medha_basu Profile Banner
Medha Basu Profile
Medha Basu

@medha_basu

Followers
1K
Following
2K
Media
175
Statuses
2K

Co-founder @DefogData (YC W23). Former journalist/editor/content marketing person. Once interviewed a terrorist

Singapore / San Francisco
Joined January 2013
Don't wanna be here? Send us removal request.
@medha_basu
Medha Basu
2 years
Amazing to be ending this week with SQLCoder trending at #5 on @huggingface 😮
2
3
16
@medha_basu
Medha Basu
8 months
Asked Claude Code to use an LLM to summarize stuff for a CLI tool I'm building. Why did it decide to use OpenAI 😆
3
1
7
@medha_basu
Medha Basu
9 months
Using Claude Code is insane. I feel very powerful. Like I have superpowers I really should not
0
0
3
@geoffreylitt
Geoffrey Litt
9 months
# the nightmare bicycle imo, the most important idea in product design is to avoid the "nightmare bicycle". imagine a bicycle where the product manager said "people don't get math so we can't have numbered gears - we need to have labeled buttons for gravel mode, downhill mode,
120
292
3K
@rishdotblog
Rishabh Srivastava
9 months
Open-sourcing Introspect: MIT-licensed Deep-Research for your internal data! Works with spreadsheets, databases, PDFs, and web search. Has a remarkably simple architecture – Sonnet agent armed with recursive tool calling and 3 default tools. Best for use-cases where you want to
18
100
660
@gabrielchua_
gabriel
1 year
"You can run it on a single L4 GPU that costs $300/mo on GCP" "You can use logprobs and attention scores to determine where, exactly is the model paying attention to inside a prompt + what it's getting confused by when generating outputs." Very cool! congratulations on the
@rishdotblog
Rishabh Srivastava
1 year
We made a thing! Very happy to announce sqlcoder-pro and the Defog Alignment Platform. Available to use immediately without a wait-list, weights will be open-sourced very soon. The video does a quick show and tell comparison against ChatGPT (with gpt-4o). Read on for more
0
1
3
@rishdotblog
Rishabh Srivastava
1 year
We made a thing! Very happy to announce sqlcoder-pro and the Defog Alignment Platform. Available to use immediately without a wait-list, weights will be open-sourced very soon. The video does a quick show and tell comparison against ChatGPT (with gpt-4o). Read on for more
10
23
123
@rishdotblog
Rishabh Srivastava
2 years
Llama-3 based SQLCoder 8b is out! Open weights with a commercially friendly cc-by-sa license. Probably the best <10B param model for Postgres text to SQL right now. Slightly better than gpt-4-turbo and claude opus for 0-shot text to SQL generation. Also approaches their
27
117
580
@ClementDelangue
clem 🤗
2 years
7B model better than the most recent GPT4 out of the gate on text to SQL! I've said it and will say it again: except for very general tasks (like a search engine), smaller models are better/cheaper/faster!
@rishdotblog
Rishabh Srivastava
2 years
Launching the second generation of SQLCoder-7b on @huggingface today! This is distilled from our 70B model, and performs around as well* as GPT-4 for text-to-SQL generation. Finetuned on @AIatMeta's CodeLlama-7b. *To be more precise – this model is much better at ratios and
6
18
167
@GabGarrett
Gabriel Garrett
2 years
it works! SQLCoder70B for MLX / apple silicon is live. the model path is here: https://t.co/9ukO5EaEEy you'll need defog's system prompt below for it to work. (question and response outputs a bunch of junk tokens but outputs work well for new / fresh convos): ### Task
4
8
42
@rishdotblog
Rishabh Srivastava
2 years
And incredibly grateful to @JP_smasher and @wendyaww without whom this would never have happened. Incredibly lucky be working with these rockstars!
2
3
12
@rishdotblog
Rishabh Srivastava
2 years
We just opened sourced SQLCoder-70B! It outperforms all publicly accessible LLMs for Postgres text-to-SQL generation by a very wide margin. SQLCoder is finetuned on @AIatMeta's CodeLlama-70B model that was released yesterday on less than 20,000 hand-curated prompt completion
58
269
2K
@rishdotblog
Rishabh Srivastava
2 years
Welp, just finished training and evaluating CodeLlama-70B for SQL. This thing is a beast when fine-tuned. Miles ahead of anything else (including GPT-4). Open-sourcing the weights either today or tomorrow!
35
110
2K
@medha_basu
Medha Basu
2 years
Nice to see Defog on the lists for top 100 YC startups in Generative AI, Enterprise and Open Source!
2
6
31
@reach_vb
Vaibhav (VB) Srivastav
2 years
Way to go @defogdata! ⚡️ So so bullish on what @medha_basu & @rishdotblog are up to.. Open source is the way! 🤗
@caitbhri
Cait Bahari
2 years
In the past month, we caught up with fast-growing @stripe users like @yongfook, @medha_basu, @kiwicopple, and @ytk141 to hear how 2023 went for them. Excited to finally share this with the world today. ✨
0
2
10
@rishdotblog
Rishabh Srivastava
2 years
Running our new 7B model 100% locally on an M1 Mac 🤓 76% accuracy on sql-eval with GGUF. For reference, GPT-4 is 82.5% and SQLCoder-34B-v2 is at 85% Pretty wild that this works locally *on a laptop*! Super excited about getting this on a Mac app soon.
28
61
855
@dharmesh
dharmesh
2 years
@rishdotblog @ajhodls @ycombinator Thrilled to be on board as a #happyinvestor! Look forward to watching you build an amazing company. Cheers.
2
2
22
@ajhodls
first check $500k-1M pre-seed
2 years
The @defogdata team moves at light speed. We’re thrilled to partner with them to bring the most powerful open-source LLMs for enterprise data analysis. @rishdotblog and @medha_basu are exceptional founders and headed for big things. 🚀
@defogdata
Defog.ai
2 years
We are excited to announce Defog’s $2.2M funding round to develop open-source LLMs for data analysis. https://t.co/V360ID50rD The round was led by Script Capital (@ajhodls) and @ycombinator, with participation from Hike Ventures, Pioneer Fund, and notable angels. Since launch,
2
3
20
@defogdata
Defog.ai
2 years
We are excited to announce Defog’s $2.2M funding round to develop open-source LLMs for data analysis. https://t.co/V360ID50rD The round was led by Script Capital (@ajhodls) and @ycombinator, with participation from Hike Ventures, Pioneer Fund, and notable angels. Since launch,
4
6
48
@_orcaman
Or Hiltch
2 years
I will say this: I have personally tested all models listed here and many more, including ones that claim to reach GPT4-level results for natural language to SQL over generic benchmarks. But the Defog model is the only one I've seen thus far that actually delivers.
1
1
9
@medha_basu
Medha Basu
2 years
Can't wait to share more on the partnership at some point, but for now I will say that this is a result of the incredible work by my amazing colleagues this year ❤️
0
0
9