Viewing profile — mohsen1

Hmmm... I had a different experience. They had a fully automated environment where you ha to write test that passes some tests. No human involved. And the time requirement was insa…

That's a lot of words to say you need larger set of questions for today's models. 300 questions won't be enough to find the difference

> one of the basic tenants of algorithm development was that you can't just brute-force your way towards a solution for some complex problems Mote-Carlo is pretty useful still. Not…

Do you think any programmer really understands how their program works end-to-end? At some abstraction layer, we're all clueless. There are many layers between what you type into t…

RL. Lots of RL

I thought the same. If your life is so in order that you routinely sleep on the same interval, perhaps your life is not as stressful as others who sleep more chaotically

This is a Chrome extension that records lots of details in a usage session. Stuff like network calls, console logs, screenshots and also optionally screenshots and user narration T…

Hey HN, This is a Chrome extension that records lots of details in a usage session. Stuff like network calls, console logs, screenshots and also optionally screenshots and user nar…

Thanks! Any pro tips for sharding? I landed on single job because couldn't get cache to work properly for shards to be fast enough to worth it

I love nextest. without it my CI could take hours https://github.com/tsz-org/tsz/actions/runs/29002057457/job/... watch it running 32.5k unit tests without breaking a sweat!

This is perfect for my Chrome Extension for recording sessions and capturing screenshots, audio narration and videos. The output is a zip file with everything so if user wants to s…

I have a philosophical problem with adaptive thinking. It’s a dumb guess for how much thinking budget to allocate ahead of thinking. At least in the context of LLMs there is probab…

Computer Scientist Explains One Concept in 5 Levels of Difficult https://www.youtube.com/watch?v=fOGdb1CTu5c This video is very beautifully explains it

This seems to be a new trend. Noticed it with GPT "ultra" in their announcement[1]. I'm with you, a large language model and a system of many language models working together are n…

It seems like we forget that LLMs are next token prediction systems. Using raw models without instruction following and chat completion bells and whistles will give you a better fe…

[dead]

Nice thing about the microvm is that you can snapshot it and restore it. Keeping the fs minimal is my goal. Snapshots restore much faster if they do not include 5GB of source code

I’ve been working with AgentCore that uses the same MicroVMs. They are capable in many ways but for coding agents that load a big got repo they get bloated quickly with the git rep…

Confusion is: ultracode is not a different model with its own benchmarks

NYT's The Daily covered this a few days ago. Has a few interesting details about what went on... https://www.nytimes.com/2026/06/04/podcasts/the-daily/trump-...

> Additionally, we’re introducing a new `ultra` mode that goes beyond the capabilities of a single agent by leveraging subagents to accelerate complex work. I'm curious about how d…