Ada Boese

547 posts

Ada Boese banner
Ada Boese

Ada Boese

@AdaBoese

Learning about LLMs as a I build the best article generator the world has ever seen! 🟩🟨⬜️⬜️⬜️⬜️⬜️⬜️⬜️⬜️ $50k/m

New York เข้าร่วม Ekim 2023
283 กำลังติดตาม149 ผู้ติดตาม
ทวีตที่ปักหมุด
Ada Boese
Ada Boese@AdaBoese·
In early days of developing SaaS, your focus has to be developing relationship with users, not revenue maximization. Otherwise you will miss out on tremendously valuable feedback.
English
1
1
8
918
Ada Boese รีทวีตแล้ว
Charly Wargnier
Charly Wargnier@DataChaz·
Must bookmark. @PunkpEye has put together a huge collection of 300+ MCP server implementations tailored for AI agents! 🤯 This Github repo links AI models to real-world tools such as web browsers, APIs, databases, cloud services, CLIs, & much more! ↳ github.com/punkpeye/aweso…
Charly Wargnier tweet media
English
4
12
40
6.9K
Ada Boese
Ada Boese@AdaBoese·
@AlexBelogubov It is a tough space/tough problem. I've been working on AIMD app for several months now. Focused on quality beyond anything else. I have good results, but the application got extremely complex to maintain.
English
0
0
1
26
Alexander Belogubov 🇺🇦
Alexander Belogubov 🇺🇦@AlexBelogubov·
I am launching a new product - Marevo ✍️ This is an AI Writing Tool with ready-made templates for creating texts. Write any text content in seconds. It's live on Product Hunt now 👇 producthunt.com/posts/marevo
Alexander Belogubov 🇺🇦 tweet media
English
22
7
80
10.5K
Shawn Hill
Shawn Hill@shwnhll·
So far this year, I’ve had $4,464.92 of interest deposited into my savings account. That’s almost $900/month for free. I had this money sitting with Chase earning 0.01% for awhile until @carriganisms told me to switch to Wealthfront and upped that to 5.5% 🤑
Shawn Hill tweet media
English
13
0
17
2.8K
Phuc Le
Phuc Le@phuclh93·
Can you guess the next cool tool I am adding to SEO Utils?
Phuc Le tweet media
English
1
2
3
638
Ada Boese
Ada Boese@AdaBoese·
I don't know what changed, but AI generated content is taking off the ground big time this month. I am increasingly using AIMD.app for my own projects rather than focusing on selling it... and holy guacamoly did I see a shift in Google Search Console this month compared to previous. Google algo changes?
English
0
0
0
150
Ada Boese
Ada Boese@AdaBoese·
@pbteja1998 So much love for this project! Been checking the progress since the start. Amazing how much you've achieved!
English
0
0
1
43
Bhanu Teja P
Bhanu Teja P@pbteja1998·
I launched SiteGPT.ai exactly 1 year ago… And we just crossed $250k in lifetime revenue today 😀 Hopefully we reach the next $250k in much less than a year. I have so many ideas on how to take SiteGPT to the next stage… …and we are just getting started.
Bhanu Teja P tweet media
English
82
10
645
52.3K
Alexander Belogubov 🇺🇦
Alexander Belogubov 🇺🇦@AlexBelogubov·
@lilybankai Thanks for letting me know! You entered Https in the URL instead of https, so it didn’t work :) I fixed it, now it should work in different case of letters, try it now.
English
1
0
0
95
Ada Boese
Ada Boese@AdaBoese·
I've been very quiet. I don't know if it is good for my social presence, but it is been very good for my product growth. Need to find a balance of the two.
English
0
0
1
136
Andrew Pierno
Andrew Pierno@AndrewPierno·
just finished curating a list of 150+ tech companies that raised <$5m in the last 30 days (feb-march) 🤯 - 100% verified b2b email - founder name - industry - size of round ❤️ like + comment 'send' and I’ll dm you the google sheet for free (we sell these for $299 otherwise)
GIF
English
339
20
370
31.6K
Ada Boese
Ada Boese@AdaBoese·
Everyone keeps throwing random suggestions at Google. "Google should do X, Y, Z for the best results" It is not hard to find good results in a small datasets. Everyone seem to ignore that whatever they do must be feasible with trillions of datapoints
