Tag: llm

5 interesting thing (28/03/2025)

PgAI – LLMs have been part of everyday life already for a while. One aspect I think has not been explored well so far is using them as part of ETL. The implementations I have seen so far don’t take advantage of batch APIs and are not standardized to enable the easy replacement of a model. Having said that, I believe those hurdles will be overcome soon.

https://github.com/timescale/pgai

Related links

Life Altering PostgreSql Patterns – a back-to-basics post. I agree with most of the points mentioned there, specifically around adding creaetd_at, updated_at, and deleted_at attributes to all tables and saving state data as logs rather than saving only the latest state. I found the section about enum tables interesting. This is the first time I was exposed to this idea, and the ability to add a description or metadata is excellent.

https://mccue.dev/pages/3-11-25-life-altering-postgresql-patterns

Via this post, I learned about the on update cascade option, you can read more about it here – https://medium.com/geoblinktech/postgresql-foreign-keys-with-condition-on-update-cascade-330e1b25b6e5

AI interfaces of the future – I usually don’t share videos, but I think this talk is thought-provoking for several reasons –

  • Gen UI patterns – an emerging field, the talk reviews several products and highlights good and destructive patterns. Some of the patterns, like suggestions or auto-complete, are transparent to us but are present in many products we know, and that’s something important to notice when you build such a product.
  • Product review: Knowing what is out there is good for inspiration, ideas, and understanding the competitive landscape. However, new products are coming out every day, and it is hard to track all of them.

Simplify Your Tech Stack: Use PostgreSQL for Everything – Two widespread tensions, especially in startups, are build vs. buy conflicts and using specialized products or technologies (e.g., different databases) that are top of the breed but not many people can use and maintain vs. more common technology that more people can maintain but can have performance drawbacks or other limitations. Mainly working in startups, I usually prefer to use standard technology to run faster, knowing that the product, focus, and priorities often change. With that being said, I acknowledge that early adoption of new technologies can be life-changing for a startup, but figuring out what to bet on is hard.

https://medium.com/timescale/simplify-your-tech-stack-use-postgresql-for-everything-f77c96026595

CDK Monitoring Constructs – if you are using AWS CDK as your IAC tool, CDK monitoring constructs enable you to create cloudwatch alarms and dashboards almost out of the box. I wish they would release and add additional options at a faster pace.

https://pypi.org/project/cdk-monitoring-constructs/

5 interesting things (31/05/2024)

How we built Text-to-SQL at Pinterest – Text-to-SQL and vice versa became one of the canonical examples of LLM, and every product needs one. The post described a very interesting work that can be implemented relatively easily. I relate the most to the closing paragraph, which emphasizes the gap between demos, tutorials, benchmarks, and real-world use cases. – “It would be helpful for applied researchers to produce more realistic benchmarks which include a larger amount of denormalized tables and treat table search as a core part of the problem.”

https://medium.com/pinterest-engineering/how-we-built-text-to-sql-at-pinterest-30bad30dabff

(p.s I mentioned post in a recent LinkedIn post – LLMs in the enterprise – looking beyond the hype on what’s possible today)

How an empty S3 bucket can make your AWS bill explode – this story completely blew my mind (and gladly not my account). I was happy to see that AWS is looking into this issue and wondered if in bigger accounts, such anomalies could get unnoticed.

https://medium.com/@maciej.pocwierz/how-an-empty-s3-bucket-can-make-your-aws-bill-explode-934a383cb8b1

The Design Philosophy of Great Tables –  great_tables is a Python package for creating wonderful-looking tables. This post shares its visual design philosophy and is worth reading if you create tables even if you will not use this package.

https://posit-dev.github.io/great-tables/blog/design-philosophy/

1-measure-3-1 – a variation of the 1-3-1 problem-solving method for making proposals. I found it specifically effective for engineers as it is structured and focused.

