m3h · HackerTrans

m3h

691 karmajoined hace 13 años

Hello there

Chief Product Architect at APIMatic... I help API providers create the best Developer Experience for their APIs through awesome client libraries and documentation.

I spend a lot of time thinking about HTTP APIs and Code Generation.

Email at mehdi [at] apimatic [dot] io.

LinkedIn: https://www.linkedin.com/in/mehdi-jaffery/

- Mehdi Raza Jaffery

Submissions

ChatGPT and Codex Weekly Users Cross 10M

twitter.com

3 pointsby m3hhace 5 días0 comments

GPT 5.5 uses Grug Brained talk during reasoning for 2x token efficiency

youtube.com

4 pointsby m3hhace 26 días0 comments

Vibe Coding to Agentic Engineering: A Three-Phase Workflow with Claude Code

apimatic.io

2 pointsby m3hhace 28 días0 comments

AI SDK 7 is available

vercel.com

2 pointsby m3hel mes pasado0 comments

US Government Asks OpenAI to Stagger AI Model Release

bloomberg.com

2 pointsby m3hel mes pasado1 comments

Vibe Coding to Agentic Engineering with Claude Code

apimatic.io

1 pointsby m3hel mes pasado0 comments

Codex usage grows after Fable nerf model release

twitter.com

2 pointsby m3hhace 2 meses0 comments

Replace your CI with a merge queue

blog.exe.dev

4 pointsby m3hhace 2 meses0 comments

Wslc: A native Linux container runtime for Windows

boxofcables.dev

23 pointsby m3hhace 2 meses0 comments

[untitled]

1 pointsby m3hhace 2 meses0 comments

Wterm – A terminal emulator for the web

wterm.dev

66 pointsby m3hhace 2 meses18 comments

Ask HN: Are LLMs creating busy work?

5 pointsby m3hhace 2 meses7 comments

Migrate from Stainless to APIMatic CodeGen

migrate-from-stainless.apimatic.io

1 pointsby m3hhace 2 meses0 comments

APIMatic – Type-safe SDKs for 7 languages from an OpenAPI spec

apimatic.io

4 pointsby m3hhace 2 meses1 comments

Training MiniMax-M2.1

minimaxi.com

3 pointsby m3hhace 7 meses0 comments

Neptune.ai Is Joining OpenAI

neptune.ai

1 pointsby m3hhace 8 meses1 comments

React Compiler

react.dev

1 pointsby m3hhace 9 meses0 comments

Sora iOS App

apps.apple.com

1 pointsby m3hhace 10 meses1 comments

Software engineering job openings hit five-year low?

blog.pragmaticengineer.com

255 pointsby m3hel año pasado269 comments

Pakistan deploys the great firewall for internet

dawn.com

4 pointsby m3hhace 2 años0 comments

comments

Is there a specific list of changes they made to the system prompt? They're claiming they removed 80% of it. That's quite substantial. It would be good to know what the model knows to do by training and what we need to avoid over-specifying in our system prompts.

Saying that "give Claude judgment" is too vague for agent implementors. Given the lack of specific details, my takeaway is that we need to go and review all context and rework prompts from prompts/descriptions from scratch until they pass the evals again.

hace 9 díasdiscuss

A while back, I saw a similar feature land in Codex (I'm using the VS Code plugin) but it got removed quickly. What is the chance that an LLM recommended this same idea to the Claude PM or lead? I see LLMs across different providers converging on similar ideas or biases frequently.

hace 11 díasdiscuss

> Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters.

This puts them on the top of the largest open models list:

  Kimi K3            2.8T
  DeepSeek-V4-Pro    1.6T (49B active)
  Kimi K2.6          ~1T (32B active)
  GLM-5.2            754B (40B active)
  DeepSeek-V3.2      685B
  Mistral Large 3    675B

That's one mighty large model! Moonshot is going to need the USD 500 million reportedly raised earlier this year to run this model.

hace 15 díasdiscuss

The author shared their experience building the first version in a month: https://themackabu.dev/blog/js-in-one-month

And then the follow up few months later: https://themackabu.dev/blog/ant-part-two

I'm not sure what the economics of building a new runtime and ecosystem from scratch are but it seems we're already in a phase where individual developers are creating software which previously took a whole team. And its only getting started...

hace 17 díasdiscuss

[dead]

hace 17 díasdiscuss

We have an official pelican on a bicycle from the OpenAI livestream:

https://imgshare.cc/mz9xwut3

hace 18 díasdiscuss

The speed up numbers based on their testing:

    Codebase    | TypeScript 6 | TypeScript 7 | Speedup
    ------------|--------------|--------------|--------
    vscode      | 125.7s       | 10.6s        | 11.9x
    sentry      | 139.8s       | 15.7s        | 8.9x
    bluesky     | 24.3s        | 2.8s         | 8.7x
    playwright  | 12.8s        | 1.47s        | 8.7x
    tldraw      | 11.2s        | 1.46s        | 7.7x

Congratulations to the team for pulling off this feat while doing a responsible migration (looking at you, Bun).

