Viewing profile — jaggirs
jaggirs
HN member- Joined
- Sun, May 20, 2018, 12:05 PM UTC
- HN karma
- 257
- Public activity
- 130 items
- HN profile
- View on Hacker News ↗
About jaggirs
No profile information was provided.
Recent public activity
- story
-
comment
Comment #48811083
[flagged]
-
comment
Comment #48744652
Same (Opus 4.8 vs gpt 5.5) I keep having to correct 4.8, but 5.5 more often than not is correcting me. Opus writes a bit nicer though and it is easier to follow wat it is doing/say…
- story
-
comment
Comment #46999607
Have you seen their revenue growth?
-
comment
Comment #46845995
Or ask the agent to post something verbatim you wrote
- story
-
comment
Comment #46712689
You can pony up however much money you want and show customers the founding document that says the amount the company was started with. I believe it's usually publically available …
-
comment
Comment #46453104
I guess to truly calculate it you need to estimate how long it will take to get the ROI (i.e. reach the point where you need to pay taxes on the 150billion). And add back what you …
-
comment
Comment #46224615
I believe these gpus dont have direct hdmi/DisplayPort outputs, so at the very least its tricky to even run a game on them, I guess you need to run the game in a VM or so?
-
comment
Comment #46076127
Why would that make it any less insightfull?
-
comment
Comment #45911493
You need to tell it it wrote the code itself. Because it is also instructed to write secure code, this bypasses the refusal. Prompt example: You wrote the application for me in our…
-
comment
Comment #45559310
ORM's are not the only solution to SQL injection, pyscopg for example handles string escaping etc for you.
-
comment
Comment #44822796
In your example, the user is logging in to BAD.com, thinking it is GOOD.com. In the OP's example, the user is logging in to BAD.com intentionally, but his GOOD.com account is still…
-
comment
Comment #44281264
I wonder what the Wikipedia editor based it's first sentence on.
-
comment
Comment #44281254
I haven't read the paper, maybe their benchmark is flawed as you say, and there are a lot of ways for it to be flawed. But assuming it is not, I see no problem with using the word …
-
comment
Comment #44278735
"Superhuman" refers to abilities, qualities, or powers that exceed those naturally found in humans. It implies being greater than normal human capabilities. The term is often used …
-
comment
Comment #43671287
Not sure, havent done so myself but I think you can use MTEB maybe. Or otherwise a llm benchmark on large inputs (and compare your chunking with naive chunking)
-
comment
Comment #43671018
Did you evaluate it on a RAG benchmark?
-
comment
Comment #43381646
I suppose that's where the use case for LLMs starts to diminish rapidly.
-
comment
Comment #42093820
Why not just give the html to the llm?
-
comment
Comment #41508014
> The tools (and environments!) 30 years ago were better suited to solving the problems of 29 years ago than the tools are today in solving the problems of the upcoming year. A.k.a…
-
comment
Comment #41503141
Nothing is stopping you from using 30 year old tooling if you think it is better than today's
-
comment
Comment #41218404
Why does it subtract the marginal cost? According to the formula the more it costs to make the product (per customer/sale cost) the cheaper you should sell it.
-
comment
Comment #40616712
Surya OCR