Viewing profile — prettyblocks
prettyblocks
HN member- Joined
- Mon, Dec 30, 2024, 2:28 AM UTC
- HN karma
- 378
- Public activity
- 119 items
- HN profile
- View on Hacker News ↗
About prettyblocks
No profile information was provided.
Recent public activity
-
comment
Comment #49252306
In what dystopian black mirror alternate reality can anyone possibly perceive this as saving the profession of programming? It sounds like hell.
-
comment
Comment #49196989
Maybe it improved in the last year but it's substantially worse than before it became X. Back then the algorithm was tuned to align with the users interests and posts would get vis…
-
comment
Comment #49177959
I always thought that the frontier coding models were specifically trained to perform well in the harness from their providers. I imagine this will always be the case to some exten…
-
comment
Comment #49163671
I imagine most people that get into entrepreneurship do so precisely because they don't want to go work for someone else.
-
comment
Comment #49092736
The difference is that Anthropic engineers have infinite tokens to throw at these problems for free. The rest of us do not and that's where optimizations in how the coding harness …
-
comment
Comment #48935316
But many people are doing just that, automating workflows through prompt templates and skills.
-
comment
Comment #48933870
> I can’t help but wonder whether constant use of “agent” harnesses will lead to an atrophy of the software engineering (or really any field) muscles. It will, but I'm not sure the…
-
comment
Comment #48839973
The default system prompt is so lean: https://github.com/earendil-works/pi/blob/main/packages/codi...
-
comment
Comment #48813595
Yes, if you're just going down a list of jira tickets and implementing product features, but for many folks it's also an art medium.
- story
-
comment
Comment #48314008
Mostly yes, but I think it's both, because some people become life long fans, like the adult Pokemon card collectors.
-
comment
Comment #48194139
In my experience most people with the type of critique I'm seeing from you have only tried it one time or have not taken the time to invest in an environment/process that will work…
-
comment
Comment #48193191
I'm curious. What have you actually tried? Are you just prompting the LLM with one off tasks? For good results, you need to take the time to read the documentation for the harness …
-
comment
Comment #48188765
#2 is not really an option though. It's more like #1 or #3.
-
comment
Comment #48107607
If you use lmstudio it will tell you which models will fit in what you've got available.
-
comment
Comment #48107576
It's great, but I wish I could use these things without it feeling like my laptop is going to melt through the desk.
-
comment
Comment #47939698
You can also use JS to inject a CSP and it will enforce the strict most policy.
-
comment
Comment #47934068
There are paid solutions for this, I've seen Exa recommended.
-
comment
Comment #47934054
I've been relatively impressed with local llms, but by far the hardest thing for me is how hot they make my laptop run.
-
comment
Comment #47915849
I believe it's 9k/year in parking revenue.
-
comment
Comment #47903153
> However, in hindsight, Leary proved to be a false prophet who helped destroy the 1960s movements by pushing young people to take a drug that fried their brains and diverted their…
-
comment
Comment #47849362
Back in the day when I was in HS, kids would go to Borders and swap the stickers from cheap books onto expensive computer books.
-
comment
Comment #47765345
For me the vision/OCR is much better than other models in weights class.
-
comment
Comment #47757550
> Yes ai can’t see, it only understands numbers. I've also used AI to build frontends that I'm more than satisfied with, and I think it can "see" perfectly fine. The frontier model…
-
comment
Comment #47757490
I think it's safe to assume that "AI help was used" in everything these days and I don't understand why that should be a problem.