English
0
0
1
165
Ada Boese
Ada Boese@AdaBoese·
What happened to all the speculations about GPT5 coming out?
English
0
0
0
342
Saïd Aitmbarek
Saïd Aitmbarek@SaidAitmbarek·
Super proud to support International Women's Day for the whole weekend😊 Microlaunch.net has the privilege of being a second home for many talented women who make great products👌 Please show your support by giving feedback on their product weekend and help them reach the Top-10🎖 🎬@hannaz_z | building BoolVideo (slug: boolvideo) 💡@Juliet__de | building Fipner AI (slug: flipnerai) 👥@shreya_gr | building AICamp (slug: aicamp) ✨@cyb3ramelia | building Kleanse (slug: kleanseapp) 💸@BusMark_w_Nika | building on YT (slug: businessmarketingwithnika) 🎶@verry_codes | building Drumbitious (slug: drumbitious) 💬@Carollmir | building MojiPulse (slug: mojipulse) 📋@Catalina_Melnic | building Morrow (slug: morrow) ✍🏻@adaboese | building AIMD (slug: aimd) 🦾@EnumHQ | build Enum Smart AI Assistant (slug: enumsmartaiassistant) How to vote: microlaunch.net/p/ Example: microlaunch.net/p/flipnerai We definitely need more women in tech and Women's Day should be every day🙏 Have a nice weekend✨
Saïd Aitmbarek tweet media
English
4
4
19
1.1K
Ada Boese
Ada Boese@AdaBoese·
This experiment has been pretty nuts
Ada Boese tweet media
English
0
0
1
128
Ada Boese
Ada Boese@AdaBoese·
Claude vs. OpenAI GPT-4 generated content, side-by-side comparison - OpenAI GPT-4 gist.github.com/adaboese/12e3c… - Claude 3 (Opus) gist.github.com/adaboese/d0b73… Both of these are outputs of AIMD app. They are not made using a single prompt, but rather using RAG with over a dozen instructions. This allows to test a quite broad range of expectations, such as the adherence to instructions, error rate, speed, etc. Since the two model APIs are mostly compatible, I've decided to compare it side-by-side. A few interesting observations: - Claude followed instructions a lot closer than OpenAI. The outline that was provided to the initial instructions is pretty close to the final article structure despite multiple revisions. - Claude output scored better in terms of use of broader set of data formats (tables, lists, quotes). - Contrary to many tweets, Claude output is not excessively verbose. Worth mentioning that part of RAG instructions to rewrite content for brevity. - Claude took 5 minutes to execute 52 prompts. OpenAI took 7 minutes. – Image inputs (prompts) are generated with respective models, but the actual images are generated using DALLE.
English
0
0
0
192
Ada Boese
Ada Boese@AdaBoese·
@mattshumer_ @levelsio This works equally well with OpenAI just in case. That's the approach that I use.
English
1
0
10
1.3K
Ada Boese
Ada Boese@AdaBoese·
@levelsio @AnthropicAI I've not seen anyone talk about throughput speeds. How are those? thinking of trying this out for AIMD.app, although pretty happy with current LLMs
English
0
0
1
652
@levelsio
@levelsio@levelsio·
Trying Claude 3 today by @AnthropicAI for cbt.chat At first glance it feels slightly better than GPT4 and way better than Mistral etc. The first thing I notice is that its responses seem MUCH more human than LLMs before it "I know it may not feel like it right now, but you ARE going to get through this." That ARE is quite human, and GPT4 would never capitalize emphasis like that unless you ask it to
@levelsio tweet media
@levelsio@levelsio

Added first RAG to cbt.chat it can now open URLs "retrieval augmented generation (RAG)"

English
37
24
562
320.1K
Ada Boese
Ada Boese@AdaBoese·
AIMD.app is by far the most advanced article generator, using several different LLMs and external APIs to create content that's both easy to read and contains rich data with images, quotations, tables, etc.
English
0
0
1
99