wassname/detect_bs_text
1
0
Fork 0
mirror of https://github.com/wassname/detect_bs_text.git synced 2026-08-19 12:10:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

wip

Browse Source
This commit is contained in:
wassname
2025-01-06 12:12:19 +08:00
parent 07803d2c90
commit 75ced83574
5 changed files with 4524 additions and 1007 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nbs/03_get_lesswrong_data.ipynb
+24 -4
View File
@@ -470,7 +470,7 @@
},
{
"cell_type": "code",
"execution_count": 144,
"execution_count": 147,
"metadata": {},
"outputs": [
{
@@ -486,7 +486,27 @@
"../samples/2025_lw_the-intelligence-curse.md 1.2061121463775635\n",
"../samples/2025_lw_the-intelligence-curse.md 1.2061121463775635\n",
"../samples/2025_lw_human-study-on-ai-spear-phishing-campaigns.md 0.9995136260986328\n",
"../samples/2025_lw_human-study-on-ai-spear-phishing-campaigns.md 0.9995136260986328\n"
"../samples/2025_lw_human-study-on-ai-spear-phishing-campaigns.md 0.9995136260986328\n",
"../samples/2025_lw_the-subset-parity-learning-problem-much-more-than-you-wanted.md 0.9548193216323853\n",
"../samples/2025_lw_the-subset-parity-learning-problem-much-more-than-you-wanted.md 0.9548193216323853\n",
"../samples/2025_lw_2024-in-ai-predictions.md 0.8065339922904968\n",
"../samples/2025_lw_2024-in-ai-predictions.md 0.8065339922904968\n",
"../samples/2025_lw_debating-buying-nvda-in-2019.md 0.7926478385925293\n",
"../samples/2025_lw_debating-buying-nvda-in-2019.md 0.7926478385925293\n",
"../samples/2025_lw_review-planecrash.md 0.689734160900116\n",
"../samples/2025_lw_review-planecrash.md 0.689734160900116\n",
"../samples/2024_lw_by-default-capital-will-matter-more-than-ever-after-agi.md 0.6629015207290649\n",
"../samples/2024_lw_by-default-capital-will-matter-more-than-ever-after-agi.md 0.6629015207290649\n",
"../samples/2025_lw_the-field-of-ai-alignment-a-postmortem-and-what-to-do-about.md 0.5714353919029236\n",
"../samples/2025_lw_the-field-of-ai-alignment-a-postmortem-and-what-to-do-about.md 0.5714353919029236\n",
"../samples/2024_lw_the-plan-2024-update.md 0.542655885219574\n",
"../samples/2024_lw_the-plan-2024-update.md 0.542655885219574\n",
"../samples/2025_lw_comment-on-death-and-the-gorgon.md 0.5308915376663208\n",
"../samples/2025_lw_comment-on-death-and-the-gorgon.md 0.5308915376663208\n",
"../samples/2025_lw_my-agi-safety-research-2024-review-25-plans.md 0.49594494700431824\n",
"../samples/2025_lw_my-agi-safety-research-2024-review-25-plans.md 0.49594494700431824\n",
"../samples/2025_lw_preference-inversion.md 0.48199906945228577\n",
"../samples/2025_lw_preference-inversion.md 0.48199906945228577\n"
]
}
],
@@ -495,7 +515,7 @@
" md = markdownify(row[\"htmlBody\"]).strip()\n",
"\n",
" return f\"\"\"---\n",
"title: {row['title']}\n",
"title: \"{row['title'].replace('\"', \"'\")}\"\n",
"date: {row['modifiedAt']}\n",
"url: {row['pageUrl']}\n",
"novelty: {row['novelty']}\n",
@@ -507,7 +527,7 @@
"\"\"\"\n",
"\n",
"\n",
"for i in range(5):\n",
"for i in range(15):\n",
" for ii in [i, -i-1]:\n",
" row = df.iloc[i]\n",
" s = to_markdown(row)\n",