alvis

What surprise me is that Opus 4.5 lost all reasoning scores to Gemini and GPT. I thought it’s the area the model will shine the most

I’m not sure even if these browser automation brings much value other than financial analysts, at least for the moment

Not another comet or Claude browser extension plz. I stopped using them only a few days after launching

Not another comet or Claude browser extension plz. I stopped using them only a few days after launching

Why would us-east-1 cause many UK banks and even UK gov web sites down too!? Shouldn't they operate in the UK region due to GDPR?

Is anthropic killing its own plugin just days it was born????

Well. I bet Notion simply forget some of APIs are private before. I started developing using Notion APIs on the first day it got released. They have constant updates and I have seen lots of improvement. There is just no reason why they intentionally want to make the duplicate page API on MCP but not api.

PS. Just want to say, Notion MCP is still very buggy. It can't handle code block, nor large page very well

The question is, whether having UI in chatgpt a game changer, fundamentally?

Given there is already a MCP-UI project, I’m not surprised it can be done. But even that I’m not very convinced that it’s the right approach. After all, it’s still far too slow for real usage…

So it’s take 2 for Open AI’s App Store moment. But this time surfing Anthropic’s MCP wave. Smart interop.. or just chasing the cool kids?

It's interest to see this quote: `for the bottom 10% of user turns sorted by model-generated tokens (including hidden reasoning and final output), GPT‑5-Codex uses 93.7% fewer tokens than GPT‑5`

It sounds like it can make simple tasks much more correct. It's impressive to me. Today coding agent tends to pretend they're working hard by generating lots of unnecessary code. Hope it's true

nay. When you use claude long enough, you'd find yourself spending more time refactoring than coding lol

And lest we forget opus was accidentally dumber last week! https://status.anthropic.com/incidents/72f99lh1cj2c

A smell of changing strategy? Claude has been the favourite of engineers and it seems it’s now trying to win back the general consumer market where ChatGPT has taken the majority. But at the cost of Claude code? Codex is like a shark chasing CC nowadays.

Or another way of thinking. How much is the penalty we are talking about for semantic vs conventional grep?

My thinking is that for large codebase, sorting embedding matches maybe more efficient than reading all files and hence there is no point to put semantic search behind a --semantic flag

A proper title could be "Semantic grep with completely local embeddings"

Put the title aside, the tool, if it works as described, is pretty insane

I suppose AI is meant to free human from soul crushing tasks, not another certification human worker has to care about

The part I don't get is the pricing. Seems like its pricing is solely based on requests. Then how would someone use gpt 4.1 when opus is charing the same price???

Everything in context hurts focus. It's like some people suffering from hyperthymesia. They are easily get distracted when the recall something

Context window after certain size doesn’t bring in much benefit but higher bill. If it still keeps forgetting instructions it would be just much easier to be ended up with long messages with higher context consumption and hence the bill

I’d rather having an option to limit the context size

Personally, I prefer GPT-5 than 4o. It does a good job. But like many others I don't like the sudden removal because it also removed O3, which I sometime use for research based task. GPT-5 thinking mode is okay, but I feel O3 is still better.

MCP support has landed in gpt-5 but the video has no mention at all! https://platform.openai.com/docs/models/gpt-5

It's hidden in the doc. It MCP support!!! has https://platform.openai.com/docs/models/gpt-5

Where is GPT5 pro???

But hold on. 5 in LIVE5TREAM for gpt 5 or 5 models or 5 modals? Luckily we already have 4.5 so can’t be it, right?

10AM PT!

$1 per federal agency almost sounds too good to be true. The bigger test, though, will be how agencies handle issues like hallucinations and multimodal integration at scale. Interested to see what kind of safeguards or human-in-the-loop systems they’ll actually deploy.

Funny Open AI and Anthropic seems to be coordinating their releases on the same day

It has an interesting note: `Currently, the time to first token you receive from a background response is higher than what you receive from a synchronous one. We are working to reduce this latency gap in the coming weeks.`

A webhook by nature has a latency anyway, but it seems like the latency is much longer than one would expected such that OpenAI has to add this note???

It's indeed an issue. I love codex that it contains everything in a sandbox and I can review what has changed. It's proper and I've much better idea what's going on.

That said, I ditched codex for claude code... Sorry open ai. No MCP and no way to interact during execution is a huge drawback.