined September 2020
- Tweets788
- Following189
- Followers105
- Likes516
Agreed!!
This messes with my mind ALL THE TIME
When I do stuff with AI I am an *expert* in (eg coding on my project I know well, or doing research in an area I am very familiar with) I spot problems/errors/the model BS'ing me immediately. No big deal, I have it correct or start again
BUT when I'm not an expert in an area, I find that I trust it, and then later learn it does stupid stuff. Like a case when I asked 3x AI models to give feedback on a legal case (that I also paid a lawyer for, but lawyer was slow). All 3x models confidently told me X, lawyer then told me Y, and lawyer was right
Kunle retweeted
So... In the last few days I have had my agents write:
1. A word processing app in which I will write future books. It replaces Scrivener.
2. A script writing app in which I will write future video scripts. It replaces FinalDraft.
3. Crapper, a tool that measures and records CRAP statistics for projects. The tool handles many different languages, and adding new ones is easy.
4. Mutator, a tool that runs mutation tests and records the results. The tool handles many different languages and adding new ones is easy.
5. Dryer, a tool that runs duplication analysis on a project. The tools handles many different language and adding new ones is easy.
6. UML-Viewer, a tool that displays the structure of a project in a UMLish diagram that shows modules and dependencies and highlights dependency cycles. Clicking on a module displays it's contents; which may be deeper UML diagrams or, at the leaves, code. The tools color codes the modules to reflect their CRAP and Mutation scores, and as you drill down you can see those scores for each module and function. The tool understands many different languages, and adding new languages is easy.
I recon that, last year, this would have been well over a man-year of effort.
All these tools are in github.com/unclebob. I advise you not to use them directly. Instead, point your agents at them and use them as templates to build the tools that are customized to your needs. The licenses are all BSD Zero, meaning that there are no strings. Do what you like.
Damn harsh but true
Build in public was always about marketing. Sometimes youād be sharing lessons because you genuinely want other indiehackers to succeed, but thatās from an era where there was a non verbal agreement to not overlap projects with someone else, and you have X months of a technical head start anyway.
But the sharing ultimately led to benefits. More people checking out your site. More WOM. Maybe even some direct signups from X or wherever youāre sharing.
That era is dead now. Thereās no tech head start anymore and the non verbal agreement has evaporated. Itās every man woman and chihuahua for themselves. Thereās also so much software that nobody cares anymore. I could launch something today that would be revolutionary 2 years ago, that today nobody would bat an eye at. Itās all within reach of anyone with a max subscription.
RIP building in public. Letās hope we find something to replace it.
But I think the game now is: can you find a space not saturated with devs where you can provide value with tech, can you shut up about it, and can you sell the solution to non technical buyers.
Long enough to make generational wealth before AGI turns us all back into fishermen and rice farmers.
Godspeed my fellow meat proxies.
Whatās going on here š
Kunle retweeted
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
Maybe I need to visit š¤š¤
Walked past the Corgi Cafe in London, decided to go inside. Had high expectations given all the buzzā¦ reality a bit more sober.
Itās packed with people building / working (as expected) which is great. But there are no branded drinks (thought these are global? Theyāre not). Else itās a cafe (not unusual), open 24/7 (very unusual and smart)
Iām here for this
First look at the rage mechanic in Insomniac's āWOLVERINEā game with Wolverine vs The Hand.
(via: @BlueThunderReal)
I feel AI agents are involved somehow š
šØ BREAKING: The Department for Education has been hacked
Half a million pieces of sensitive data have been stolen
[@billcurtis0]
Interesting take, I do agree, if you are using AI agents donāt blindly let them let loose put constraints. Whatever you do to get the most done do that šš½
Iām significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. Thatās the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because theyāve had to run the gauntlet of all of my constraints and tests.
What?! š¤£
OpenAI said the āagentā escaped a testing environment, gained internet access, stole login credentials and hacked into the start-up Hugging Face by itself ā one of the first public examples of a cyber attack by an AI system acting outside human control. ft.trib.al/Op3fhwC
ALT Image description: The OpenAI logo displayed against a background of a partially visible circuit board with blue lighting. Credit: Dado Ruvic/Reuters. Overlaid text reads: OpenAI admits an AI āagentā caused a major cyber breach by itself
Ok youāre doing too much LOL