https://www.annashipman.co.uk/jfdi/1-measure-3-1.html

On Making Mistakes — I love it when people combine experience or knowledge in one field or domain with another. For example, someone brings her experience as a soccer player to managing a team, or someone uses lessons he learned as a supermarket cashier to software architecture. This post discusses making mistakes and working through them and refers to several domains, including improv, chess, and F1 team management.

https://read.perspectiveship.com/p/on-making-mistakes

5 interesting things (08/03/2024)

(Almost) Every infrastructure decision I endorse or regret after 4 years running infrastructure at a startup – in my current role as a CTO of an early-stage startup, I make many choices about tools, programming languages, architecture, vendors, etc. This retrospective view was fascinating not only for the tools themselves but also for the arguments.

https://cep.dev/posts/every-infrastructure-decision-i-endorse-or-regret-after-4-years-running-infrastructure-at-a-startup/

Everything You Can Do with Python’s textwrap Module – I have used Python for more than 10 years and never heard of textwrap model. Maybe you, too, haven’t heard of it.

https://towardsdatascience.com/everything-you-can-do-with-pythons-textwrap-module-0d82c377a4c8

It was never about LLM performance – I couldn’t agree more. The performance gaps between different LLMs are becoming neglectable. Now, it is about the experience you build using those models and the guardrails you put in to ensure the experience.

https://read.technically.dev/p/it-was-never-about-llm-performance

How to build an enterprise LLM application: Lessons from GitHub Copilot – the post ends with a summary of 3 key takeaways – 

  • Identify a focused problem and thoughtfully discern an AI’s use cases.
  • Integrate experimentation and tight feedback loops into the design process
  • As you scale, continue to leverage user feedback and prioritize user needs

Those takeaways are general and correct for almost every product launch I can think of. The post provides more concrete tips for LLM applications. It is interesting to read about a product on such a scale that I use it on a daily basis.

https://github.blog/2023-09-06-how-to-build-an-enterprise-llm-application-lessons-from-github-copilot/

Speaking for Hackers – public speaking is hard. From choosing a topic, submitting a CFP, preparing your talk and slides, and wrapping it all up. Every step can be tricky, and each of us has other things that are harder for us. This site provides excellent materials for all the parts before, during, and after the talk, making it easier to step out of our shells and share the knowledge.

https://sfhbook.netlify.app/

5 interesting things (15/01/2024)

SQL as API – I saw several efforts to expose RDBMS as API over the years. This post suggests another engel – exposing an API that accepts SQL. Consider this a brain teaser.

https://valentin.willscher.de/posts/sql-api/

SomeEstimates –  For me, the loss of trust described in the post is the most harassing implication of a culture where estimates are often missed –

“Another negative outcome is a loss of trust between developers and management since a constant sense of urgency is tantamount to no sense of urgency at all.”

https://www.shaiyallin.com/post/someestimates

How to Make Anthropic’s Claude Models Consistently Generate Valid JSON – Gettign valid and consistent JSON from LLM is an issue. Prompt engineering, as described in this post, can solve some of those issues; the json_repair package mentioned there can solve additional problems. With the GPT store announced this week and the evolving models, I believe this will be solved soon in one way or another.

https://levelup.gitconnected.com/how-to-make-anthropics-claude-models-consistently-generate-valid-json-d74ce037ca46

Bonus – https://github.com/mangiucugna/json_repair

My PostgreSQL wishlist – Another brain teaser. The items I most relate to are having created_at and updated_at columns created and maintained automatically and being immutable. I’m curious to follow the comments on this post.

https://ryanguill.com/postgresql/sql/2024/01/08/postgresql-wishlist.html

Everyday storytelling for engineers. The CAO Method – Although storytelling has become an overused buzzword in the last few years (I thought it was already over the hill). This post is important not due to the specific method but to the recognition that ICs practice storytelling every day, and mastering this skill can affect your promotion, career path, tasks you get, etc. 

https://tonyfreed.substack.com/p/everyday-storytelling-for-engineers