bredren

This intentionality in the application of AI is very confusing for folks because at first glance it seems like it should just work.

It seems to, even.

Whereas if you hand a router to someone with a flush trim but in it and ask them to clean up the edge of a table they will take one look at it and nope away from that dangerous spinning thing.

If they have the mind to give it a shot and despite a quality tool and bit they bite into the table and ruin the line (or something much worse) no one will be surprised—-they have no experience or recognition of what expertise is in woodworking.

But with AI, it is much more hazy what expertise is.

The methodology for quality results is changing each week and the articulation in personal tooling involved makes it challenging to adopt another “expert”’s workflows.

Did the article get edited? There is not much description of the field trip.

It also enables a similar model to Facebook's insight into third party mobile app growth. The state could look for early growth trends in a given category or model type.

Then their org has the option to burnish or bury models that align with their goals.

Which garage door opener brands / models would you recommend?

> The object was described as being "similar to the Eye or [sic] Sauron from Lord of the Rings, except without the pupil, or maybe an orange Storm Electrify bowling ball."

It would have been some fantastic spy tech, alright.

It is very important, the low latency.

I prompt orchestrations most of the day, and am very particular about the fidelity of my context stack.

Yet I’ve used advanced voice mode on ChatGPT via the iOS app a lot. And I have not had a problem with it understanding my requests or my side of the conversation.

I have looked at the dictation of my side and seen it has blatant mistakes, but I think the models have overcome that the same way they do conference audio stt transcripts.

I have had times where the ~sandbox of those conversations and their far more limited ability to build useful corpus of context via web searches or by accessing prior conversation content.

The biggest problem I have had with adv voice was when I accidentally set the personality to some kind of non emotional setting. (The current config seems much more nuanced)

The AI who normally speaks with relative warmth and easy going nature turned into an emotionless and detached entity.

It was unable to explain why it was acting this way. I suspect the low latency did disservice there because when it is paired with something adversarial it was deeply troubling.

They may read like so many others, but what I don't understand is why special agents in the FBI would take it upon themselves to report strange phenomena.

This seems like it would be a CLM, as the authority of their testimony is central to their function as federal LE.

For example, see this document: https://www.war.gov/medialink/ufo/release_1/western_us_event...

(from series of documents from incident data 9/1/23)

I identified this in August last year but it was specifically excluded by Anthropic's Vulnerability Disclosure Program Policy at the time.

You can still see the exclusion on HackerOne: https://hackerone.com/anthropic-vdp/policy_scopes

   Out of Scope:

    Abusing intended functionality of Claude CLI
    Using aliased commands, symlinks or other environment-specific settings to bypass permission prompts
    Local storage of Claude Code credentials, configuration and logs

Symlinks have been very important to manage skills from disparate sources and managing multiple CLIs.

Codex did not originally support symlink'd skills but added it in response to user requests on Jan 9th.

1. Worktrees

2. Multiple simultaneous projects

3. Orchestration that includes handling of CI workflow

4. Active work to further improve or refine tooling

5. Experimentation producing muscle memory as experience versus code output

This line makes a valid point. People record strangers all the time. In an obvious way or trying to be sneaky.

Just because you don’t notice it doesn’t mean it doesn’t happen.

However, this is still a different thing than smart glasses which can further be segmented into who designed the smart glasses.

I see, good to be curious.

"No vibe coding" is an ambiguous claim. I was asking whether they meant no AI-generated implementation, no AI assistance whatsoever, or just "not primarily generated by prompts."

Why do you ask?

One of the features is “no vibe coding, classic development style.”

I think that’s kind of interesting, especially when building a retro enablement.

But I wonder does this mean no AI was used at all? Even for say, code review?

No judgment either way just curious for clarification.

The prompt did not specify advanced gameplay.

I do not see instructions to assist in task decomposition and agent ~"motivation" to stay aligned over long periods as cargo culting.

See up thread for anecdotes [1].

