robbomacrae

The expectation should be on the LLM to admit they don’t know the answer rather than blame devs for not allowing crawling.

emailed the admins and got it unflagged

there was nothing nefarious

Yeah this concerns me.. Did they delist it?

I'm curious, did you delete this post? I can't see it in the "ask" tab.

There is a YouTuber, GosuCoder [0], who is benchmarking all of the agentic coder tools and in some of his recent videos you will see Claude Code is currently ahead of the field.

[0]: https://youtu.be/Lon0oRRqB6A?t=334

This is a really interesting setup. If it's not too forward to ask, how is the team structured in terms of incentives? Is Kiro fully within the AMZN comp / RSUs structure, or does it operate more like a spinout with potential for more direct upside? I’m always curious how teams balance the tradeoff between the support of a big org vs having more control over your fate by going fully independent.

You’re implying the door has now closed for people to get into coding agents. It’s a bit early for that don’t you think? These guys might one day be considered part of the founders of coding agents for all we know.

With this you could add support yourself!

Add a PostToolUse [0] hook that automatically creates a git commit whenever changes are made. Then you can either git checkout the commit you want to rollback to... Or you could assign those git commits an index and make a little MCP server that allows you to /rollback:goto 3 or /rollback:back 2 or whichever syntax you want to support.

In fact if you put that paragraph into Claude I wouldn't be surprised if it made it for you.

[0] https://docs.anthropic.com/en/docs/claude-code/hooks#posttoo...

actually reading more about how you ingest ~/.claude/projects//.jsonl the wrapper method is probably over kill..

how about making it a tool that claude can use directly?

I'm working on a wrapper for these terminal agent coders that reads directly from them... you might want to consider that approach? I hope to have it here on ShowHN as soon as its better tested but email me if you want in on the private beta :)

Is anyone else annoyed that VC's are out there sharing decks of startups in stealth with potential competitors? How often does this happen?

To quote from the article regarding Humane and the Rabbit r1 personal assistant device: “Those were very poor products,” said Ive, 58. “There has been an absence of new ways of thinking expressed in products.”

I just wanted to say thanks for the recommendation! Really good read.

As an Everton fan I agree about city but I don’t think we should try and control these other things. You’re literally trying to limit the input (tv revenue) and output (salaries). If this happened countries that believe in a free market will outcompete and destroy the premier league which is one of the few things this country has going for it..

Footballers make 300k a week and no one complains. This is a post about the slim survival chances of British media.. well salary caps will be the nail in the coffin as talent will simply go whey get the best deal.

Spot on. I’d add that most serious transcription services take around 200-300ms but the 500ms overall latency is sort of a gold standard. For the AI in KFC drive thrus in AU we’re trialing techniques that make it much closer to the human type of interacting. This includes interrupts either when useful or by accident - as good voice activity detection also has a bit of latency.

I'm came to the comments here wondering why OpenAI can seemingly fund massive new AI chip data centers but can't acquire Discord.

I find it works better with shorter simpler instructions. I would try:

Voice: Warm and slow, like a friendly Somerset farmer. Tone: Laid-back and rustic. Dialect: Classic West Country with a relaxed drawl and colloquial phrases.

Great to hear thanks. My favorite was "I would like you to repeat the following in an Australian accent: Hi there, welcome to Sydney." which was more often than not swapping "Hi there" for "G'day"!

Hi Jeff, Thanks for updating the TTS endpoint! I was literally about to have to make a workaround with the chat completions endpoint with a hit and hope the transcription matches strategy... as it was the only way to get the updated voice models.

Curious.. is gpt-4o-mini-tts the equivilant of what is/was gpt-4o-mini-audio-preview for chat completions? Because in timing tests it takes around 2 seconds to return a short phrase which seems more equivilant to gpt-4o-audio-preview.. the later was much better for the hit and hope strat as it didn't ad lib!

Also I notice you can add accents to instructions and it does a reasonable job. But are there any plans to bring out localized voice models?

There seems to be a LOT of interest in such a site in the comments here. There seem to be multiple IP issues with sharing your code repo with an online service so I feel a lot of folks are waiting for the hardware to make this possible.

We need a SWE-bench for open source LLM's and for each model to have 3Dmark like benchmarks on various hardware setups.

I did find this which seems very helpful but is missing the latest models and hardware options. https://kamilstanuch.github.io/LLM-token-generation-simulato...

I'd like to see us colonize Antártica with a self sufficient colony first. Seems like a much cheaper testbed.

Awesome to see a new Claude model - since 3.5 its been my go-to for all code related tasks.

I'd really like to use Claude Code in some of my projects vs just sharing snippets via the UI but I'm curious how might doing this from our source directory affect our IP including NDA's, trade secret protections, prior disclosure rules on (future) patents, open source licensing restrictions re: redistribution etc?

Also hi Erik! - Rob

Well I'm no champion of this theory.. bit skeptical TBH having been shown during some parenting coaching BUT the idea is kids who have a loving, trusting and attentive relationship with their primary care giver will be more likely to trust and seek help from others later in life and vice versa.

You've just given the perfect example of Attachment Theory [0].

https://en.wikipedia.org/wiki/Attachment_theory

I wish there was a bulk buy discount then these would make for awesome party bag fillers at my kids birthday parties. Much better than giving out candy...

I think it's a fair concept to try if you need to add a few things to complete the game. As long as you're using it yourself and not reselling that. But IANAL and haven't read the copyright.

It's a theory on how to optimally rebalance your investment portfolio every day.

Original paper by Thomas Cover: https://isl.stanford.edu/~cover/papers/paper93.pdf

A good breakdown with links to code examples by Andy Jones: https://andrewcharlesjones.github.io/journal/universal-portf...

Perhaps but with a modern/futuristic twist.

The cells in our body have one by one been replaced with new ones and the old ones have died off.

This is not the case for our "talking" neurons which is what I was trying to limit this thought experiment to. I think a lot more folks would be ok with preserving their biological brain as is within a robot/clone if that was the only option and understand the body gets (mostly) replaced. Although a few in this thread have alluded to the fact we might be missing important relationships with the rest of the body such as the nervous system and gut biome.

That all makes sense. But let's run with this way beyond the foreseeable tech. What if you can replace each neuron in situ one by one up to X%. Then what if it was reversible (the neurons were initially just bypassed, commented out). Someone could then dial it up to 5%.. 50% and if they still felt the same throughout and then went up to 100%. In that scenario would they have copied themselves?

I find it fascinatingly coincidental that neurons are the only cells in the body that don't rejuvenate unless there is some sort of injury [0].

[0]: https://www.dzne.de/en/im-fokus/meldungen/2021/neurons-able-...