Viewing profile — m0rde
m0rde
HN member- Joined
- Thu, Sep 28, 2023, 10:57 AM UTC
- HN karma
- 39
- Public activity
- 37 items
- HN profile
- View on Hacker News ↗
About m0rde
No profile information was provided.
Recent public activity
- story
-
comment
Comment #48953065
> Fable 5: Reasoned so long it exhausted the output budget before finishing the drawing. Lol
-
comment
Comment #48867111
> * Grok 4.5 has an advantage on CursorBench: an earlier snapshot of the Cursor codebase was unintentionally included in training. The exact score impact is unclear. That data has …
-
comment
Comment #48396325
Mighty Squirrel is at Gore place for the summer... Okay, maybe that's beer and closer to Waltham =P
-
comment
Comment #48346138
Yeah. I get that many HN comments are just complaints (heck mine was too and just as negative and shaming). But how bad of a day must you be having to try to shame someone about ho…
-
comment
Comment #48346067
What a difficult world you must live in these days
-
comment
Comment #47998339
From the post: > If you care about how your content moves through the world now, including through AI systems, you have to care about caching. Not as a performance optimisation for…
-
comment
Comment #47995976
> If a comment just mentions Opus without being more specific and in the absence of relevant context clues, it gets mapped to Opus Latest Consider keeping this data point but inste…
-
comment
Comment #47961058
New technology isn't perfect now -> drop technology and never use it in the future
-
comment
Comment #47149596
I think about what I do in these verbose situations; I learn to ignore most of the output and only take forward the important piece. That may be a success message or error. I've re…
-
comment
Comment #47149559
Feedback loops are important to agents. In the article, the agent runs this build command and notices an error. With that feedback loop, it can iterate a solution without requiring…
-
comment
Comment #46255009
July 2025, then posts a few days later :) maybe he just meant done with the startup life and kept blogging. Hope you find that stability.
-
comment
Comment #46155609
> The noticeable spike [~20 percentage points] in May in the figure above [tool invocations] was largely attributable to one sizable account whose activity briefly lifted overall v…
-
comment
Comment #45406821
Good points here, particularly the ends not justifying the means. I'm curious for more thoughts on "will drive more and more people out of jobs”. Isn't this the same for most advan…
-
comment
Comment #45404965
Many people would not have found this cleaner without Googling, reading reviews, etc. While that may not be an ad directly, it's part of the marketing budget. So what needs to chan…
-
comment
Comment #44423297
This is cool. I'm interested in reading more on this concept. Any chance you have a write up of experiences so far? Or can you point to other resources?
-
comment
Comment #44020884
This looks fun, thanks for sharing. Will definitely give it a shot soon. I read over the repo docs and was amazed at how clean and thorough it all looks. Can you share your develop…
-
comment
Comment #43744063
Have you tried giving it tests? Curious if you found they made things worse.
-
comment
Comment #43736935
Really well written README :)
-
comment
Comment #43736112
I've never used Claude Code or other CLI-based agents. I use Cursor a lot to pair program, letting the AI do the majority of the work but actively guiding. How do you keep tabs on …
-
comment
Comment #43671937
> Customer support lines/banks/etc must shift their opening hours slightly so that they are open outside of business hours, so that working people can use their services How would …
-
comment
Comment #43533233
Is there an example we can see?
-
comment
Comment #43358725
Original post: https://x.com/sama/status/1899535387435086115
- story
-
comment
Comment #43196981
Great idea, congrats. Can you speak a bit about the the validation piece? Were LLM hallucinations an issue and required this? Are you using some kind of structured output feature?