I can't be the only one to think it is silly to interact with tools in this way. Honestly, I see skills, "hooks", and other monkey-patch efforts as things that will be short-lived investments, weird kludges from an era where you had to "hand-crank" your AI, more often. Something to go the same way as using HTML tables as bastardized CSS
Because a deterministic shell around the model gives the best of both worlds. It’s able to achieve its goals but you define what “done” looks like and deterministically enforce checking of that in a way the model can’t cheat its way out of or forget to check on.
Yes an no. Some skills are very very tuned to our own workflows. The model providers may come up with some similar alternatives but not always. Also, sometimes you need a solution now and not in three months.
I might not be smart enough to grasp what you're saying because it sounds a little ridiculous to me.
Do you mean the AI will "figure out" how to just do the things we use skills and hooks for today? Do you understand the difference between deterministic and probabilistic behavior and why the difference matters a lot when doing technical tasks?
The entire point of hooks is deterministic responses to signals from the LLM. You run a function in response to some event and the function is given json data that conforms to a specific schema.
Hooks are meant to be 'deterministic' because they are only used for executing scripts on a specific step. So, for instance, you can execute your lint on PostEdit so every time it edits a file in your project, the harness runs your linter.
With that said, part of hooks is you can return a json object to the agent which gives it instructions such as stop, continue, etc but those to my understanding are all very explicit constants rather than loosey-goosey prompts you can pass it.
If this person looked into hooks more, they could write a script that would run their project's tests and then tell Claude to stop if tests end via a non-0 exit code.
Bro, the gazzilion DIV inside DIV spilled nonsense by all these modern frameworks is driving me crazy. TABLE as bastardized CSS is instant rendering. But hey, you're young, I get it.
It's silly until you realize how similar they are to the weird kludges we apply when we need to get deterministic behavior out of humans. Airline pilots have a number of "skill files" (although they call them checklists) which they open and use on an as-needed basis, and are trained to respect a number of "hook" conditions when specific actions must be immediately performed.
Terrible, honestly. Betrayed, gaslit. Don't tell me it's just a tool and it's my problem...hell no, fix your stupid tool. The whole point is to immerse yourself so you don't feel any different than having an energetic and resourceful junior or some perhaps limited but useful companion at your beck and call. If that illusion drops, it's on the tool.
Delightfulness? I'm seeing some indication "delightness" may be a word (can't say 100%)...but it seems a poor substitution for IMO the natural version of it
It’s a “pun” on the phrase “simplify, then add lightness”. Which is a car design philosophy that amounts to “it’s easier to make a car lighter than it is to put in a bigger engine.”
This conservative approach is widely useful. For example, beginner-to-intermediate tennis games are frequently won by the player who made fewer mistakes, rather than by the player who had more flashes of brilliance.
They are utterly cooked. The only ones I've ever seen on the "it's not so bad" side of this argument are aloof boomers and anyone young enough to never have experienced at least a good swath of the 90s--i.e. has no truly visceral basis for comparison/has no clue how bloodless and sick the vampires have left society
Is there no pipeline--or a job fair? A way to get a moment with prospective employers? It seems tragically stupid if MIT offers no such thing. Applying into the void seems like a fool's errand.
I think as-applied now, the author's take strikes a chord with me. LLMs are a technical marvel, but their results feel very cheap and tacky...it doesn't take much to catch at glimpse at the fallible man behind the curtain. They are lauded more for how impressive the illusion they render all things considered more than what they are actually GOOD FOR. Weird hallucinating search, smart but untrustworthy coding intern...people hold these things up in a way that suggests we've arrived instead of acknowledging their disappointment and saying "yes, there is a lot of power here, but we still haven't found the killer application or the thing that takes this from an impressive but flawed trick to indispensable".
That’s a glib, low effort dismissal but it makes sense if you consider it.
It’s like people that kept going to the library even with Google around. You’re not playing to the strengths of AI and relying on whatever suboptimal previous method you used to find the answers. It does really, really well with very specific queries with a lot of looks ups and dependencies that nothing else can really answer without a lot of work on your end.
I mean if my dentist adds a Helpful Super GenAI Infused Chatbot that can't book appointments or answer any questions about their services no amount of "you're holding it wrong" insistence about LLMs in general will actually make it useful to me.
The point is ChatGPT's wild success doesn't automatically mean consumers want and possibly will never want a chatbot as their primary interface for your specific app or service.
That sounds terrible! Some people just take these things in stride I guess, but I have no interest in going through these kind of hurdles for something like this...
Yah, good luck with that. Anyone who has played competitively knows you will absolutely get stomped by a higher skill opponent even if your deck is more powerful on paper unless the discrepancy is ludicrous. Garfield made his game too well to fall to such trite criticisms...he outdid himself, its immune to his own potshots, lol
That floor is pretty dang high though. It both has one of the highest costs of entry for pretty much any game (to be fair, it does change with format, but it's basically a choice between paying a lot upfront or effectively a subscription), and the advantage you have scales quite substantially with the amount that you spend (though not quite as much as some mobile games). 'pay-to-win' is a valid criticism, even if skill still matters to some extent.
reply