Quick question: How does this affect downstream tools like tsdown and esbuild, which need to build the TypeScript codebase? Can I use TS 7 and current tsdown together?

hace 21 díasdiscuss

When I reviewed the conversations affected by this issue, they did not always align with my feeling of "degraded output".

Some were definitely below par, and I recall having to iterate on the generated code more than I wanted to. However, it is only true for a very small number of conversations.

So we're looking at a small set of affected conversations, and even within that small set, only a few will have degraded output, likely because the model can compensate for the reasoning defect over the long conversation.

hace 21 díasdiscuss

Indeed, it looks like my work has suffered from the clustering issue as well:

  reasoning_output_tokens    count    percent
  ━━━━━━━━━━━━━━━━━━━━━━━━━  ━━━━━━━  ━━━━━━━━━
                         0      873    28.5948
  ─────────────────────────  ───────  ─────────
                         8       64     2.0963
  ─────────────────────────  ───────  ─────────
                         9       60     1.9653
  ─────────────────────────  ───────  ─────────
                        11       54     1.7688
  ─────────────────────────  ───────  ─────────
                       516       48     1.5722
  ─────────────────────────  ───────  ─────────
                        12       45     1.4740
  ─────────────────────────  ───────  ─────────
                        10       43     1.4085
  ─────────────────────────  ───────  ─────────
                        17       40     1.3102
  ─────────────────────────  ───────  ─────────
                        13       38     1.2447
  ─────────────────────────  ───────  ─────────
                        14       36     1.1792

Created a script for this: https://github.com/thehappybug/codex-reasoning-token-check

hace 25 díasdiscuss

Also, kudos to the Z.ai team for adding Linux support from day one.

hace 25 díasdiscuss

Z.ai documents integrations with nearly all the popular CLI-based agents: https://docs.z.ai/devpack/tool/others

If you're already used to your TUI coding agent, you don't need the desktop agent. Although it is nice that it is there for folks who prefer the Codex App/Claude App UI approach.

hace 26 díasdiscuss

Correct. Albeit the nuance here is that a more capable model might solve problems more efficiently and faster, possibly saving you tokens.

As with any new model, you won't know the real impact until you start using it for your workload.

hace 26 díasdiscuss

I didn't realize GPT 5.3 Codex was that good.

OpenAI claims to have made their new Terra model as good as GPT 5.5, but with half the cost per intelligence. Hopefully, this will bring it closer to the price you're expecting (or even better considering GPT models have good acceptance/success rates according to benchmarks).

hace 26 díasdiscuss

I think you should try an OpenAI model like GPT 5.5. It is better at following instructions and boundaries set during prompt. It feels like a more capable "agent assistant" than Claude models but without loss of intelligence.

Most of my work involves "Agentic engineering" instead of fire-and-forget. I like to stay involved during the planning as well as review and ask a lot more questions from the agent than I've seen others doing. In a way, I'm using the agent in a sort of "hyper auto-complete" mode to fill in the blanks (rather big blanks) once I've set out the requirements, scope and design (sometimes specific module boundaries). This works best for me.

hace 26 díasdiscuss

Important to note: "Sonnet 5 is an upgrade to Sonnet 4.6, but it uses an updated tokenizer that changes how the model processes text to improve performance (this is similar to the tokenizer change we introduced with Claude Opus 4.7). The tradeoff is that the same input can map to more tokens: roughly 1.0–1.35× depending on the content type. The introductory pricing is set so that the transition to Sonnet 5 is roughly cost-neutral."

hace 26 díasdiscuss

Why is Claude Sonnet 5 allowed to be released but OpenAI Terra not? Are they not the same class of models?

el mes pasadodiscuss

If GPT-5.6 preview is not available outside US government approved "trusted partners", I don't see how the General Available can be trusted later.

Who knows what they will fix, block or change in the model between the preview and GA time. Open models can't arrive soon enough.

el mes pasadodiscuss

Or we could simply hallucinate that the packages are there at the three houses.

Hallucinations all the way down...

hace 2 mesesdiscuss

How are you measuring progress at your company?

Do you feel AI agents are helping you achieve company goals faster now?

hace 2 mesesdiscuss

Might I recommend trying APIMatic out: https://migrate-from-stainless.apimatic.io/