@f

working towards better AI futures. AI safety at @snyksec. Organizing @lisbonai_. Prev: @capitalfactory @gumroad @techcrunch @oreillymedia

helloform.com
Joined September 2006
  • Tweets16.2K
  • Following944
  • Followers134K
443Media
Most things that cause me anxiety are coordination problems.
43
221
4
132
368,634
Agents resend the whole context on every call, often dozens of times per request. If you change one token near the top, you pay full price for everything under it. Context layout is a cost decision. I wrote up a few months of harness design research. Highlights below 🧵
5
3
14
1,948
more replies
On memory design: a "fact" from a web page looks identical to one the user told the agent. Record where each came from, and treat memories as facts, but not permission. Hoping to write future posts on tools, guardrails, runtime architecture. Full post, with diagrams and code ↓
1
122
Here's the full post. If you have thoughts or your own tips, I'd love to hear them. helloform.com/blog/harness-d…

Lessons in harness design: context, compaction and memory

Over the past few months, I've spent a good chunk of my time at Snyk researching harness design. Most of the discourse is still about model releases and…

helloform.com
1
1
113
how's that for job displacement
The Kobeissi Letter
@KobeissiLetterOct 26
BREAKING: Microsoft, $MSFT, is offering buyouts to 60,000 workers as part of the company’s efforts to cut costs amid AI adoption, per Bloomberg. Personnel on select teams in the US, Canada, India, and the UK at a vice president level and below will be eligible. This reflects ~27% of Microsoft's total workforce.
1
3
1,015
I use voice mode all the time. For the longest time there was no competition for ChatGPT voice mode. Claude is getting better but not quite there yet - unfortunately, because Opus 5.5 and Fable are my daily drivers. I’ve had lots of success with @bot, though. The way the harness works means there are some quirks to it work around but it is the best at just getting things done, mostly on the back of the way I’ve structured agents and the delegation between them. In short: for brainstorming, ChatGPT. For productivity on the move, Grok Bot. I assume Duet is going to change my views somewhat but this is where I stand today.
Ben Vinegar
@bentlegenOct 26
🚙 had a few hours of driving today, so tried being productive w/ both Claude and ChatGPT voice mode - drafted some follow-up emails - researched some customer prospects - practiced public speaking (!) useful! but even hands free, it was distracting & impacted my driving 😞
2
5
1,339
this morning, riding a bike - "hey siri, play undertow by tool" - "playing under-dough by tool" - "play undertow by tool" - "playing under-dough by tool" - "fine. play lateralus by tool" I guess I need to look into their bread-oriented discography
1
4
1,636
"wow, nobody warned us of all these risks" but actually, lots of people did, quite often.
Fred Oliveira 🧠
@fJul 21
I've been saying it a lot, but the damned if you do (talk about AI risk) damned if you don't (talk about AI risk) conundrum is going to get us in trouble. If we stop disseminating important information because grifters and morons think it's all hype, we can't coordinate.
2
1,678
all of this and we are still in the "before the going gets tough" times
2
1,347
so real talk - if super intelligence is out of the running, what are we actually going to call it when it really is smarter than us?
7
6
2,742
wait, is @elonmusk's plan to colonize Mars to have us all simply drive up to the planet?
4
3,057
the newest version of the Claude desktop app is a significant step forward. Long-horizon task progress is easier to follow; the sidebar is much better; the terminal panes are *good*. The only thing I think adds friction than it is worth is forcing people to create environments under Code, but this looks like a stepping stone into promoting cloud environments a little harder. Great job, @bcherny and team.
1
5
2,857
Fred Oliveira 🧠 retweeted
Cristóbal Valenzuela
@c_valenzuelabOct 14
25
371
25
10,994
112,019
Fred Oliveira 🧠 retweeted
roon
@tszzlOct 13
the researchers at all the labs would tell you in private and sometimes in public that alignment has not been solved. if this is true, then racing into RSI is a folly that is unprecedented in world history. we will need to significantly slow the frontier of research very soon
140
333
82
3,255
441,147
My wife just asked me if the agent I keep talking about is called “Croc bot”, and I’ll be honest - I can’t wait for lunch to be done so I can go home and build *that*. With apologies to the @bot team.
3
7
3,002
Scott has had many paragraphs I like (of course). But this one, I love.
I agree that in-person debates are confrontational and bad for truth-seeking. But I didn’t propose a debate in order to seek truth. I proposed it because, under California Penal Code § 415(1), it’s illegal for me to challenge you to a duel. I think your public writing on this topic has been dishonorable. Out of obligation, I will respond to the meaty arguments that you have set out for me. But what would be viscerally satisfying would be to make you get up on a stage where I read your own words to you in real time and ask “Really? Really?” after each sentence. Then I could watch you squirm as you try to square your output with your status as one of America’s top public intellectuals.

ALT I agree that in-person debates are confrontational and bad for truth-seeking. But I didn’t propose a debate in order to seek truth. I proposed it because, under California Penal Code § 415(1), it’s illegal for me to challenge you to a duel. I think your public writing on this topic has been dishonorable. Out of obligation, I will respond to the meaty arguments that you have set out for me. But what would be viscerally satisfying would be to make you get up on a stage where I read your own words to you in real time and ask “Really? Really?” after each sentence. Then I could watch you squirm as you try to square your output with your status as one of America’s top public intellectuals.

1
2
3,694
Source, if you need it: astralcodexten.com/p/an-open…

An Open Letter To Steven Pinker On AI

...

astralcodexten.com
2,156
Load more