m3h

m3h

eergisterendiscuss

[dead]

m3h

eergisterendiscuss

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

https://imgshare.cc/mz9xwut3

m3h

eergisterendiscuss

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?

m3h

6 dagen geledendiscuss

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.

m3h

6 dagen geledendiscuss

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

m3h

9 dagen geledendiscuss

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

m3h

9 dagen geledendiscuss

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.

m3h

10 dagen geledendiscuss

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.

m3h

10 dagen geledendiscuss

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).

m3h

10 dagen geledendiscuss

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.

m3h

10 dagen geledendiscuss

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."

m3h

10 dagen geledendiscuss

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

m3h

14 dagen geledendiscuss

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.

m3h

21 dagen geledendiscuss

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

Hallucinations all the way down...

m3h

2 maanden geledendiscuss

How are you measuring progress at your company?

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

m3h

2 maanden geledendiscuss

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

m3h

2 maanden geledendiscuss

Helpful link: https://migrate-from-stainless.apimatic.io/

m3h

2 maanden geledendiscuss

On a side note, for those impacted by the recent Stainless API wind down, APIMatic is offering 50% off for the first year: https://migrate-from-stainless.apimatic.io/

m3h

2 maanden geledendiscuss

Congratulations to the Stainless team for their hardwork.

We are offering a 50% off for the first year subscription price at www.apimatic.io for companies impacted by this.

If you're looking for a solid long term SDK and docs partner, APIMatic is the OG CodeGen serving companies like PayPal, Maxio and PayQuicker for the past 10 years.

Reach out to [email protected] and I'll help you migrate.

PS: sorry for the shameless plug but sdks and APIs are my life and blood :-)

m3h

7 maanden geledendiscuss

Why do major LLMs block china? Isn't that a potentially huge market for them?

Submissions

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

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

AI SDK 7 is available

US Government Asks OpenAI to Stagger AI Model Release

Vibe Coding to Agentic Engineering with Claude Code

Codex usage grows after Fable nerf model release

Replace your CI with a merge queue

Wslc: A native Linux container runtime for Windows

[untitled]

Wterm – A terminal emulator for the web

Ask HN: Are LLMs creating busy work?

Migrate from Stainless to APIMatic CodeGen

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

Training MiniMax-M2.1

Neptune.ai Is Joining OpenAI

React Compiler

Sora iOS App

comments