Viewing profile — shaburn
shaburn
HN member- Joined
- Mon, Oct 03, 2016, 10:21 PM UTC
- HN karma
- 951
- Public activity
- 605 items
- HN profile
- View on Hacker News ↗
About shaburn
No profile information was provided.
Recent public activity
-
comment
Comment #44012309
thats what the auditors that charge a fortune are for
-
story
Ask HN: Who is working on a SOC2 Security Audit Agent while you sleep"?
I want to buy it, I don't want to build it. It should audit my code with preset parameters when I am offline. It should flag issues and propose changes with tradeoffs in SOC and co…
- story
- story
-
comment
Comment #42065947
You should now assume your sources are compromised if you did not expect this
-
comment
Comment #41940939
Would be great to have a fixed blockchain based event log, ideally encrypted.
- story
-
story
Show HN: Prompts to Reduce LLM Political Bias
Each LLM possesses a unique as sometimes transient political bias, which is problematic for many business applications. Here are prompts I've had success with in reducing this bias…
-
comment
Comment #39722422
How would you score your ability to negotiate 1 to 10 (10 as the best)?
- story
-
comment
Comment #38667446
Which books? Where do I find them exactly? More quantitative than qualitative. More like SEC data.
-
comment
Comment #38667439
My brain.
-
comment
Comment #38667438
I mostly just want to know how much water/nutrients to provide it and when.
- story
-
comment
Comment #38631548
Current Admin = EA ... "'The speed of SEC rule-making has created difficulties for firms. The IAA said the SEC should take a step back from that proposal and work with the industry…
- story
- story
-
comment
Comment #38510265
Visualization never seems to get the credit due in software development. This is amazing.
-
comment
Comment #38510223
[flagged]
- story
-
comment
Comment #38464264
I beleive the model bias is highly influenced by the modelers. See Grok and OpenAI.
-
story
Ask HN: How can political bias across LLMs be factored?
Political bias is measurable and significant across models(and probably changing over time for closed-sourced). In search of objectivity, what are the best ways to account for this…
-
comment
Comment #38180426
LlamaIndex, HuggingFace, LangChain, and Ludwig are functioning as partial proxy aggregators of what is working and working better than alternatives. Most people in this space have …
-
comment
Comment #38120126
Why will function names and variables be named better? Will this also apply to the better code bases?
-
comment
Comment #38118719
I think structure will shrink and simplify to fit context window token limits at the expense of developer(human) experience and developer bias.