Umer Mansoor (@umer111k) header
Umer Mansoor (@umer111k) profile picture

On a mission to transforms healthcare. CTO @ January AI.

San Francisco Bay Area, CA
Joined July 2025
Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)Photo by Umer Mansoor (@umer111k)
Umer Mansoor retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
1,711
6,771
1,585
56,867
8,238,847
Umer Mansoor retweeted
Alibaba open-sourced the code reviewer it says has served tens of thousands of developers and found millions of defects internally. Open Code Review does not leave the whole review loop to an LLM: deterministic code handles file coverage, bundling, rule matching and comment positioning, while the agent handles reasoning and repository context. On its benchmark of 200 PRs across 50 open-source repos, Alibaba reports higher precision and F1 than Claude Code with the same model, using roughly 1/9 the tokens, with lower recall as the trade-off. GitHub Repo: github.com/alibaba/open-code…
50
183
20
1,540
130,208
Umer Mansoor retweeted
Sorry, but asking Jacob about AI extinction risk is like asking your AC guy about climate change. Not saying it's necessarily uninteresting or wrong per se but let’s keep things in perspective and hear from the full range of expertise across the ecosystem!
346
663
141
7,029
868,508
Umer Mansoor retweeted
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6
1,108
3,070
1,746
28,759
7,227,227
Umer Mansoor retweeted
Couldn't resist. Here's a pure PyTorch from-scratch re-implementation of Gemma 3 270M in a Jupyter Notebook (uses about 1.49 GB RAM): github.com/rasbt/LLMs-from-s…
Gemma 3 270M! Great to see another awesome, small open-weight LLM for local tinkering. Here's a side-by-side comparison with Qwen3. Biggest surprise that it only has 4 attention heads!
60
516
24
3,754
350,039
Umer Mansoor retweeted
8 RAG architectures all AI Engineers should know:
17
339
10
1,913
228,811
Transform unstructured legal documents into queryable knowledge graphs that understand not just content, but relationships between entities. This comprehensive tutorial shows you how to build a knowldedge graph creation workflow using LlamaCloud and @neo4j for legal contract processing: 📄 Use LlamaParse to extract clean text from PDF documents, even complex legal contracts 🤖 Classify contract types using an LLM to enable context-aware processing 🔍 Extract structured data with LlamaExtract, tailoring extraction schemas to each contract category 🕸️ Store everything in @neo4j as a rich knowledge graph that captures intricate relationships between parties, locations, and contract terms The tutorial includes complete code for building an agentic workflow that processes contracts from PDF to knowledge graph in a single pipeline. Check out the full cookbook: docs.llamaindex.ai/en/latest…
5
95
4
459
102,271
Umer Mansoor retweeted
Daniel clearly hasn't seen the language balls.
why does everyone pick sides with programming languages, and then refuse to use anything else who cares, they're basically all the same, just marginally different syntax
716
1,497
585
22,557
8,643,300
Google just released LangExtract Python library. It can extract structured data from unstructured docs with precise sources in just a few lines of code. 100% Opensource.
325
597
25
6,900
776,166
Umer Mansoor retweeted
going to try live-tweeting the GPT-5 livestream. first, GPT-5 in an integrated model, meaning no more model switcher and it decides when it needs to think harder or not. it is very smart, intuitive, and fast. it is available to everyone, including the free tier, w/reasoning!
1,048
1,968
518
26,833
3,704,643
Umer Mansoor retweeted
🚀 MassGen 0.0.3 is here! Major architecture upgrade for multi-agent scaling: 📷 GPT-OSS Support #GPToss 📷@AnthropicAI , @cerebras, @GoogleAI, @grok, @OpenAI
🚀 @massgen_ai 0.0.3 is here! Major architecture upgrade for multi-agent scaling: 🧠 GPT-OSS Support #GPToss 🔧 Multi-backend support: @AnthropicAI , @cerebras , @GoogleAI , @grok , @OpenAI 🔄 Async parallel iterative refinement Give it a spin 👇 github.com/Leezekun/MassGen
1
2
5
235
JanuaryAI just released Mirror, its new AI health engine. It analyzed years of my multi-omics, wearables, and labs and flagged a number of cool insights unknown to both my physician and me. A specialist confirmed it was super valuable info. This kind of AI has huge potential.
1
8
36
2,537
Umer Mansoor retweeted
Most important tech blog this year: OpenAI engineer and ex-founder of $3.5B Segment wrote a tell all post about how OpenAI works internally. From obsession with X, devout use of Slack to engineering culture and tech stack. A peek under the hood of a generational company.
75
326
22
4,124
513,622
We're thrilled to introduce our latest AI innovation, "January Mirror." Mirror is a health context engine that makes LLMs safe, accurate, and clinically intelligent. Built to power the next generation of health AI. 👇
2
7
701
Umer Mansoor retweeted
agree with lots of what jensen has been saying about ai and jobs; there is a ton of stuff to do in the world. people will 1) do a lot more than they could do before; ability and expectation will both go up 2) still care very much about other people and what they do 3) still be very driven by creating and being useful to others for sure jobs will be very different, and maybe the jobs of the future will look like playing games to us today while still being very meaningful to those people of the future. (people of the past might say that about us.) betting against human's ability to want more stuff, find new ways to play status games, ability to find new methods for creative expression, etc is always a bad bet. maybe human money and machine money will be totally different things, who knows, but we have a LOT of main character energy. more to come.
1,255
1,040
338
12,422
4,247,490
"I Couldn't Offer Employees the Major Perks That Tech Giants Can — Here's How I Hired the Best AI Engineers Anyway" - Noosheen Hashemi. Great article about the team at JanuaryAI 👏 Thanks to @Entrepreneur for the feature! entrepreneur.com/growing-a-b…
1
2
207
Umer Mansoor retweeted
Context Engineering Guide I'm writing a detailed guide on context engineering for AI devs. v1 is out now! (bookmark it) I use a concrete deep research multi-agent example to show what context engineering involves.
37
293
18
2,020
288,180