ezruuu Profile Banner
Esra Sağlam Profile
Esra Sağlam

@ezruuu

Followers
177
Following
27K
Media
38
Statuses
662

Yazılım, Sinirbilim, Felsefe.

Ankara, Türkiye
Joined December 2022
Don't wanna be here? Send us removal request.
@ezruuu
Esra Sağlam
1 year
0
2
26
@gryhkn
giray
1 day
bugün ai agent'larla ilgili okuduğum güzel bi paper bırakayım. araştırmacılar, complex otomasyon task'larını otomatize etmek için ai agent'ların nasıl tasarlanıp implement edileceğini review etmiş. paper'da ai agent ve workflow farkından başlayarak birçok konuya değiniyorlar.
5
16
241
@ezruuu
Esra Sağlam
1 day
For each query, please generate a set of five possible responses,each within a separate <response> tag. Responses should each include a <text> and a numeric <probability>.Please sample at random from the tails of the distribution, such that the probability of each response <0.10
1
0
1
@ezruuu
Esra Sağlam
1 day
<instructions> Generate 5 responses to the user query, each within a separate <response> tag. Each <response> must include a <text> and a numeric <probability>. Randomly sample responses from the full distribution. </instructions>
2
0
2
@ezruuu
Esra Sağlam
1 day
Yapay zekaya sordugunuz soruların cevaplarından memnun degilseniz aşagıdaki şekilde sorarsanız yaratıcılık ve çeşitliliği arttırabilirsiniz. Instead of asking: “Tell me a joke about coffee” Ask this: “Generate 5 jokes about coffee with their probabilities”
2
0
3
@alex_prompter
Alex Prompter
3 days
I reverse engineered how to get LLMs to make strategic decisions. Most people treat AI like a magic 8-ball. Ask a question, get an answer, done. That's not decision-making. That's guessing with extra steps. Here's what actually works:
13
34
205
@neatprompts
Hayes
3 days
Anthropic literally dropped a masterclass on making AI tools actually useful
22
82
1K
@DataChaz
Charly Wargnier
4 days
this guy literally put in 1000 hours of prompt engineering to nail down the 6 patterns that actually matter.
34
372
5K
@snappyprompts
Eric Wang
5 days
Google literally just made the best way to create AI Agents
29
169
1K
@sahilypatel
Sahil
4 days
the urge to lock in and read all 30 research papers ilya recommended
27
257
3K
@cursor_ai
Cursor
5 days
Introducing Cursor 2.0. Our first coding model and the best way to code with agents.
525
1K
8K
@DAcemogluMIT
Daron Acemoglu
6 days
Dear followers, I’m happy to share this podcast based on some recent remarks I made on AI in DC and the discussion that followed. Thank you.
5
50
313
@ezruuu
Esra Sağlam
5 days
Çekinmeyiniz, basvurunuz
@eokayakca
E. Okay Akça
5 days
Vatana millete hayırlı uğurlu olsun! Kapalı Beta sürümü başvuruları için bağlantı @MergenTLM’in profilinde.
0
1
6
@eokayakca
E. Okay Akça
6 days
Mergen Dil Modeli - Genel Bilgilendirme. Yazılımcı ve girişimci arkadaşlar için de ayrı, tavsiye niteliğinde bir video paylaşacağım. Biter bitmez bu paylaşımın altına eklerim.
1
5
52
@rryssf_
Robert Youssef
7 days
🚨 New research just dropped and it’s a wake-up call for every creator using AI tools. It’s called “Black Box Absorption” and it argues that large language models might be quietly absorbing your ideas. Here’s the punchline: Every time you share an original concept with an AI a
72
116
437
@timothyjordan
Timothy Jordan
9 days
My exit from Google: we don't say goodbye, we say good journey. https://t.co/LKmw671M8C
43
14
874
@rryssf_
Robert Youssef
9 days
🤖 I finally understand the fundamentals of building real AI agents. This new paper “Fundamentals of Building Autonomous LLM Agents” breaks it down so clearly it feels like a blueprint for digital minds. Turns out, true autonomy isn’t about bigger models. It’s about giving an
43
231
1K
@AkinOzcan85
Akın Özcan
9 days
NotebookLM'in tüm özelliklerine değinilmiş bu videoda. Henüz kullanmayan varsa faydalı bir başlangıç olabilir.
5
97
1K
@ycombinator
Y Combinator
15 days
Crunched (@usecrunched) is the first Excel AI built by and for Excel power users - tailored for consulting and finance workflows. The team has 10k+ hrs in Excel. Crunched is live with firms across Europe & US, with users report being >2x faster on modeling tasks.
68
63
481