simianwords's submissions

1.		Can AI do fact-checking? (wired.com)
		4 points by simianwords 3 days ago \| past \| discuss
2.		Use AI for reviewing code especially when the diff is huge (simianwords.bearblog.dev)
		7 points by simianwords 17 days ago \| past \| 8 comments
3.		Ask HN: How are thinking efforts implemented?
		104 points by simianwords 32 days ago \| past \| 31 comments
4.		MCP Needs an Approval Button (simianwords.bearblog.dev)
		2 points by simianwords 34 days ago \| past \| 1 comment
5.		Why Deep Learning Works Even Though It Shouldn't (moultano.wordpress.com)
		4 points by simianwords 39 days ago \| past
6.		Investigating the hidden moat behind all the LLM apps (simianwords.bearblog.dev)
		2 points by simianwords 43 days ago \| past \| 1 comment
7.		The state of AI voice assistants is bad but there's a clear winner (simianwords.bearblog.dev)
		2 points by simianwords 44 days ago \| past
8.		The generation vs. verification delta explains why LLM's are useful (simianwords.bearblog.dev)
		1 point by simianwords 45 days ago \| past
9.		Omni 1 (ai.google.dev)
		5 points by simianwords 50 days ago \| past \| 1 comment
10.		AI can fix the fragmented online public transport space (simianwords.bearblog.dev)
		1 point by simianwords 52 days ago \| past
11.		A new wave of software efficiency is coming (simianwords.bearblog.dev)
		1 point by simianwords 56 days ago \| past
12.		Redesigning Agent Skills – two missing parts (simianwords.bearblog.dev)
		2 points by simianwords 67 days ago \| past
13.		Grok 4.3 (x.ai)
		405 points by simianwords 69 days ago \| past \| 529 comments
14.		The LLM costs are not going up (simianwords.bearblog.dev)
		2 points by simianwords 80 days ago \| past
15.		The LLM costs are not going up (simianwords.bearblog.dev)
		3 points by simianwords 80 days ago \| past
16.		Redesigning Agent Skills – two missing parts (simianwords.bearblog.dev)
		1 point by simianwords 89 days ago \| past
17.		Improving Agent Skills user experience by adding hooks (simianwords.bearblog.dev)
		2 points by simianwords 3 months ago \| past
18.		Under these conditions, LLM's basically never hallucinate (simianwords.bearblog.dev)
		1 point by simianwords 3 months ago \| past \| 2 comments
19.		Why aren't LLM's trained on their own Chain Of Thought?
		3 points by simianwords 3 months ago \| past \| 2 comments
20.		The generation vs. verification delta explains why LLM's are useful (simianwords.bearblog.dev)
		2 points by simianwords 3 months ago \| past
21.		Why domain specific LLMs won't exist: an intuition (simianwords.bearblog.dev)
		5 points by simianwords 3 months ago \| past \| 4 comments
22.		Why domain specific LLMs won't exist: an intuition (simianwords.bearblog.dev)
		5 points by simianwords 3 months ago \| past
23.		How the Left Accidentally Bolstered the Nativist Right (theatlantic.com)
		5 points by simianwords 3 months ago \| past \| 1 comment
24.		Cognitive Science of Religion (wikipedia.org)
		1 point by simianwords 3 months ago \| past
25.		Claude can generate custom diagrams, and charts directly in your conversation (claude.com)
		2 points by simianwords 3 months ago \| past
26.		Claude now has Generative UI – interactive charts and diagrams (twitter.com/claudeai)
		2 points by simianwords 3 months ago \| past \| 1 comment
27.		Cursor discovered a novel solution to Problem Six of the First Proof challenge (twitter.com/mntruell)
		4 points by simianwords 4 months ago \| past
28.		BullshitBench: Models Answering Nonsense Questions (petergpt.github.io)
		2 points by simianwords 4 months ago \| past
29.		It doesn't matter if the post was fully AI generated (simianwords.bearblog.dev)
		3 points by simianwords 4 months ago \| past \| 3 comments
30.		Deep research in ChatGPT is now powered by GPT-5.2 (twitter.com/openai)
		2 points by simianwords 4 months ago \| past \| 1 comment
		More