Ben Davis's banner

Ben Davis

@davis7 • 22,985 subscribers

yells at @theo both on and off camera (co-host of the nerd snipe podcast)

Shorts

I entirely stole this from Codex desktop btw, it's been there forever but no one knows about it lmao All u have to do to get stuff like this in ur threads (in Codex or T3 Code) is ask the agent to "visualize" in the thread Great for mockups, graphs, images, tables, etc.

I entirely stole this from Codex desktop btw, it's been there forever but no one knows about it lmao All u have to do to get stuff like this in ur threads (in Codex or T3 Code) is ask the agent to "visualize" in the thread Great for mockups, graphs, images, tables, etc.

28,074 просмотров

To me so far the big news with Grok 4.7 is it's speed. The new "fast" mode is actually extremely fast (idk what the TPS is but it's really good) It's very obviously not Astra/Fable class, SpaceXAi (or anyone else really) has yet to make one so far. Grok 4.7 is pretty clearly competing with Opus/Sol, and I would definitely take Grok 4.7 over either of them Price is very good, my gut says it's more efficient but I don't have hard numbers on that yet, and it's got all the main capabilities u need to actually be useful these days: subagents, long running tasks, looping, etc. Supposedly they trained it on the Grok Bot harness so it's really good at conversation + knowledge work. Really curious how that plays out, good product is SpaceXAi's biggest advantage right now so getting the models tailor made for those could work. Especially if that lets them keep the model on the cheaper side so they can serve more of it

To me so far the big news with Grok 4.7 is it's speed. The new "fast" mode is actually extremely fast (idk what the TPS is but it's really good) It's very obviously not Astra/Fable class, SpaceXAi (or anyone else really) has yet to make one so far. Grok 4.7 is pretty clearly competing with Opus/Sol, and I would definitely take Grok 4.7 over either of them Price is very good, my gut says it's more efficient but I don't have hard numbers on that yet, and it's got all the main capabilities u need to actually be useful these days: subagents, long running tasks, looping, etc. Supposedly they trained it on the Grok Bot harness so it's really good at conversation + knowledge work. Really curious how that plays out, good product is SpaceXAi's biggest advantage right now so getting the models tailor made for those could work. Especially if that lets them keep the model on the cheaper side so they can serve more of it

54,012 просмотров

The new btca experience, now just a skill b/c it's way better: Turns out the best way to let coding agents search github for context is to let them search github repos for context

The new btca experience, now just a skill b/c it's way better: Turns out the best way to let coding agents search github for context is to let them search github repos for context

87,952 просмотров

Updated the subagents system in my custom Pi extension to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...

Updated the subagents system in my custom Pi extension to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...

24,827 просмотров

Can finally play doom in Claude Code

Can finally play doom in Claude Code

36,817 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

OPENAI NO YOU CAN'T LET GOOGLE WIN LIKE THIS

OPENAI NO YOU CAN'T LET GOOGLE WIN LIKE THIS

1,307,191 просмотров • 1 месяц назад

Started out thinking I was gonna make a video on Dots and my issues with them, but kinda ended up just talking about "personal assistant" agents generally TL;DR: grok bot is the best one by far. Muse is good, but if ur reading this post it's not for u, and Dots needs work

Started out thinking I was gonna make a video on Dots and my issues with them, but kinda ended up just talking about "personal assistant" agents generally TL;DR: grok bot is the best one by far. Muse is good, but if ur reading this post it's not for u, and Dots needs work

239,303 просмотров • 11 дней назад

Just had a new holy shit moment with GPT-6 Astra... Asked it to setup the vid I just recorded in Final Cut (import clips, color grading, sync clips, etc.) to get ready to edit Hadn't actually watched it work like this live before, below is the live reaction from me + my editor

Just had a new holy shit moment with GPT-6 Astra... Asked it to setup the vid I just recorded in Final Cut (import clips, color grading, sync clips, etc.) to get ready to edit Hadn't actually watched it work like this live before, below is the live reaction from me + my editor

416,853 просмотров • 1 месяц назад

The Muse Wonder release was imo quite slept on, at least for the full version, not the not full version that one's bad, but the full one is a great model. It's a new "flavor" of model that gets very close to the frontier, but still doesn't quite reach it...

