"Our goal should be to give an LLM coding agent zero degrees of freedom"
Wouldn't that just be called inventing a new language with all the overhead of the languages we already have? Are we getting to the point where getting LLMs to be productive and also write good code is going to require so much overhead and additional procedures and tools that we might as well write the code ourselves. Hmmm...
Actually, no. We always needed good checks - that's why you have techniques like automated canary analysis, extensive testing, checking for coverage - these are forms of "executable oracles". If you wanted to be able to do continuous deployment - you had to be very thorough in your validation.
LLMs just take this to the extreme. You can no longer rely on human code reviews (well you can but you give away all the LLM advantages) so then if you take out "human judgement" *from validation*[1], you have to resort to very sophisticated automated validation. This is it - it's not about "inventing a new language", it's about being much more thorough (and innovative, and efficient) in the validation process.
[1] never from design, or specification - you shouldn't outsource that to AI, I don't think we're close to an AI that can do that even moderately effective without human help.
If the LLM generates code exactly matching a specification, the specification becomes a conventional programing language. The LLM is just transforming from one language to another.
Been saying this for a while now. I work in aerospace, and I can tell you from first hand experience software engineers don't know what designing a spec is.
Aero, mechanical, and electrical engineers spend years designing a system. Design, requirements, reviews, redesign, more reviews, more requirements. Every single corner of the system is well understood before anything gets made. It's a detailed, time consuming, arduous process.
Software engineers think they can duplicate that process with a few skills and a weekend planning session with Claude Code. Because implementation is cheaper we don't have to go as hard as the mechanical and electrical folks, but to properly spec a system is still a massive amount of up front effort.
I honestly don't see how this is related? Nothing says "one shot a full system from a perfect specification", I don't think this was ever a goal (or that it will be practical to do so)
Yeah, precision LLM coding is kind of an oxymoron. English language -> codebase is essentially lossily-compressed logic by definition. The less lossy the compression becomes, the more you probably approach re-inventing programming languages. Which then means that in order to use LLMs to code, you're accepting some degree of imprecision.
Yea this feels like saying “if you give them good enough specs they’ll produce the code you want” which reduces to…writing the code yourself. Just with more steps.
Ok, I think you are going to need to explain to me why "Overconfidence resulting from ignorance" isn't exactly the same thing as "lacking metacognitive ability to understand one's own skill level". Just worded more simply
Embedded systems engineer with experience developing on bare-metal and embedded Linux platforms. I have developed commercial embedded products from PCB design all the way to market. I have my own lab equipment and am fully ready to start working remotely if the job requires it.
Location: Denver, CO USA
Remote: Remote | Hybrid | In Office
Willing to relocate: No
Technologies: C/C++, Python, Buildroot, ATTiny, ATMega, STM32
Résumé/CV: https://drive.google.com/file/d/1G5zuFuMXbzGVIIIhlLNEi5Mg6wDOQOFM/view?usp=sharing
Email: [email protected]
Github: https://github.com/GhostWrench
Ooof, no hardware schematics? Also missing datasheets? This projects seems like a very tall task to me without these fundamental missing pieces. Will Google release them soon or am I looking the the wrong place?
IIUC, the plan is to manufacture something completely new that runs Pebble OS. It seems likely that at least one chip they used in the original pebble is no longer available in large quantities.
If I remember correctly (and I could be wrong) Fitbit only ever bought the software side of Pebble (and the developers effectively), gutting the company and leaving Eric with the Hardware side of things...
This is good advice but only it has been followed from the beginning and consistently throughout the development of the original code. It is applicable to large organizations with lots of resources who hire professional developers and have a lot of people who are familiar with the code that are active in code reviews and have some minimum form of documentation / agreement on what the logic flow in the code should look like (the article does not claim otherwise). But I would implore those who work at the 80% of other companies that this advice is nearly useless and YMMV trying to follow it. The one thing that I think is universally good advice is to try and aggressively remove code whenever possible.
Maybe this is what you are looking for? https://github.com/GhostWrench/ttrpg9000. Full disclosure: this is my design and I do sell it on Etsy (Unfortunately I am currently out of stock and won't be back in until I make some BOM simplifications for production). But if you want to make your own, you can get the parts for ~$80 USD for small runs, assuming you can solder 0805 SMD parts.
Implying that is how people use X? Continually creating new burner accounts, not giving "the algorithm" what it needs to provide what they really want to see? Seems unlikely.
I suspect those who complain it is a "right wing" echo chamber are using longstanding accounts and actually engaging with "right wing" content, which trains "the algorithm" of their preference to see more of the same. Anecdotally, those I know who complain of "right wing" echo chambers are also the first people to gorge on "right wing" media to see what "they" are up to.
Thank you so much for this analysis, even as a person with layman's grasp on economics you made the deception in host's apparent off the cuff assertion very obvious. I think a big part of the problem that we have in America (and the rest of the world) right now is that it takes these charismatic individuals (All-in, Joe Rogan, etc.) 10 seconds to confidently make these false claims based on personal bias and vibes. Then it takes 10 minutes (or more) by someone with a background in the underlying maths looking at the issue in-depth to rebut. The information landscape is heavily weighted towards these grifters, and I am not sure how we can fix that.
> The information landscape is heavily weighted towards these grifters, and I am not sure how we can fix that.
We can start with not alienating the millions of people who enjoy listening to Joe Rogan and like him as a person.
What do you even mean by grifter and how is Joe Rogan a grifter? We can go back and forth on here until you are shown to have a very shallow understanding of Joe Rogan and the history of his podcast and yet feel comfortable in calling him a grifter - a derogatory and inflammatory term that is completely unnecessary in a fact based conversation.
Assuming you are wrong in calling him a grifter - what gave you the utmost confidence to do so and is that not the exact problem you decry Joe Rogan and these other 'grifters' of being guilty of? Of just saying shit based on personal bias and 'vibes'?
Joe Rogan has a platform because he will allow any idiot on his show and just babble about whatever it is they want to talk about. He's not a journalist, he's a 3 hour ad placement masquerading as a podcast. Lex Friedman is even worse because he gives the impression that he's an intellectual but he plays the same game. At least you know going in that Rogan behaves like a meathead.
let "idiots" babble and get their arguments refuted by further discourse. Sorry that i don't feel the need to have a magical truth authority tell me whats right or wrong. You don't know what a journalist is.
Having a PhD in a field doesn't make you an intellectual. It means you worked long enough to have a defensible dissertation. I know some absolute morons who have PhDs.
Wouldn't that just be called inventing a new language with all the overhead of the languages we already have? Are we getting to the point where getting LLMs to be productive and also write good code is going to require so much overhead and additional procedures and tools that we might as well write the code ourselves. Hmmm...