> Decompose the user's query into all required sub-requests and confirm that each one is completed. Do not stop after completing only part of the request. Only terminate your turn when you are sure the problem is solved.

I see this as a portrayal of the strength of 5.5, since it suggests the ability to be assigned this clearly important role to ~one shot requests like this.

I've been using a cli-ai-first task tool I wrote to process complex "parent" or "umberella" into decomposed subtasks and then execute on them.

This has allowed my workflows to float above the ups and downs of model performance.

That said, having the AI do the planning for a big request like this internally is not good outside a demo.

Because, you want the planning of the AI to be part of the historical context and available for forensics due to stalls, unwound details or other unexpected issues at any point along the way.

[1] https://news.ycombinator.com/item?id=47879819

> ...this is equivalent to providing all of your employees with a flamethrower, and then saying they bear all responsibility for the fires they start.

This is essentially the policy of most SWE groups but with PRs merged, though right?

You can / should use AI to accelerate SWE workflows and assist in reviews but if you merge something that is bad or breaks production that is on you.

> "Hey, don't blame us for giving them flamethrowers, it's company policy not to burn everything to the ground!".

Flamethrowers are inherently dangerous to the operator and are ~intended to be used burn things to the ground.

I'm no expert on arms but there is probably a simile with a better fit out there.

I am counting on physical, semi technical contract work to pay once SWE opportunities shrink to the point where it’s not worth it anymore.

Now is the time to get handy if not already. Robotics /physical automation will lag info by a good stretch.

It has shown surprising stickiness. Occupying some middle ground between full adoption and still ~in the code.

I am starting to see some potential in moving back away from pure terminal, a mixed modality with AI. But it is not in the direction of IDE in any traditional sense.

A secret backup test to the pelican? This is as noteworthy as 4.7 dropping.

I thought this would provide easy query access, but it does not seem to.

Is there a CLI that queries hn.algolia.com and returns structured data?

This sounded pretty good, a ~mullvad for LLM. Then:

> Strongwall.ai is led by Andrew Northwall, CEO and Bryce Nyeggen, CTO. Andrew has 20+ years in tech, former COO of Trump Media & Technology Group, architect behind the relaunch of Parler, and senior technologist for large-scale infrastructure and AI systems.

“What cannot be known hollows the mind. Fill it not with guesswork.”

I suspect it has already happened. People just don’t realize it yet.

Idk it was a great, super underrated product.

Were you there when BM produced the macOS compatible eGPU units in collaboration with Apple?

They underestimate the likelihood of black swan because it is very hard for adults to concretely imagine things that have not happened before and then even temporarily fully believe ~"dreams will come true."

One of my go-tos on this is the Fukushima nuclear accident. IIUC there were plenty of folks in Japan who knew of the high risk. Perhaps many interested in nuclear energy outside of Japan, too.

But the average adult if asked about the prospect of a major nuclear incident occurring say, "tomorrow," would narrow their eyes in skepticism. There's almost an instinctual level seeding of doubt.

This can be a good thing. LK-99 was an excellent test of the dissonance from dramatic changes in reality and costs of inaccuracy.

The greatest VCs I have known are exceptional at suspending disbelief to test their ability to basically shape world building.

I think AI needs to greatly accelerate open hardware design and make advanced manufacturing more accessible to really make a dent.

User facing software is not the limiting factor in AI assisted replacement of Apple products.

From what I can tell, this was not clearly settled.

Your example author, actually corrected themselves saying LLMs “possibly” could perform successfully: https://news.ycombinator.com/item?id=47732696

We saw yesterday that expert orchestration around small, publicly available models can produce results on the level of the unreleased model.

I take a contra view and instead see this as fuel on the fire for tinkering to squeeze advanced functionality out of more available things.

It has always been like this, the amateur improvising tooling and equipment to outdo companies with comparably infinite resources.

The article positions the smaller models as capable under expert orchestration, which to be any kind of comparable must include validation.

It’s not just the edge but the corners where the finger accommodation is for opening the lid.

There’s a sharp corner there is unnecessary.