The Muse Wonder release was imo quite slept on, at least for the full version, not the not full version that one's bad, but the full one is a great model. It's a new "flavor" of model that gets very close to the frontier, but still doesn't quite reach it...

16,154 просмотров • 4 дней назад

Had Astra on ultrafast (on med reasoning) rebuild 1-1 from scratch on the modretro they gave us at Dev Day yesterday - Took ~3 mins - Used 4 subagents - Used ~10% of my weekly limit ($500/mo. plan) Ultrafast should rarely be used, but I'm ngl when u do use it it's really cool

Had Astra on ultrafast (on med reasoning) rebuild 1-1 from scratch on the modretro they gave us at Dev Day yesterday - Took ~3 mins - Used 4 subagents - Used ~10% of my weekly limit ($500/mo. plan) Ultrafast should rarely be used, but I'm ngl when u do use it it's really cool

39,929 просмотров • 18 дней назад

This is very late, but I'm finally done with my 5.5 vid - use low reasoning - the name sucks - it's fast - best code I've ever seen a model write came from this model - openai's new pre-training is amazing - price looks worse than it is - over sensitive to every little thing in it's context window - feels wildly different compared to 5.4 - turn reasoning off. try it. turn the reasoning off. do it.

This is very late, but I'm finally done with my 5.5 vid - use low reasoning - the name sucks - it's fast - best code I've ever seen a model write came from this model - openai's new pre-training is amazing - price looks worse than it is - over sensitive to every little thing in it's context window - feels wildly different compared to 5.4 - turn reasoning off. try it. turn the reasoning off. do it.

285,279 просмотров • 5 месяцев назад

Getting bored of the standard one shot games/3d stuff, I think at least in the medium term the much more interesting side of things is the modding I had Opus 5.5 take the Majora's Mask recomp and build a full new area. It's got puzzles, enemies, rewards, and a mini dungeon...

Getting bored of the standard one shot games/3d stuff, I think at least in the medium term the much more interesting side of things is the modding I had Opus 5.5 take the Majora's Mask recomp and build a full new area. It's got puzzles, enemies, rewards, and a mini dungeon...

33,006 просмотров • 23 дней назад

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time

20,050 просмотров • 16 дней назад

Recently I was working on something with Astra and it implemented a Swift app, with a BE server also in Swift. It worked fine, but I'm not a Swift guy so I had it rewrite the BE in TS After that went perfectly, I've been thinking a lot more about the stuff that kinda doesn't matter as much anymore Programming languages, libraries, formatters, etc. All of it feels pretty effortless to switch in/out and I just don't care as much as I did before. Wanted to try and go over this in a video, as well as talk a bit about why I don't cover things like Svelte nearly as much as I used to (when I'm using it now more than ever)

Recently I was working on something with Astra and it implemented a Swift app, with a BE server also in Swift. It worked fine, but I'm not a Swift guy so I had it rewrite the BE in TS After that went perfectly, I've been thinking a lot more about the stuff that kinda doesn't matter as much anymore Programming languages, libraries, formatters, etc. All of it feels pretty effortless to switch in/out and I just don't care as much as I did before. Wanted to try and go over this in a video, as well as talk a bit about why I don't cover things like Svelte nearly as much as I used to (when I'm using it now more than ever)

28,447 просмотров • 29 дней назад

GPT-6 Astra is my favorite model of all time and it's not really close It's a step function similar to Fable or Opus 4.5, the computer use stuff has unlocked truly novel workflows

GPT-6 Astra is my favorite model of all time and it's not really close It's a step function similar to Fable or Opus 4.5, the computer use stuff has unlocked truly novel workflows

39,248 просмотров • 1 месяц назад

My Opus 5 video is late, but that ended up being good because I would have made a very different video on release day I really like the idea of this model, but actually using it kinda sucks...

My Opus 5 video is late, but that ended up being good because I would have made a very different video on release day I really like the idea of this model, but actually using it kinda sucks...

57,696 просмотров • 2 месяцев назад

Put together a video on the ways I'm using all the modern AI stuff for my day to day work (both dev and non-dev stuff) Gone through a huge shift over the last few months to where Codex desktop app has basically become my "interface" for my computer...

