Juan

building better and fairer interviews at

[Juan @ditorodev]

@tensor_rotator release it then, pretty sure msft is pretty happy to pay 100million for agi

[Juan @ditorodev]

@mattpocockuk One super helpful thing I have done is get it to grill me while doing gherkins. Helps a lot to understand the feature + models understand them perfectly and implement the requieres test

[Juan @ditorodev]

lol the claude extension is the wors
ask: "please format this document"
ai: "Oh perfect, ill write an app script for that, search the strings, and format with functions :D"

[Juan @ditorodev]

@AlemTuzlak believe the same
excited of introducing it on our stack + pydantic AI for AG-UI on our UI

[Juan @ditorodev]

@b_nnett i had pay 300EUR for this

[Juan @ditorodev]

Lol for awhile i was looking at this and thinking: ugh when will the opensource models ever get to SOTA, then i remembered that opus 4.7 is like 3 months old and just last week was outdated

FUCKING UNBELIEVABLE GREAT WORK

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[Juan @ditorodev]

@dillon_mulroy not sure but using state machines and event sourcing is the best way to get to this IMO

So perhaps @statelyai ?

[Juan @ditorodev]

@benhylak @mitchellh @zeeg this is its favorite

[Juan @ditorodev]

So much better to work with voice ai by having my own workbench than to deal with provider BS

Frameworks like livekit are the ones doing most of the work

[Juan @ditorodev]

Been using this internally for a couple weeks, this is the best solution so far

[Y Combinator @ycombinator]

TesterArmy is the simplest way to QA your website or mobile app.

It runs real tests across browsers and devices, catches regressions on every PR, generates tests from natural language, and much more.

Try now and start testing in minutes: @TesterArmy

[Y Combinator @ycombinator]

TesterArmy is the simplest way to QA your website or mobile app.

It runs real tests across browsers and devices, catches regressions on every PR, generates tests from natural language, and much more.

Try now and start testing in minutes: @TesterArmy

[SIGKITTEN @SIGKITTEN]

oh no what happened to all the principals and morals from last month

[Juan @ditorodev]

@zeddotdev This is still connected to the worktrees of zed right?

[Juan @ditorodev]

@zeddotdev I love you so much

[Juan @ditorodev]

@filippkowalski Underrated as fuck given Claude codes stupidity for next month I’m thinking of migrating the whole team to cursor

[Anshu @anshuc]

@github holy shit, how did the attackers find a large enough uptime window to get in?

[Juan @ditorodev]

@zeeg Yeah I guess also going with pi a codex sub can be used and then subsidized for awhile

[Juan @ditorodev]

@zeeg dude warden is amazing. Pretty expensive to run but impressive how good it manages the context. It catched like 4 security issues on a 50k+ PR we were struggling to merge

[Juan @ditorodev]

looking at gofeatureflag im becoming go pilled, so cool to have binaries run cheaply and neatly alongside other services given how performant go is im not afraid of running stuff as sidecars

[Juan @ditorodev]

nobody is prepared for how much opus-4.7 costs to produce code, shits crazy