Not always, but enough that I consider it a thing to fire in a direction, not a thing that aims.
4,197 karma · joined March 1, 2008
Not always, but enough that I consider it a thing to fire in a direction, not a thing that aims.
If it works. And I’m not sure who is going to buy the stuff the machines produce, but shrug. Presumably some bots click ads for NFT’s that other bots generate.
I also think it spends most of its iq on sounding good rather than thinking about the problem. “Yeah absolutely I can see why you’d like to…” etc. This is likely because it’s on a timer and maybe voice is more expensive to process? Text responses spend more time on the task.
Problem for jobs is that there are 200 countries and all the earnings will go to a few. Universal basic income for everyone? Or just the US?
Who gets to keep their house locations in a new fair world? The person whose parents bought in the right place 50 years ago? Who pays the money these models earn, if nobody clicks ads or does a job? What is income for if we don’t work and can just ask the AI for everything we want?
What happens when the super smart AI comes up with “better” (more fair, consistent, etc) answers than you think you have to questions like the above? What if they end up socialist? Do we force it (and invite risk it escapes and fights us for the greater good) or give in to the presumably more thorough reasoning?
I remember seeing a PC one of the rich kids brought to boarding school in 1990 and realising it was just crisper than my A500. The PC’s in the school lab were all green and orange screens with one colour CGA, so this was quite a surprise. Still took me some time to accept reality :)
Still using Claude for UX (playgrounds) and language. OpenAI has always been a little more cerebral and stern, which doesn’t suit those areas. When it tries to be friendly it comes off as someone my age trying to be a 20-something.
Text includes:
Invoke each review/audit skill in sequence. Each skill runs its own comprehensive checks and returns findings. Capture the findings from each and incorporate them into the final report.
IMPORTANT: Invoke each skill using the Skill tool. Each skill is independently runnable and will produce its own detailed output. Summarize findings per skill into the unified report format.
4. Architecture Health
Invoke: Skill(architecture-review)
Covers: module boundaries, cross-module communication, dependency direction, infrastructure layer rules, hexagonal architecture compliance.
5. Security Health
Invoke: Skill(security-review)
Covers: hardcoded secrets, SQL injection, authorization, HTTPS, CORS, input validation, authentication patterns.
I think these token doubles are there to kick you into a abundance mindset (for want of a better term) so going back feels painful. Stop counting tokens, focus on your project and the cost of your own time.
https://www.businessinsider.com/openai-chatgpt-vs-gemini-web...
"What's you number one piece of hiring advice?"
"Hire for slope, not Y-intercept. This is actually my number one piece of life advice."
-@sama, who I’m generally a big fan of. But the job is now harder
I manage the shit out of FB and YouTube. You need to block a few things so it stops testing a few segment ideas.
It won’t do the absolute fastest tasks in the stack quite as well but supposedly the coding speed and memory management benefits are more important, and there’s no GC so it’s reliable.
…If every time you looked at the dictionary it gave you a slightly different definition, and sometimes it gave you the wrong definition!
It basically stumbles around generating tokens within the bounds (usually) of your prompt, and rarely stops to think. Goal is token generation, baby. Not careful evaluation. I have to keep forcing it to stop creating magic inline strings and rather use constants or config, even though those instructions are all over my Claude.md and I’m using the top model. It loves to take shortcuts that save GPU but cost me time and money to wrestle back to rational. “These issues weren’t created by me in this chat right now so I’ll ignore them and ship it.” No, fix all the bugs. That’s the job.
Still, I love it. I can hand code the bits I want to, let it fly with the bits I don’t. I can try something new in a separate CLI tab while others are spinning. Cost to experiment drops massively.
What’s wrong with this logic? Any insiders willing to weigh in?
And almost every time it screws up we create a test, and often for the whole class of problem. More recent it’s been far better behaved. Between Opus, skills, docs, generating Mermaid diagrams, tests it’s been a lot better. I’ve also cleaned up so much of the architecture so there’s only one way to do things. This keeps it more aligned and helps with entropy. And they’ll work better as models improve. Having a match between code, documents and tests means it’s not just relying on one source.
Prompts like this seem to work: “what’s the ideal way to do this? Don’t be pragmatic. Tokens are cheaper than me hunting bugs down years later”
I expect China to want to compete with this. Simpler than full-blown Nvidia chips. Cue much cheaper and faster inference for all.
https://github.com/sebastienros/comptime/blob/main/test/Comp...
But you need to be sure you won’t want to change without compiling.
1000’s of calls per second? That’s a lot of traffic. Hide it in Claude which is already doing that kind of thing 24/7. Wait until someone uses all models at the same time to hide the overall traffic patterns and security implications. Or have AI’s driving botnets. Or steal a few hundred enterprise logins and hide the traffic that is presumably not being logged because privacy and compliance.