Put together a video on the ways I'm using all the modern AI stuff for my day to day work (both dev and non-dev stuff) Gone through a huge shift over the last few months to where Codex desktop app has basically become my "interface" for my computer...

19,843 просмотров • 1 месяц назад

Put together a vid on how/why I'm using Hermes agent My networking setup is very overkill for most people, I mostly did it because I'm paranoid (and tbh it was fun) But it's really useful, highly recommend setting one up it's a great piece of software

Put together a vid on how/why I'm using Hermes agent My networking setup is very overkill for most people, I mostly did it because I'm paranoid (and tbh it was fun) But it's really useful, highly recommend setting one up it's a great piece of software

56,002 просмотров • 4 месяцев назад

Made a video on my custom Pi extensions: - Subagents (Pi, Codex, Claude Code) - Workflows - Question ask tool - Background Terminals - Custom UI and more Combining all the harnesses together has been one of my favorite ways to work, Pi feels like the best way to do it...

Made a video on my custom Pi extensions: - Subagents (Pi, Codex, Claude Code) - Workflows - Question ask tool - Background Terminals - Custom UI and more Combining all the harnesses together has been one of my favorite ways to work, Pi feels like the best way to do it...

41,480 просмотров • 2 месяцев назад

Haiku 4.5 has finally been dethroned by GPT 5.4 mini: - faster - cheaper - smarter - better at tool calling Gemini 3.0 flash still has a place in “turn this video/audio/blob of text into json”, but for any small model task that requires an agent loop (sub agents, search, quick fixes, browser use, etc.) GPT-5.4 mini is the new king

Haiku 4.5 has finally been dethroned by GPT 5.4 mini: - faster - cheaper - smarter - better at tool calling Gemini 3.0 flash still has a place in “turn this video/audio/blob of text into json”, but for any small model task that requires an agent loop (sub agents, search, quick fixes, browser use, etc.) GPT-5.4 mini is the new king

67,624 просмотров • 7 месяцев назад

A video I never thought I would make: defending GStack I honestly wrote it off as a meme, but the concept is actually really really cool Idk exactly what this turns into long term, but the idea of "markdown file == program" has so much unexplored potential

A video I never thought I would make: defending GStack I honestly wrote it off as a meme, but the concept is actually really really cool Idk exactly what this turns into long term, but the idea of "markdown file == program" has so much unexplored potential

46,937 просмотров • 5 месяцев назад

Been testing 5.4 for about a week now and it's really good. It's the first model that kinda "just works". A hybrid of 5.3's precision and opus' speed/initiative I've done ~300 million tokens with it and it's crushed almost everything I've given it. Except for UI. It's hilariously bad at UI stuff.

Been testing 5.4 for about a week now and it's really good. It's the first model that kinda "just works". A hybrid of 5.3's precision and opus' speed/initiative I've done ~300 million tokens with it and it's crushed almost everything I've given it. Except for UI. It's hilariously bad at UI stuff.

54,357 просмотров • 7 месяцев назад

it went about as expected

it went about as expected

40,857 просмотров • 5 месяцев назад

I'm tired and need to go to bed, it's 4AM, but it's live: - setup as many git repos as "resources" as you want - "@" them in the chat UI and haiku 4.5 will use them to answer your question - $8/mo. for the hosted version, cli is BYOK - open source

I'm tired and need to go to bed, it's 4AM, but it's live: - setup as many git repos as "resources" as you want - "@" them in the chat UI and haiku 4.5 will use them to answer your question - $8/mo. for the hosted version, cli is BYOK - open source

54,300 просмотров • 9 месяцев назад

I was wrong about GPT-5.5 Kinda I still stand by everything I've said about low reasoning, it's incredible and I still use it all the time esp with Pi But I'm also doing a ton with xHigh reasoning, and especially computer use in the codex desktop app

I was wrong about GPT-5.5 Kinda I still stand by everything I've said about low reasoning, it's incredible and I still use it all the time esp with Pi But I'm also doing a ton with xHigh reasoning, and especially computer use in the codex desktop app

30,205 просмотров • 4 месяцев назад