Viewing profile — wokwokwok
wokwokwok
HN member- Joined
- Wed, Feb 28, 2018, 12:47 AM UTC
- HN karma
- 5,628
- Public activity
- 1,112 items
- HN profile
- View on Hacker News ↗
About wokwokwok
No profile information was provided.
Recent public activity
-
comment
Comment #49066474
It’s remarkable (but not reassuring) how carefully they avoid saying “part of the Atlassian family” in any promotional material for some reason.
-
comment
Comment #47270811
On the other hand, the parent post is entirely correct . What, I ask, is the point of having laws and rules if you can just ignore the ones you don't like? Its just a name, who car…
-
comment
Comment #47244780
I really like the idea of agent coding patterns. This feels like it could be expanded easily with more content though. Off the top of my head: - tell the agent to write a plan, rev…
-
comment
Comment #47108307
This is the way. The practice is: - simple - effective - retains control and quality Certainly the “unsupervised agent” workflows are getting a lot of attention right now, but they…
-
comment
Comment #47021355
This is irrelevant to the point. Using nano banana does not require arcane prompt engineering. People who have not learnt image prompt engineering probably didn't miss anything. Th…
-
comment
Comment #43925895
How can a question that is: 1) clearly technical 2) reproducible 3) has a clear failure condition Not be a suitable candidate for S/O? Did we step into a dimension where only "How …
-
comment
Comment #43925837
How about making it a site where only people who answer questions can even be eligible to be moderators? What if moderators had to actually have karma from recently answering quest…
-
comment
Comment #43847535
You’re being down voted because you’re not saying anything meaningful. Yes, you can argue that [person] is [performing an action] because they believe, from their POV that [reason1…
-
comment
Comment #43521082
You are not an expert in this field, and cherry-picking random articles in random journals does not make you an expert. > Should I pick some other experts to listen to? I think it'…
-
comment
Comment #43521040
If you're not prepared to listen to an expert, and that's what your dentist is on this topic , then nothing I, or anyone else can say, makes any difference to you. At some point, y…
-
comment
Comment #43520928
Talk to your dentist. They are experts in this field, and, unlike “random person on the internet who spent 2 minutes on google”, have informed opinions on this topic. If you want a…
-
comment
Comment #43407721
> However, what's wrong with allowing another app to post messages to my messages? > If I don't want it, let me turn them off. Can you it off for anyone sending you messages too? T…
-
comment
Comment #43338325
Because running a parallel process is often difficult. In most cases, the question becomes: So, how exactly is my app/whatever supposed to spin up a parallel process in the OS and …
-
comment
Comment #43200783
There's no distinction to me. AI is hard; edge cases are hard. AI sucks at edge cases. Between AI for cars and AI for software the long tail of edge cases that have to be catered f…
-
comment
Comment #43169772
> My estimate is that 80-90% of the code was written by AI Nice! It is entirely reasonable both to do that and to be excited about it. …buuut, if that’s what you’re doing, you shou…
-
comment
Comment #43168481
"no lines of code directly written, just directing the AI" /skeptical face. Without fail, every. single. person. I've met who says that, actually means "except for the code that I …
-
comment
Comment #42905805
> As for specific examples NHS has some terribly overwhelming forms and processes - image search IAPTUS. Are those example where a chatbot helps fill out the form, or just examples…
-
comment
Comment #42905773
> You would need to spend thousands of dollars to become a customer, if you are not already one. Can you be more specific? Like, where specifically would I have to spend money to s…
-
comment
Comment #42895905
I'm sure there's a time and place for these things, but this sounds very much like the echo chamber I hear at work all the time. Someone has a 'friend' who has a totally-not-public…
-
comment
Comment #42765903
If you’re a research lab then yes. If you’re a for profit company trying to raise funding and fend off skepticism that your models really aren’t that much better than any one else’…
-
comment
Comment #42495350
> but that overwhelmingly doesn’t work. MCTS will be the next big “thing”; not agents.
-
comment
Comment #42493006
I didn’t say they don’t work, I said there is an upper bound on the function they provide. If a discrete system can be composed of multiple LLMs the upper bound on the function the…
-
comment
Comment #42491891
We already have agentic systems; they're not particularly impressive (1). There's no specific reason to expect them to get better. Things that will shift the status quo are: MCST-L…
-
comment
Comment #42396560
> “Lighter” may be used as an alternative adjective to the word easy or easier That is, again, not common usage, there’s a word for easier to use; it’s “easier”. but whatever. It d…
-
comment
Comment #42389344
How do you compose low level operations like “click here” into composable modules like: loginAsUser(user) id = createBooking(user) loginAsAdmin() approveBooking(id) ? Is it the sam…