Mike Porter

videos here:
building piglets here:

[Mike Porter @mportdata]

I've just posted a new video:
Text-to-SQL: Create Logical Plans & Prune Your Schema w/ piglets & Apex-SQL.

This video is the first time sharing a modular text-to-SQL toolkit I've been working on called piglets.

See comments.

[Mike Porter @mportdata]

I found this episode genuinely cathartic. There’s tons of stuff in here particularly w.r.t balancing coding agent enabled pace vs quality.

[Gergely Orosz @GergelyOrosz]

Why is the creator of OpenCode pretty skeptical about AI productivity gains, and the hype around AI? A very conversation @thdxr (and lots of truth bombs:)

Timestamps:

00:00 Intro
07:03 Dax’s path into tech
09:04 Early startup experience
13:16 Getting involved with open source
16:13 OpenCode
23:17 Anthropic banning OpenCode
30:34 From terminal to GUI
32:34 OpenCode’s business model
36:33 Why inference is profitable
39:11 GPU bottlenecks
40:54 AI hype
45:50 AI spending
48:47 Dax’s memo
55:41 Dax’s skepticism of predictions
58:58 Engineering culture at OpenCode
1:02:38 How building works at OpenCode
1:05:36 Taste and quality
1:11:32 Dax’s work setup
1:12:35 The role of engineers and EMs
1:15:50 Advice for engineers
1:18:12 Book recommendation

Brought to you by:

• @AntithesisHQ – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages https://t.co/AKYm4cbVCU

• @WorkOS – everything you need to make your app enterprise ready https://t.co/aiAee0oF5h

• @turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable https://t.co/w9y67Gs8ab

Three interesting thoughts from Dax:

1. No AI-native coding agent company is “winning” by being better with AI.

Dax says that none of OpenCode’s competitors are crushing them, and that nobody is using AI so well that others cannot compete.

2. Most software engineers profit from AI as time gained, not increased output — unless you change incentives!

Dax says the natural way for software engineers to “cash out” their AI tooling gains is with time savings, by doing the same work as before, but faster. Until compensation and motivation structures change, most teams should expect output to stay flat while engineers go home earlier. There’s nothing wrong with this, but AI vendors sell a different outcome to CFOs: increased output.

3. AI code generation mutes the “guilt” of doing the wrong thing, but this builds up tech debt.

Pre-AI, writing a hack felt bad, the second time it felt really bad, and by the third time you’d often just refactor in order to fix up the code. Now, the agent hides the hack, which skews devs’ judgment and results in less tech debt being cleaned up.

[Mike Porter @mportdata]

@mattpocockuk First time since quitting teaching to be an engineer I’ve come across the ‘Zone of Proximal Development’.

[Mike Porter @mportdata]

My honest answer: my recommendation was weak. 😭😭😭

[Mike Porter @mportdata]

Decent morning

[Mike Porter @mportdata]

@threepointone It pains me to say it being from the west coast of England but this is my favourite bit of coast outside of Cornwall. Riley’s fish shack is unreal.

[Mike Porter @mportdata]

Not saying anything novel here, but, Codex + /goal is really powerful.

[Mike Porter @mportdata]

@leostera @OpenAI @AnthropicAI I’ve found this past week that just telling codex that that’s not needed for one change stops it doing it for subsequent changes.

[Mike Porter @mportdata]

piglets is compatible with
LLMs from: @openai, @AnthropicAI @GoogleDeepMind, @OpenRouter, @cohere, @MistralAI, @deepseek_ai and any others supported by @LangChain
and
Databases such as: @duckdb, @Snowflake, and any others supported by @sqlalchemy

[Mike Porter @mportdata]

piglets is a modular text-to-sql Python library. As of v0.1.16 you can use piglets for:
- Logical Planning
- Dual-Pathway Pruning
- Semantic Linking
- Data Profiling

Check it out: https://t.co/RBwq6PmqNs

[Mike Porter @mportdata]

@Bowen_Pony Thanks! There is a newer video covering up to Semantic Linking here: https://t.co/d4V9ASk9Uj and as of yesterday we can also generate Data Profiling queries. Running those queries is my next step.

[Mike Porter @mportdata]

check out piglets here: https://t.co/jn8lS8djx5

[Mike Porter @mportdata]

piglets v0.1.15 (Modular Text-to-SQL Python Library)
https://t.co/RBwq6PmqNs
https://t.co/MlShKFpmtg

Profiler class added with a method for generating table profiler queries

[Mike Porter @mportdata]

“He’s listening to a podcast whilst doing chores, his hands just got dirty. Now have his iPhone switch from his AirPods to his car stereo.”

[Mike Porter @mportdata]

@PolitlcsGlobal @SkyNews

[Mike Porter @mportdata]

piglets is built using @LangChain for model providers @sqlalchemy for database connectors. As a result we already support all major LLM and database providers.

[Mike Porter @mportdata]

My current obsession is text-to-SQL, as a result I’ve started to build a Python package (piglets) that is a modular text-to-SQL library. The basis of this are the components of the Apex-SQL paper (which I’d also recommend checking out).

[Mike Porter @mportdata]

Text-to-SQL: using piglets to prepare your context with @duckdb and @openai

In this video we use piglets 🐷 to prepare our context for the text-to-SQL step.

It also demonstrates a new piglets primitive, Policies.

https://t.co/PWzhitG69Z

[Mike Porter @mportdata]

Something I had to overcome with piglets was integration tests and example notebooks that didn’t require specific databases to be pre paid for and pre populated. @duckdb and it’s TPC-H extension solves this perfectly.

[Mike Porter @mportdata]

Text-to-SQL: using piglets to prepare your context with @duckdb and @openai

In this video we use piglets 🐷 to prepare our context for the text-to-SQL step.

It also demonstrates a new piglets primitive, Policies.

https://t.co/PWzhitG69Z

[Mike Porter @mportdata]

Text-to-SQL: using piglets to prepare your context with @duckdb and @openai

In this video we use piglets 🐷 to prepare our context for the text-to-SQL step.

It also demonstrates a new piglets primitive, Policies.

https://t.co/PWzhitG69Z

[Mike Porter @mportdata]

piglets v0.1.14 - Now includes Semantic Linking, this is a Text-to-SQL technique taken from Apex-SQL where we combine a schema agnostic plan with a database schema to produce schema specific guidance.
https://t.co/RBwq6PmqNs